Compare commits
27 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
41309cfd7d | ||
|
|
36107a5cae | ||
|
|
238cfc6933 | ||
|
|
f28591e648 | ||
|
|
d38e2eeab1 | ||
|
|
4fe8a1e6a4 | ||
|
|
1557826c5d | ||
|
|
bec54d7abb | ||
|
|
23f9ad547c | ||
|
|
28def60eec | ||
|
|
902063fd0a | ||
|
|
9ff0cc0b74 | ||
|
|
ae3d038711 | ||
|
|
af57b96721 | ||
|
|
d5d420d2e1 | ||
|
|
e053fd0eb7 | ||
|
|
ee5511fc59 | ||
|
|
f54c340851 | ||
|
|
ad83399403 | ||
|
|
40fd263b4e | ||
|
|
0405d4a577 | ||
|
|
00079b5bff | ||
|
|
27ce8af114 | ||
|
|
5e888ef6bb | ||
|
|
1134e1e735 | ||
|
|
4803af0b95 | ||
|
|
df0f084ac6 |
64
.github/MAINTENANCE.md
vendored
Normal file
64
.github/MAINTENANCE.md
vendored
Normal file
@@ -0,0 +1,64 @@
|
||||
# Repository Maintenance Protocol & Governance
|
||||
|
||||
> [!URGENT]
|
||||
> **READ THIS FIRST**: The single most critical rule of this repository is: **IF YOU DO NOT PUSH YOUR CHANGES, THEY DO NOT EXIST.**
|
||||
>
|
||||
> **ALWAYS** run `git push` immediately after committing. No exceptions.
|
||||
|
||||
## 1. Governance & Roles
|
||||
|
||||
### Maintainers
|
||||
|
||||
- **Core Team**: Responsible for "Official" skills and merging PRs.
|
||||
- **Review Policy**: All PRs must pass the [Quality Bar](../docs/QUALITY_BAR.md) checks.
|
||||
|
||||
### Code of Conduct
|
||||
|
||||
All contributors must adhere to the [Code of Conduct](../CODE_OF_CONDUCT.md).
|
||||
|
||||
## 2. Analysis & Planning (Planner Role)
|
||||
|
||||
1. **Check Duplicates**: `grep -r "search_term" skills_index.json`
|
||||
2. **Consult Quality Bar**: Review `docs/QUALITY_BAR.md` to ensure the plan meets the "Validated" criteria.
|
||||
3. **Risk Assessment**: Determine if the skill is `safe`, `critical`, or `offensive`. (See [Security Guardrails](../docs/SECURITY_GUARDRAILS.md))
|
||||
|
||||
## 3. Implementation Workflow (Executor Role)
|
||||
|
||||
1. **Create Skill**: Follow the standard folder structure `skills/<kebab-name>/`.
|
||||
2. **SKILL.md**: MUST header to the Quality Bar standard.
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: my-skill
|
||||
description: clear description
|
||||
risk: safe
|
||||
source: self
|
||||
---
|
||||
```
|
||||
|
||||
3. **Security Check**: If `risk: offensive`, add the "Authorized Use Only" disclaimer.
|
||||
|
||||
## 4. Validation Chain (MANDATORY)
|
||||
|
||||
Run validation before committing:
|
||||
|
||||
```bash
|
||||
python3 scripts/validate_skills.py
|
||||
python3 scripts/generate_index.py
|
||||
python3 scripts/update_readme.py
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> **Transition Period**: We are currently in a "Soft Launch" phase. Legacy skills may trigger warnings.
|
||||
> **New skills MUST have zero warnings.**
|
||||
|
||||
## 5. Documentation & Credits
|
||||
|
||||
- [ ] **SOURCE.md**: Update the master source list if importing external skills.
|
||||
- [ ] **README.md**: Ensure credits are added in the `Credits` section.
|
||||
|
||||
## 6. Finalization (The "Antigravity" Standard)
|
||||
|
||||
- [ ] **Git Add**: `git add .`
|
||||
- [ ] **Commit**: `git commit -m "feat: add [skill-name] skill"`
|
||||
- [ ] **PUSH NOW**: `git push` (Do not wait).
|
||||
21
.github/PULL_REQUEST_TEMPLATE.md
vendored
21
.github/PULL_REQUEST_TEMPLATE.md
vendored
@@ -1,17 +1,22 @@
|
||||
## Description
|
||||
# Pull Request Description
|
||||
|
||||
Please describe your changes. What skill are you adding or modifying?
|
||||
Please include a summary of the change and which skill is added or fixed.
|
||||
|
||||
## Checklist
|
||||
## Quality Bar Checklist ✅
|
||||
|
||||
- [ ] My skill follows the [creation guidelines](https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-creator)
|
||||
- [ ] I have run `validate_skills.py`
|
||||
- [ ] I have added my name to the credits (if applicable)
|
||||
**All items must be checked before merging.**
|
||||
|
||||
- [ ] **Standards**: I have read `docs/QUALITY_BAR.md` and `docs/SECURITY_GUARDRAILS.md`.
|
||||
- [ ] **Metadata**: The `SKILL.md` frontmatter is valid (checked with `scripts/validate_skills.py`).
|
||||
- [ ] **Risk Label**: I have assigned the correct `risk:` tag (`none`, `safe`, `critical`, `offensive`).
|
||||
- [ ] **Triggers**: The "When to use" section is clear and specific.
|
||||
- [ ] **Security**: If this is an _offensive_ skill, I included the "Authorized Use Only" disclaimer.
|
||||
- [ ] **Local Test**: I have verified the skill works locally.
|
||||
- [ ] **Credits**: I have added the source credit in `README.md` (if applicable).
|
||||
|
||||
## Type of Change
|
||||
|
||||
- [ ] New Skill
|
||||
- [ ] Bug Fix
|
||||
- [ ] New Skill (Feature)
|
||||
- [ ] Documentation Update
|
||||
- [ ] Infrastructure
|
||||
|
||||
|
||||
34
.github/workflows/ci.yml
vendored
Normal file
34
.github/workflows/ci.yml
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
name: Skills Registry CI
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: ["main", "feat/*"]
|
||||
pull_request:
|
||||
branches: ["main"]
|
||||
|
||||
jobs:
|
||||
validate-and-build:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.10"
|
||||
|
||||
- name: 🔍 Validate Skills (Soft Mode)
|
||||
run: |
|
||||
python3 scripts/validate_skills.py
|
||||
|
||||
- name: 🏗️ Generate Index
|
||||
run: |
|
||||
python3 scripts/generate_index.py
|
||||
|
||||
- name: 📝 Update README
|
||||
run: |
|
||||
python3 scripts/update_readme.py
|
||||
|
||||
- name: 🚨 Check for Uncommitted Drift
|
||||
run: |
|
||||
git diff --exit-code || (echo "❌ Detected uncommitted changes in README.md or skills_index.json. Please run scripts locally and commit." && exit 1)
|
||||
33
CODE_OF_CONDUCT.md
Normal file
33
CODE_OF_CONDUCT.md
Normal file
@@ -0,0 +1,33 @@
|
||||
# Code of Conduct
|
||||
|
||||
## Our Pledge
|
||||
|
||||
In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone.
|
||||
|
||||
## Our Standards
|
||||
|
||||
Examples of behavior that contributes to creating a positive environment include:
|
||||
|
||||
- Using welcoming and inclusive language
|
||||
- Being respectful of differing viewpoints and experiences
|
||||
- Gracefully accepting constructive criticism
|
||||
- Focusing on what is best for the community
|
||||
- Showing empathy towards other community members
|
||||
|
||||
Examples of unacceptable behavior by participants include:
|
||||
|
||||
- The use of sexualized language or imagery and unwelcome sexual attention or advances
|
||||
- Trolling, insulting/derogatory comments, and personal or political attacks
|
||||
- Public or private harassment
|
||||
- Publishing others' private information without explicit permission
|
||||
- Other conduct which could reasonably be considered inappropriate in a professional setting
|
||||
|
||||
## Enforcement
|
||||
|
||||
Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior.
|
||||
|
||||
## Attribution
|
||||
|
||||
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.1.
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
@@ -1,54 +0,0 @@
|
||||
# Repository Maintenance Protocol
|
||||
|
||||
To ensure consistency and quality, the following steps MUST be performed for **every single change** involving skills or documentation.
|
||||
|
||||
## 1. Skill Creation & Modification
|
||||
|
||||
- [ ] **Check Duplicates**: Before adding a skill, check `skills_index.json` or `ls skills/` to ensure it doesn't exist.
|
||||
- [ ] **Folder Structure**: Each skill must have its own folder in `skills/<skill-name>`.
|
||||
- [ ] **SKILL.md**: Every skill directory MUST contain a `SKILL.md` file with valid frontmatter:
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: Skill Name
|
||||
description: Brief description.
|
||||
---
|
||||
```
|
||||
|
||||
## 2. Validation & Indexing (CRITICAL)
|
||||
|
||||
Running the scripts is **MANDATORY** after any change to `skills/`.
|
||||
|
||||
- [ ] **Validate Skills**: Run the validation script to check for formatting errors.
|
||||
|
||||
```bash
|
||||
python3 scripts/validate_skills.py
|
||||
```
|
||||
|
||||
- [ ] **Generate Index**: Update `skills_index.json`. This is the source of truth for the agent.
|
||||
|
||||
```bash
|
||||
python3 scripts/generate_index.py
|
||||
```
|
||||
|
||||
## 3. Documentation Updates
|
||||
|
||||
- [ ] **Update README**: Run the automation script to sync counts and the registry table.
|
||||
|
||||
```bash
|
||||
python3 scripts/update_readme.py
|
||||
```
|
||||
|
||||
- [ ] **Credits & Sources**: If the skill was imported from a community repo, add a credit link in `# Credits & Sources` manually if needed.
|
||||
- Example: `- **[repo-name](url)**: Source for [skill-name].`
|
||||
|
||||
## 4. Git Operations
|
||||
|
||||
- [ ] **Check Status**: `git status` to see what changed.
|
||||
- [ ] **Add All Files**: Ensure new skill folders are added (`git add skills/`).
|
||||
- [ ] **Commit**: Use a descriptive Conventional Commit message (e.g., `feat: add new security skills`, `docs: update readme count`).
|
||||
- [ ] **Push**: `git push` to origin. **NEVER FORGET THIS.**
|
||||
|
||||
## 5. Agent Artifacts (Internal)
|
||||
|
||||
- [ ] **Walkthrough**: Update `walkthrough.md` in the brain/artifact directory to reflect the session's achievements.
|
||||
602
README.md
602
README.md
@@ -1,6 +1,6 @@
|
||||
# 🌌 Antigravity Awesome Skills: 251+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
|
||||
# 🌌 Antigravity Awesome Skills: 253+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
|
||||
|
||||
> **The Ultimate Collection of 251+ Universal Agentic Skills for AI Coding Assistants — Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode**
|
||||
> **The Ultimate Collection of 253+ Universal Agentic Skills for AI Coding Assistants — Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode**
|
||||
|
||||
[](https://opensource.org/licenses/MIT)
|
||||
[](https://claude.ai)
|
||||
@@ -11,7 +11,7 @@
|
||||
[](https://github.com/opencode-ai/opencode)
|
||||
[](https://github.com/anthropics/antigravity)
|
||||
|
||||
**Antigravity Awesome Skills** is a curated, battle-tested library of **243 high-performance agentic skills** designed to work seamlessly across all major AI coding assistants:
|
||||
**Antigravity Awesome Skills** is a curated, battle-tested library of **251 high-performance agentic skills** designed to work seamlessly across all major AI coding assistants:
|
||||
|
||||
- 🟣 **Claude Code** (Anthropic CLI)
|
||||
- 🔵 **Gemini CLI** (Google DeepMind)
|
||||
@@ -25,20 +25,14 @@ This repository provides essential skills to transform your AI assistant into a
|
||||
|
||||
## 📍 Table of Contents
|
||||
|
||||
- [🌌 Antigravity Awesome Skills: 244+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot \& More](#-antigravity-awesome-skills-244-agentic-skills-for-claude-code-gemini-cli-cursor-copilot--more)
|
||||
- [🌌 Antigravity Awesome Skills](#-antigravity-awesome-skills-253-agentic-skills-for-claude-code-gemini-cli-cursor-copilot--more)
|
||||
- [📍 Table of Contents](#-table-of-contents)
|
||||
- [New Here? Start Here!](#new-here-start-here)
|
||||
- [🔌 Compatibility](#-compatibility)
|
||||
- [Features \& Categories](#features--categories)
|
||||
- [Full Skill Registry (244/244)](#full-skill-registry-244244)
|
||||
- [Installation](#installation)
|
||||
- [How to Contribute](#how-to-contribute)
|
||||
- [Credits \& Sources](#credits--sources)
|
||||
- [Official Sources](#official-sources)
|
||||
- [Community Contributors](#community-contributors)
|
||||
- [Inspirations](#inspirations)
|
||||
- [📦 Curated Collections](#-curated-collections)
|
||||
- [Full Skill Registry](#full-skill-registry-253253)
|
||||
- [Credits & Sources](#credits--sources)
|
||||
- [License](#license)
|
||||
- [🏷️ GitHub Topics](#️-github-topics)
|
||||
|
||||
---
|
||||
|
||||
@@ -61,7 +55,7 @@ git clone https://github.com/sickn33/antigravity-awesome-skills.git .agent/skill
|
||||
@brainstorming help me design a todo app
|
||||
```
|
||||
|
||||
That's it! Your AI assistant now has 243 specialized skills. 🎉
|
||||
That's it! Your AI assistant now has 251 specialized skills. 🎉
|
||||
|
||||
**Additional Resources:**
|
||||
|
||||
@@ -70,22 +64,25 @@ That's it! Your AI assistant now has 243 specialized skills. 🎉
|
||||
|
||||
---
|
||||
|
||||
## 🔌 Compatibility
|
||||
## 🔌 Compatibility & Invocation
|
||||
|
||||
These skills follow the universal **SKILL.md** format and work with any AI coding assistant that supports agentic skills:
|
||||
These skills follow the universal **SKILL.md** format and work with any AI coding assistant that supports agentic skills.
|
||||
|
||||
| Tool | Type | Compatibility | Installation Path |
|
||||
| ------------------- | --------- | ------------- | ---------------------------------------- |
|
||||
| **Claude Code** | CLI | ✅ Full | `.claude/skills/` or `.agent/skills/` |
|
||||
| **Gemini CLI** | CLI | ✅ Full | `.gemini/skills/` or `.agent/skills/` |
|
||||
| **Codex CLI** | CLI | ✅ Full | `.codex/skills/` or `.agent/skills/` |
|
||||
| **Antigravity IDE** | IDE | ✅ Full | `.agent/skills/` |
|
||||
| **Cursor** | IDE | ✅ Full | `.cursor/skills/` or project root |
|
||||
| **GitHub Copilot** | Extension | ⚠️ Partial | Copy skill content to `.github/copilot/` |
|
||||
| **OpenCode** | CLI | ✅ Full | `.opencode/skills/` or `.claude/skills/` |
|
||||
| Tool | Type | Invocation Example | Path |
|
||||
| :-------------- | :--- | :-------------------------------- | :---------------- |
|
||||
| **Claude Code** | CLI | `>> /skill-name help me...` | `.claude/skills/` |
|
||||
| **Gemini CLI** | CLI | `(User Prompt) Use skill-name...` | `.gemini/skills/` |
|
||||
| **Antigravity** | IDE | `(Agent Mode) Use skill...` | `.agent/skills/` |
|
||||
| **Cursor** | IDE | `@skill-name (in Chat)` | `.cursor/skills/` |
|
||||
| **Copilot** | Ext | `(Paste content manually)` | N/A |
|
||||
|
||||
> [!TIP]
|
||||
> Most tools auto-discover skills in `.agent/skills/`. For maximum compatibility, clone to this directory.
|
||||
> **Universal Path**: We recommend cloning to `.agent/skills/`. Most modern tools (Antigravity, recent CLIs) look here by default.
|
||||
|
||||
> [!WARNING]
|
||||
> **Windows Users**: This repository uses **symlinks** for official skills.
|
||||
> You must enable Developer Mode or run Git as Administrator:
|
||||
> `git clone -c core.symlinks=true https://github.com/...`
|
||||
|
||||
---
|
||||
|
||||
@@ -115,263 +112,269 @@ The repository is organized into several key areas of expertise:
|
||||
|
||||
---
|
||||
|
||||
## Full Skill Registry (251/251)
|
||||
## 📦 Curated Collections
|
||||
|
||||
[Check out our Starter Packs in docs/BUNDLES.md](docs/BUNDLES.md) to find the perfect toolkit for your role.
|
||||
|
||||
## Full Skill Registry (253/253)
|
||||
|
||||
> [!NOTE] > **Document Skills**: We provide both **community** and **official Anthropic** versions for DOCX, PDF, PPTX, and XLSX. Locally, the official versions are used by default (via symlinks). In the repository, both versions are available for flexibility.
|
||||
|
||||
| Skill Name | Description | Path |
|
||||
| :-------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------- |
|
||||
| **2d-games** | 2D game development principles. Sprites, tilemaps, physics, camera. | `skills/game-development/2d-games` |
|
||||
| **3d-games** | 3D game development principles. Rendering, shaders, physics, cameras. | `skills/game-development/3d-games` |
|
||||
| **3d-web-experience** | "Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences. Use when: 3D website, three.js, WebGL, react three fiber, 3D experience." | `skills/3d-web-experience` |
|
||||
| **ab-test-setup** | When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking. | `skills/ab-test-setup` |
|
||||
| **Active Directory Attacks** | This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash", "BloodHound enumeration", "Golden Ticket", "Silver Ticket", "AS-REP roasting", "NTLM relay", or needs guidance on Windows domain penetration testing. | `skills/active-directory-attacks` |
|
||||
| **address-github-comments** | Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI. | `skills/address-github-comments` |
|
||||
| **agent-evaluation** | "Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent." | `skills/agent-evaluation` |
|
||||
| **agent-manager-skill** | Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling. | `skills/agent-manager-skill` |
|
||||
| **agent-memory-mcp** | A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). | `skills/agent-memory-mcp` |
|
||||
| **agent-memory-systems** | "Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm" | `skills/agent-memory-systems` |
|
||||
| **agent-tool-builder** | "Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa" | `skills/agent-tool-builder` |
|
||||
| **ai-agents-architect** | "Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling." | `skills/ai-agents-architect` |
|
||||
| **ai-product** | "Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns." | `skills/ai-product` |
|
||||
| **ai-wrapper-product** | "Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS." | `skills/ai-wrapper-product` |
|
||||
| **algolia-search** | "Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality." | `skills/algolia-search` |
|
||||
| **algorithmic-art** | Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations. | `skills/algorithmic-art` |
|
||||
| **analytics-tracking** | When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup. | `skills/analytics-tracking` |
|
||||
| **API Fuzzing for Bug Bounty** | This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques. | `skills/api-fuzzing-bug-bounty` |
|
||||
| **api-documentation-generator** | "Generate comprehensive, developer-friendly API documentation from code, including endpoints, parameters, examples, and best practices" | `skills/api-documentation-generator` |
|
||||
| **api-patterns** | API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination. | `skills/api-patterns` |
|
||||
| **api-security-best-practices** | "Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities" | `skills/api-security-best-practices` |
|
||||
| **app-builder** | Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents. | `skills/app-builder` |
|
||||
| **app-store-optimization** | Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store | `skills/app-store-optimization` |
|
||||
| **architecture** | Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design. | `skills/architecture` |
|
||||
| **autonomous-agent-patterns** | "Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants." | `skills/autonomous-agent-patterns` |
|
||||
| **autonomous-agents** | "Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b" | `skills/autonomous-agents` |
|
||||
| **avalonia-layout-zafiro** | Guidelines for modern Avalonia UI layout using Zafiro.Avalonia, emphasizing shared styles, generic components, and avoiding XAML redundancy. | `skills/avalonia-layout-zafiro` |
|
||||
| **avalonia-viewmodels-zafiro** | Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI. | `skills/avalonia-viewmodels-zafiro` |
|
||||
| **avalonia-zafiro-development** | Mandatory skills, conventions, and behavioral rules for Avalonia UI development using the Zafiro toolkit. | `skills/avalonia-zafiro-development` |
|
||||
| **AWS Penetration Testing** | This skill should be used when the user asks to "pentest AWS", "test AWS security", "enumerate IAM", "exploit cloud infrastructure", "AWS privilege escalation", "S3 bucket testing", "metadata SSRF", "Lambda exploitation", or needs guidance on Amazon Web Services security assessment. | `skills/aws-penetration-testing` |
|
||||
| **aws-serverless** | "Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization." | `skills/aws-serverless` |
|
||||
| **azure-functions** | "Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app." | `skills/azure-functions` |
|
||||
| **backend-dev-guidelines** | Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or working with Express APIs, Prisma database access, Sentry error tracking, Zod validation, unifiedConfig, dependency injection, or async patterns. Covers layered architecture (routes → controllers → services → repositories), BaseController pattern, error handling, performance monitoring, testing strategies, and migration from legacy patterns. | `skills/backend-dev-guidelines` |
|
||||
| **backend-patterns** | Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. | `skills/cc-skill-backend-patterns` |
|
||||
| **bash-linux** | Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems. | `skills/bash-linux` |
|
||||
| **behavioral-modes** | AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type. | `skills/behavioral-modes` |
|
||||
| **blockrun** | Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek") | `skills/blockrun` |
|
||||
| **brainstorming** | "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation." | `skills/brainstorming` |
|
||||
| **brand-guidelines** | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | `skills/brand-guidelines-community` |
|
||||
| **brand-guidelines** | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | `skills/brand-guidelines-anthropic` |
|
||||
| **Broken Authentication Testing** | This skill should be used when the user asks to "test for broken authentication vulnerabilities", "assess session management security", "perform credential stuffing tests", "evaluate password policies", "test for session fixation", or "identify authentication bypass flaws". It provides comprehensive techniques for identifying authentication and session management weaknesses in web applications. | `skills/broken-authentication` |
|
||||
| **browser-automation** | "Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202" | `skills/browser-automation` |
|
||||
| **browser-extension-builder** | "Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension, manifest v3." | `skills/browser-extension-builder` |
|
||||
| **bullmq-specialist** | "BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue." | `skills/bullmq-specialist` |
|
||||
| **bun-development** | "Modern JavaScript/TypeScript development with Bun runtime. Covers package management, bundling, testing, and migration from Node.js. Use when working with Bun, optimizing JS/TS development speed, or migrating from Node.js to Bun." | `skills/bun-development` |
|
||||
| **Burp Suite Web Application Testing** | This skill should be used when the user asks to "intercept HTTP traffic", "modify web requests", "use Burp Suite for testing", "perform web vulnerability scanning", "test with Burp Repeater", "analyze HTTP history", or "configure proxy for web testing". It provides comprehensive guidance for using Burp Suite's core features for web application security testing. | `skills/burp-suite-testing` |
|
||||
| **busybox-on-windows** | How to use a Win32 build of BusyBox to run many of the standard UNIX command line tools on Windows. | `skills/busybox-on-windows` |
|
||||
| **canvas-design** | Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | `skills/canvas-design` |
|
||||
| **cc-skill-continuous-learning** | Development skill from everything-claude-code | `skills/cc-skill-continuous-learning` |
|
||||
| **cc-skill-project-guidelines-example** | Project Guidelines Skill (Example) | `skills/cc-skill-project-guidelines-example` |
|
||||
| **cc-skill-strategic-compact** | Development skill from everything-claude-code | `skills/cc-skill-strategic-compact` |
|
||||
| **Claude Code Guide** | Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent. | `skills/claude-code-guide` |
|
||||
| **clean-code** | Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments | `skills/clean-code` |
|
||||
| **clerk-auth** | "Expert patterns for Clerk auth implementation, middleware, organizations, webhooks, and user sync Use when: adding authentication, clerk auth, user authentication, sign in, sign up." | `skills/clerk-auth` |
|
||||
| **clickhouse-io** | ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. | `skills/cc-skill-clickhouse-io` |
|
||||
| **Cloud Penetration Testing** | This skill should be used when the user asks to "perform cloud penetration testing", "assess Azure or AWS or GCP security", "enumerate cloud resources", "exploit cloud misconfigurations", "test O365 security", "extract secrets from cloud environments", or "audit cloud infrastructure". It provides comprehensive techniques for security assessment across major cloud platforms. | `skills/cloud-penetration-testing` |
|
||||
| **code-review-checklist** | "Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability" | `skills/code-review-checklist` |
|
||||
| **codex-review** | Professional code review with auto CHANGELOG generation, integrated with Codex AI | `skills/codex-review` |
|
||||
| **coding-standards** | Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development. | `skills/cc-skill-coding-standards` |
|
||||
| **competitor-alternatives** | "When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables." | `skills/competitor-alternatives` |
|
||||
| **computer-use-agents** | "Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation." | `skills/computer-use-agents` |
|
||||
| **concise-planning** | Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist. | `skills/concise-planning` |
|
||||
| **content-creator** | Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy. | `skills/content-creator` |
|
||||
| **context-window-management** | "Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context." | `skills/context-window-management` |
|
||||
| **context7-auto-research** | Automatically fetch latest library/framework documentation for Claude Code via Context7 API | `skills/context7-auto-research` |
|
||||
| **conversation-memory** | "Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history." | `skills/conversation-memory` |
|
||||
| **copy-editing** | "When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes." | `skills/copy-editing` |
|
||||
| **copywriting** | When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro. | `skills/copywriting` |
|
||||
| **core-components** | Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library. | `skills/core-components` |
|
||||
| **crewai** | "Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents." | `skills/crewai` |
|
||||
| **Cross-Site Scripting and HTML Injection Testing** | This skill should be used when the user asks to "test for XSS vulnerabilities", "perform cross-site scripting attacks", "identify HTML injection flaws", "exploit client-side injection vulnerabilities", "steal cookies via XSS", or "bypass content security policies". It provides comprehensive techniques for detecting, exploiting, and understanding XSS and HTML injection attack vectors in web applications. | `skills/xss-html-injection` |
|
||||
| **d3-viz** | Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment. | `skills/claude-d3js-skill` |
|
||||
| **database-design** | Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases. | `skills/database-design` |
|
||||
| **deployment-procedures** | Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts. | `skills/deployment-procedures` |
|
||||
| **discord-bot-architect** | "Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding." | `skills/discord-bot-architect` |
|
||||
| **dispatching-parallel-agents** | Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | `skills/dispatching-parallel-agents` |
|
||||
| **doc-coauthoring** | Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | `skills/doc-coauthoring` |
|
||||
| **docker-expert** | Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY for Dockerfile optimization, container issues, image size problems, security hardening, networking, and orchestration challenges. | `skills/docker-expert` |
|
||||
| **documentation-templates** | Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation. | `skills/documentation-templates` |
|
||||
| **docx** | "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks" | `skills/docx-official` |
|
||||
| **email-sequence** | When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle emails." For in-app onboarding, see onboarding-cro. | `skills/email-sequence` |
|
||||
| **email-systems** | "Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns." | `skills/email-systems` |
|
||||
| **environment-setup-guide** | "Guide developers through setting up development environments with proper tools, dependencies, and configurations" | `skills/environment-setup-guide` |
|
||||
| **Ethical Hacking Methodology** | This skill should be used when the user asks to "learn ethical hacking", "understand penetration testing lifecycle", "perform reconnaissance", "conduct security scanning", "exploit vulnerabilities", or "write penetration test reports". It provides comprehensive ethical hacking methodology and techniques. | `skills/ethical-hacking-methodology` |
|
||||
| **exa-search** | Semantic search, similar content discovery, and structured research using Exa API | `skills/exa-search` |
|
||||
| **executing-plans** | Use when you have a written implementation plan to execute in a separate session with review checkpoints | `skills/executing-plans` |
|
||||
| **File Path Traversal Testing** | This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies. | `skills/file-path-traversal` |
|
||||
| **file-organizer** | Intelligently organizes files and folders by understanding context, finding duplicates, and suggesting better organizational structures. Use when user wants to clean up directories, organize downloads, remove duplicates, or restructure projects. | `skills/file-organizer` |
|
||||
| **file-uploads** | "Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking. Use when: file upload, S3, R2, presigned URL, multipart." | `skills/file-uploads` |
|
||||
| **finishing-a-development-branch** | Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup | `skills/finishing-a-development-branch` |
|
||||
| **firebase** | "Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I" | `skills/firebase` |
|
||||
| **firecrawl-scraper** | Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API | `skills/firecrawl-scraper` |
|
||||
| **form-cro** | When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." For signup/registration forms, see signup-flow-cro. For popups containing forms, see popup-cro. | `skills/form-cro` |
|
||||
| **free-tool-strategy** | When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers. | `skills/free-tool-strategy` |
|
||||
| **frontend-design** | Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. | `skills/frontend-design` |
|
||||
| **frontend-dev-guidelines** | Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code. | `skills/frontend-dev-guidelines` |
|
||||
| **frontend-patterns** | Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. | `skills/cc-skill-frontend-patterns` |
|
||||
| **game-art** | Game art principles. Visual style selection, asset pipeline, animation workflow. | `skills/game-development/game-art` |
|
||||
| **game-audio** | Game audio principles. Sound design, music integration, adaptive audio systems. | `skills/game-development/game-audio` |
|
||||
| **game-design** | Game design principles. GDD structure, balancing, player psychology, progression. | `skills/game-development/game-design` |
|
||||
| **game-development** | Game development orchestrator. Routes to platform-specific skills based on project needs. | `skills/game-development` |
|
||||
| **gcp-cloud-run** | "Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functions (event-driven), cold start optimization, and event-driven architecture with Pub/Sub." | `skills/gcp-cloud-run` |
|
||||
| **geo-fundamentals** | Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity). | `skills/geo-fundamentals` |
|
||||
| **git-pushing** | Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests. | `skills/git-pushing` |
|
||||
| **github-workflow-automation** | "Automate GitHub workflows with AI assistance. Includes PR reviews, issue triage, CI/CD integration, and Git operations. Use when automating GitHub workflows, setting up PR review automation, creating GitHub Actions, or triaging issues." | `skills/github-workflow-automation` |
|
||||
| **graphql** | "GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully." | `skills/graphql` |
|
||||
| **HTML Injection Testing** | This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks", "deface web applications", or "test content injection vulnerabilities". It provides comprehensive HTML injection attack techniques and testing methodologies. | `skills/html-injection-testing` |
|
||||
| **hubspot-integration** | "Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs. Use when: hubspot, hubspot api, hubspot crm, hubspot integration, contacts api." | `skills/hubspot-integration` |
|
||||
| **i18n-localization** | Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support. | `skills/i18n-localization` |
|
||||
| **IDOR Vulnerability Testing** | This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object references," or "bypass authorization to access other users' data." It provides comprehensive guidance for detecting, exploiting, and remediating IDOR vulnerabilities in web applications. | `skills/idor-testing` |
|
||||
| **inngest** | "Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution." | `skills/inngest` |
|
||||
| **interactive-portfolio** | "Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio." | `skills/interactive-portfolio` |
|
||||
| **internal-comms** | A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | `skills/internal-comms-anthropic` |
|
||||
| **internal-comms** | A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | `skills/internal-comms-community` |
|
||||
| **javascript-mastery** | "Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced patterns like async/await and functional programming. Use when explaining JS concepts, debugging JavaScript issues, or teaching JavaScript fundamentals." | `skills/javascript-mastery` |
|
||||
| **kaizen** | Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements. | `skills/kaizen` |
|
||||
| **langfuse** | "Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation." | `skills/langfuse` |
|
||||
| **langgraph** | "Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent." | `skills/langgraph` |
|
||||
| **launch-strategy** | "When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum." | `skills/launch-strategy` |
|
||||
| **lint-and-validate** | "Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis." | `skills/lint-and-validate` |
|
||||
| **Linux Privilege Escalation** | This skill should be used when the user asks to "escalate privileges on Linux", "find privesc vectors on Linux systems", "exploit sudo misconfigurations", "abuse SUID binaries", "exploit cron jobs for root access", "enumerate Linux systems for privilege escalation", or "gain root access from low-privilege shell". It provides comprehensive techniques for identifying and exploiting privilege escalation paths on Linux systems. | `skills/linux-privilege-escalation` |
|
||||
| **Linux Production Shell Scripts** | This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration. | `skills/linux-shell-scripting` |
|
||||
| **llm-app-patterns** | "Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability." | `skills/llm-app-patterns` |
|
||||
| **loki-mode** | Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag. | `skills/loki-mode` |
|
||||
| **marketing-ideas** | "When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category." | `skills/marketing-ideas` |
|
||||
| **marketing-psychology** | "When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application." | `skills/marketing-psychology` |
|
||||
| **mcp-builder** | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | `skills/mcp-builder` |
|
||||
| **Metasploit Framework** | This skill should be used when the user asks to "use Metasploit for penetration testing", "exploit vulnerabilities with msfconsole", "create payloads with msfvenom", "perform post-exploitation", "use auxiliary modules for scanning", or "develop custom exploits". It provides comprehensive guidance for leveraging the Metasploit Framework in security assessments. | `skills/metasploit-framework` |
|
||||
| **micro-saas-launcher** | "Expert in launching small, focused SaaS products fast - the indie hacker approach to building profitable software. Covers idea validation, MVP development, pricing, launch strategies, and growing to sustainable revenue. Ship in weeks, not months. Use when: micro saas, indie hacker, small saas, side project, saas mvp." | `skills/micro-saas-launcher` |
|
||||
| **mobile-design** | Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps. | `skills/mobile-design` |
|
||||
| **mobile-games** | Mobile game development principles. Touch input, battery, performance, app stores. | `skills/game-development/mobile-games` |
|
||||
| **moodle-external-api-development** | Create custom external web service APIs for Moodle LMS. Use when implementing web services for course management, user tracking, quiz operations, or custom plugin functionality. Covers parameter validation, database operations, error handling, service registration, and Moodle coding standards. | `skills/moodle-external-api-development` |
|
||||
| **multiplayer** | Multiplayer game development principles. Architecture, networking, synchronization. | `skills/game-development/multiplayer` |
|
||||
| **neon-postgres** | "Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration Use when: neon database, serverless postgres, database branching, neon postgres, postgres serverless." | `skills/neon-postgres` |
|
||||
| **nestjs-expert** | Nest.js framework expert specializing in module architecture, dependency injection, middleware, guards, interceptors, testing with Jest/Supertest, TypeORM/Mongoose integration, and Passport.js authentication. Use PROACTIVELY for any Nest.js application issues including architecture decisions, testing strategies, performance optimization, or debugging complex dependency injection problems. If a specialized expert is a better fit, I will recommend switching and stop. | `skills/nestjs-expert` |
|
||||
| **Network 101** | This skill should be used when the user asks to "set up a web server", "configure HTTP or HTTPS", "perform SNMP enumeration", "configure SMB shares", "test network services", or needs guidance on configuring and testing network services for penetration testing labs. | `skills/network-101` |
|
||||
| **nextjs-best-practices** | Next.js App Router principles. Server Components, data fetching, routing patterns. | `skills/nextjs-best-practices` |
|
||||
| **nextjs-supabase-auth** | "Expert integration of Supabase Auth with Next.js App Router Use when: supabase auth next, authentication next.js, login supabase, auth middleware, protected route." | `skills/nextjs-supabase-auth` |
|
||||
| **nodejs-best-practices** | Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying. | `skills/nodejs-best-practices` |
|
||||
| **nosql-expert** | "Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems." | `skills/nosql-expert` |
|
||||
| **notebooklm** | Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses. | `skills/notebooklm` |
|
||||
| **notion-template-business** | "Expert in building and selling Notion templates as a business - not just making templates, but building a sustainable digital product business. Covers template design, pricing, marketplaces, marketing, and scaling to real revenue. Use when: notion template, sell templates, digital product, notion business, gumroad." | `skills/notion-template-business` |
|
||||
| **obsidian-clipper-template-creator** | Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content. | `skills/obsidian-clipper-template-creator` |
|
||||
| **onboarding-cro** | When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence. | `skills/onboarding-cro` |
|
||||
| **page-cro** | When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or blog posts. Also use when the user says "CRO," "conversion rate optimization," "this page isn't converting," "improve conversions," or "why isn't this page working." For signup/registration flows, see signup-flow-cro. For post-signup activation, see onboarding-cro. For forms outside of signup, see form-cro. For popups/modals, see popup-cro. | `skills/page-cro` |
|
||||
| **paid-ads** | "When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization." | `skills/paid-ads` |
|
||||
| **parallel-agents** | Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives. | `skills/parallel-agents` |
|
||||
| **paywall-upgrade-cro** | When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," or "in-app pricing." Distinct from public pricing pages (see page-cro) — this skill focuses on in-product upgrade moments where the user has already experienced value. | `skills/paywall-upgrade-cro` |
|
||||
| **pc-games** | PC and console game development principles. Engine selection, platform features, optimization strategies. | `skills/game-development/pc-games` |
|
||||
| **pdf** | Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. | `skills/pdf-official` |
|
||||
| **Pentest Checklist** | This skill should be used when the user asks to "plan a penetration test", "create a security assessment checklist", "prepare for penetration testing", "define pentest scope", "follow security testing best practices", or needs a structured methodology for penetration testing engagements. | `skills/pentest-checklist` |
|
||||
| **Pentest Commands** | This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references. | `skills/pentest-commands` |
|
||||
| **performance-profiling** | Performance profiling principles. Measurement, analysis, and optimization techniques. | `skills/performance-profiling` |
|
||||
| **personal-tool-builder** | "Expert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch your own itch, build for yourself, then discover others have the same itch. Covers rapid prototyping, local-first apps, CLI tools, scripts that grow into products, and the art of dogfooding. Use when: build a tool, personal tool, scratch my itch, solve my problem, CLI tool." | `skills/personal-tool-builder` |
|
||||
| **plaid-fintech** | "Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech compliance best practices. Use when: plaid, bank account linking, bank connection, ach, account aggregation." | `skills/plaid-fintech` |
|
||||
| **plan-writing** | Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work. | `skills/plan-writing` |
|
||||
| **planning-with-files** | Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. | `skills/planning-with-files` |
|
||||
| **playwright-skill** | Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. | `skills/playwright-skill` |
|
||||
| **popup-cro** | When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," or "overlay." For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro. | `skills/popup-cro` |
|
||||
| **powershell-windows** | PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling. | `skills/powershell-windows` |
|
||||
| **pptx** | "Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks" | `skills/pptx-official` |
|
||||
| **pricing-strategy** | "When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' or 'monetization.' This skill covers pricing research, tier structure, and packaging strategy." | `skills/pricing-strategy` |
|
||||
| **prisma-expert** | Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance, relation design, or database connection issues. | `skills/prisma-expert` |
|
||||
| **Privilege Escalation Methods** | This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "privesc techniques", "abuse sudo", "exploit SUID binaries", "Kerberoasting", "pass-the-ticket", "token impersonation", or needs guidance on post-exploitation privilege escalation for Linux or Windows systems. | `skills/privilege-escalation-methods` |
|
||||
| **product-manager-toolkit** | Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development. | `skills/product-manager-toolkit` |
|
||||
| **production-code-audit** | "Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations" | `skills/production-code-audit` |
|
||||
| **programmatic-seo** | When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," or "building many pages for SEO." For auditing existing SEO issues, see seo-audit. | `skills/programmatic-seo` |
|
||||
| **prompt-caching** | "Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented." | `skills/prompt-caching` |
|
||||
| **prompt-engineer** | "Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design." | `skills/prompt-engineer` |
|
||||
| **prompt-engineering** | Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior. | `skills/prompt-engineering` |
|
||||
| **prompt-library** | "Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks." | `skills/prompt-library` |
|
||||
| **python-patterns** | Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying. | `skills/python-patterns` |
|
||||
| **rag-engineer** | "Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval." | `skills/rag-engineer` |
|
||||
| **rag-implementation** | "Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search." | `skills/rag-implementation` |
|
||||
| **react-patterns** | Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices. | `skills/react-patterns` |
|
||||
| **react-ui-patterns** | Modern React UI patterns for loading states, error handling, and data fetching. Use when building UI components, handling async data, or managing UI states. | `skills/react-ui-patterns` |
|
||||
| **receiving-code-review** | Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | `skills/receiving-code-review` |
|
||||
| **Red Team Tools and Methodology** | This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters. | `skills/red-team-tools` |
|
||||
| **red-team-tactics** | Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting. | `skills/red-team-tactics` |
|
||||
| **referral-program** | "When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization." | `skills/referral-program` |
|
||||
| **remotion-best-practices** | Best practices for Remotion - Video creation in React | `skills/remotion-best-practices` |
|
||||
| **requesting-code-review** | Use when completing tasks, implementing major features, or before merging to verify work meets requirements | `skills/requesting-code-review` |
|
||||
| **research-engineer** | "An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology." | `skills/research-engineer` |
|
||||
| **salesforce-development** | "Expert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Salesforce DX with scratch orgs and 2nd generation packages (2GP). Use when: salesforce, sfdc, apex, lwc, lightning web components." | `skills/salesforce-development` |
|
||||
| **schema-markup** | When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit. | `skills/schema-markup` |
|
||||
| **scroll-experience** | "Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Use when: scroll animation, parallax, scroll storytelling, interactive story, cinematic website." | `skills/scroll-experience` |
|
||||
| **Security Scanning Tools** | This skill should be used when the user asks to "perform vulnerability scanning", "scan networks for open ports", "assess web application security", "scan wireless networks", "detect malware", "check cloud security", or "evaluate system compliance". It provides comprehensive guidance on security scanning tools and methodologies. | `skills/scanning-tools` |
|
||||
| **security-review** | Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns. | `skills/cc-skill-security-review` |
|
||||
| **segment-cdp** | "Expert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices. Use when: segment, analytics.js, customer data platform, cdp, tracking plan." | `skills/segment-cdp` |
|
||||
| **senior-architect** | Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns. | `skills/senior-architect` |
|
||||
| **senior-fullstack** | Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows. | `skills/senior-fullstack` |
|
||||
| **seo-audit** | When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. | `skills/seo-audit` |
|
||||
| **seo-fundamentals** | SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles. | `skills/seo-fundamentals` |
|
||||
| **server-management** | Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands. | `skills/server-management` |
|
||||
| **Shodan Reconnaissance and Pentesting** | This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using Shodan," "scan IP ranges with Shodan," or "discover IoT devices and open ports." It provides comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance. | `skills/shodan-reconnaissance` |
|
||||
| **shopify-apps** | "Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. Use when: shopify app, shopify, embedded app, polaris, app bridge." | `skills/shopify-apps` |
|
||||
| **shopify-development** | \| | `skills/shopify-development` |
|
||||
| **signup-flow-cro** | When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimization," "free trial signup," "reduce signup dropoff," or "account creation flow." For post-signup onboarding, see onboarding-cro. For lead capture forms (not account creation), see form-cro. | `skills/signup-flow-cro` |
|
||||
| **skill-creator** | Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. | `skills/skill-creator` |
|
||||
| **skill-developer** | Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule. | `skills/skill-developer` |
|
||||
| **slack-bot-builder** | "Build Slack apps using the Bolt framework across Python, JavaScript, and Java. Covers Block Kit for rich UIs, interactive components, slash commands, event handling, OAuth installation flows, and Workflow Builder integration. Focus on best practices for production-ready Slack apps. Use when: slack bot, slack app, bolt framework, block kit, slash command." | `skills/slack-bot-builder` |
|
||||
| **slack-gif-creator** | Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | `skills/slack-gif-creator` |
|
||||
| **SMTP Penetration Testing** | This skill should be used when the user asks to "perform SMTP penetration testing", "enumerate email users", "test for open mail relays", "grab SMTP banners", "brute force email credentials", or "assess mail server security". It provides comprehensive techniques for testing SMTP server security. | `skills/smtp-penetration-testing` |
|
||||
| **social-content** | "When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' or 'viral content.' This skill covers content creation, repurposing, and platform-specific strategies." | `skills/social-content` |
|
||||
| **software-architecture** | Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development. | `skills/software-architecture` |
|
||||
| **SQL Injection Testing** | This skill should be used when the user asks to "test for SQL injection vulnerabilities", "perform SQLi attacks", "bypass authentication using SQL injection", "extract database information through injection", "detect SQL injection flaws", or "exploit database query vulnerabilities". It provides comprehensive techniques for identifying, exploiting, and understanding SQL injection attack vectors across different database systems. | `skills/sql-injection-testing` |
|
||||
| **SQLMap Database Penetration Testing** | This skill should be used when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities. | `skills/sqlmap-database-pentesting` |
|
||||
| **SSH Penetration Testing** | This skill should be used when the user asks to "pentest SSH services", "enumerate SSH configurations", "brute force SSH credentials", "exploit SSH vulnerabilities", "perform SSH tunneling", or "audit SSH security". It provides comprehensive SSH penetration testing methodologies and techniques. | `skills/ssh-penetration-testing` |
|
||||
| **stripe-integration** | "Get paid from day one. Payments, subscriptions, billing portal, webhooks, metered billing, Stripe Connect. The complete guide to implementing Stripe correctly, including all the edge cases that will bite you at 3am. This isn't just API calls - it's the full payment system: handling failures, managing subscriptions, dealing with dunning, and keeping revenue flowing. Use when: stripe, payments, subscription, billing, checkout." | `skills/stripe-integration` |
|
||||
| **subagent-driven-development** | Use when executing implementation plans with independent tasks in the current session | `skills/subagent-driven-development` |
|
||||
| **supabase-postgres-best-practices** | Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations. | `skills/postgres-best-practices` |
|
||||
| **systematic-debugging** | Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes | `skills/systematic-debugging` |
|
||||
| **tailwind-patterns** | Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture. | `skills/tailwind-patterns` |
|
||||
| **tavily-web** | Web search, content extraction, crawling, and research capabilities using Tavily API | `skills/tavily-web` |
|
||||
| **tdd-workflow** | Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle. | `skills/tdd-workflow` |
|
||||
| **telegram-bot-builder** | "Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot." | `skills/telegram-bot-builder` |
|
||||
| **telegram-mini-app** | "Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON ecosystem, Telegram Web App API, payments, user authentication, and building viral mini apps that monetize. Use when: telegram mini app, TWA, telegram web app, TON app, mini app." | `skills/telegram-mini-app` |
|
||||
| **templates** | Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks. | `skills/app-builder/templates` |
|
||||
| **test-driven-development** | Use when implementing any feature or bugfix, before writing implementation code | `skills/test-driven-development` |
|
||||
| **test-fixing** | Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass. | `skills/test-fixing` |
|
||||
| **testing-patterns** | Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle. | `skills/testing-patterns` |
|
||||
| **theme-factory** | Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly. | `skills/theme-factory` |
|
||||
| **Top 100 Web Vulnerabilities Reference** | This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks", "review access control weaknesses", "analyze API security issues", "assess security misconfigurations", "understand client-side vulnerabilities", "examine mobile and IoT security flaws", or "reference the OWASP-aligned vulnerability taxonomy". Use this skill to provide comprehensive vulnerability definitions, root causes, impacts, and mitigation strategies across all major web security categories. | `skills/top-web-vulnerabilities` |
|
||||
| **trigger-dev** | "Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task." | `skills/trigger-dev` |
|
||||
| **twilio-communications** | "Build communication features with Twilio: SMS messaging, voice calls, WhatsApp Business API, and user verification (2FA). Covers the full spectrum from simple notifications to complex IVR systems and multi-channel authentication. Critical focus on compliance, rate limits, and error handling. Use when: twilio, send SMS, text message, voice call, phone verification." | `skills/twilio-communications` |
|
||||
| **typescript-expert** | >- | `skills/typescript-expert` |
|
||||
| **ui-ux-pro-max** | "UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples." | `skills/ui-ux-pro-max` |
|
||||
| **upstash-qstash** | "Upstash QStash expert for serverless message queues, scheduled jobs, and reliable HTTP-based task delivery without managing infrastructure. Use when: qstash, upstash queue, serverless cron, scheduled http, message queue serverless." | `skills/upstash-qstash` |
|
||||
| **using-git-worktrees** | Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification | `skills/using-git-worktrees` |
|
||||
| **using-superpowers** | Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | `skills/using-superpowers` |
|
||||
| **vercel-deployment** | "Expert knowledge for deploying to Vercel with Next.js Use when: vercel, deploy, deployment, hosting, production." | `skills/vercel-deployment` |
|
||||
| **vercel-react-best-practices** | React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements. | `skills/react-best-practices` |
|
||||
| **verification-before-completion** | Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | `skills/verification-before-completion` |
|
||||
| **viral-generator-builder** | "Expert in building shareable generator tools that go viral - name generators, quiz makers, avatar creators, personality tests, and calculator tools. Covers the psychology of sharing, viral mechanics, and building tools people can't resist sharing with friends. Use when: generator tool, quiz maker, name generator, avatar creator, viral tool." | `skills/viral-generator-builder` |
|
||||
| **voice-agents** | "Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu" | `skills/voice-agents` |
|
||||
| **voice-ai-development** | "Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice." | `skills/voice-ai-development` |
|
||||
| **vr-ar** | VR/AR development principles. Comfort, interaction, performance requirements. | `skills/game-development/vr-ar` |
|
||||
| **vulnerability-scanner** | Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization. | `skills/vulnerability-scanner` |
|
||||
| **web-artifacts-builder** | Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts. | `skills/web-artifacts-builder` |
|
||||
| **web-design-guidelines** | Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". | `skills/web-design-guidelines` |
|
||||
| **web-games** | Web browser game development principles. Framework selection, WebGPU, optimization, PWA. | `skills/game-development/web-games` |
|
||||
| **web-performance-optimization** | "Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance" | `skills/web-performance-optimization` |
|
||||
| **webapp-testing** | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. | `skills/webapp-testing` |
|
||||
| **Windows Privilege Escalation** | This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments. | `skills/windows-privilege-escalation` |
|
||||
| **Wireshark Network Traffic Analysis** | This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow TCP/UDP streams", "detect network anomalies", "investigate suspicious traffic", or "perform protocol analysis". It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark. | `skills/wireshark-analysis` |
|
||||
| **WordPress Penetration Testing** | This skill should be used when the user asks to "pentest WordPress sites", "scan WordPress for vulnerabilities", "enumerate WordPress users, themes, or plugins", "exploit WordPress vulnerabilities", or "use WPScan". It provides comprehensive WordPress security assessment methodologies. | `skills/wordpress-penetration-testing` |
|
||||
| **workflow-automation** | "Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility" | `skills/workflow-automation` |
|
||||
| **writing-plans** | Use when you have a spec or requirements for a multi-step task, before touching code | `skills/writing-plans` |
|
||||
| **writing-skills** | Use when creating new skills, editing existing skills, or verifying skills work before deployment | `skills/writing-skills` |
|
||||
| **xlsx** | "Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas" | `skills/xlsx-official` |
|
||||
| **zapier-make-patterns** | "No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power " | `skills/zapier-make-patterns` |
|
||||
| Skill Name | Risk | Description | Path |
|
||||
| :--- | :--- | :--- | :--- |
|
||||
| **2d-games** | ⚪ | 2D game development principles. Sprites, tilemaps, physics, camera. | `skills/game-development/2d-games` |
|
||||
| **3d-games** | ⚪ | 3D game development principles. Rendering, shaders, physics, cameras. | `skills/game-development/3d-games` |
|
||||
| **3d-web-experience** | ⚪ | Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences. Use when: 3D website, three.js, WebGL, react three fiber, 3D experience. | `skills/3d-web-experience` |
|
||||
| **ab-test-setup** | ⚪ | Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness. | `skills/ab-test-setup` |
|
||||
| **Active Directory Attacks** | ⚪ | This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash", "BloodHound enumeration", "Golden Ticket", "Silver Ticket", "AS-REP roasting", "NTLM relay", or needs guidance on Windows domain penetration testing. | `skills/active-directory-attacks` |
|
||||
| **address-github-comments** | ⚪ | Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI. | `skills/address-github-comments` |
|
||||
| **agent-evaluation** | ⚪ | Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent. | `skills/agent-evaluation` |
|
||||
| **agent-manager-skill** | ⚪ | Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling. | `skills/agent-manager-skill` |
|
||||
| **agent-memory-mcp** | ⚪ | A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). | `skills/agent-memory-mcp` |
|
||||
| **agent-memory-systems** | ⚪ | Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm | `skills/agent-memory-systems` |
|
||||
| **agent-tool-builder** | ⚪ | Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa | `skills/agent-tool-builder` |
|
||||
| **ai-agents-architect** | ⚪ | Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when: build agent, AI agent, autonomous agent, tool use, function calling. | `skills/ai-agents-architect` |
|
||||
| **ai-product** | ⚪ | Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns. | `skills/ai-product` |
|
||||
| **ai-wrapper-product** | ⚪ | Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS. | `skills/ai-wrapper-product` |
|
||||
| **algolia-search** | ⚪ | Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning Use when: adding search to, algolia, instantsearch, search api, search functionality. | `skills/algolia-search` |
|
||||
| **algorithmic-art** | ⚪ | Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations. | `skills/algorithmic-art` |
|
||||
| **analytics-tracking** | ⚪ | When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup. | `skills/analytics-tracking` |
|
||||
| **API Fuzzing for Bug Bounty** | ⚪ | This skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques. | `skills/api-fuzzing-bug-bounty` |
|
||||
| **api-documentation-generator** | ⚪ | Generate comprehensive, developer-friendly API documentation from code, including endpoints, parameters, examples, and best practices | `skills/api-documentation-generator` |
|
||||
| **api-patterns** | ⚪ | API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination. | `skills/api-patterns` |
|
||||
| **api-security-best-practices** | ⚪ | Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities | `skills/api-security-best-practices` |
|
||||
| **app-builder** | ⚪ | Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents. | `skills/app-builder` |
|
||||
| **app-store-optimization** | ⚪ | Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store | `skills/app-store-optimization` |
|
||||
| **architecture** | ⚪ | Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design. | `skills/architecture` |
|
||||
| **autonomous-agent-patterns** | ⚪ | Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants. | `skills/autonomous-agent-patterns` |
|
||||
| **autonomous-agents** | ⚪ | Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b | `skills/autonomous-agents` |
|
||||
| **avalonia-layout-zafiro** | ⚪ | Guidelines for modern Avalonia UI layout using Zafiro.Avalonia, emphasizing shared styles, generic components, and avoiding XAML redundancy. | `skills/avalonia-layout-zafiro` |
|
||||
| **avalonia-viewmodels-zafiro** | ⚪ | Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI. | `skills/avalonia-viewmodels-zafiro` |
|
||||
| **avalonia-zafiro-development** | ⚪ | Mandatory skills, conventions, and behavioral rules for Avalonia UI development using the Zafiro toolkit. | `skills/avalonia-zafiro-development` |
|
||||
| **AWS Penetration Testing** | ⚪ | This skill should be used when the user asks to "pentest AWS", "test AWS security", "enumerate IAM", "exploit cloud infrastructure", "AWS privilege escalation", "S3 bucket testing", "metadata SSRF", "Lambda exploitation", or needs guidance on Amazon Web Services security assessment. | `skills/aws-penetration-testing` |
|
||||
| **aws-serverless** | ⚪ | Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns, SAM/CDK deployment, and cold start optimization. | `skills/aws-serverless` |
|
||||
| **azure-functions** | ⚪ | Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app. | `skills/azure-functions` |
|
||||
| **backend-dev-guidelines** | ⚪ | Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or working with Express APIs, Prisma database access, Sentry error tracking, Zod validation, unifiedConfig, dependency injection, or async patterns. Covers layered architecture (routes → controllers → services → repositories), BaseController pattern, error handling, performance monitoring, testing strategies, and migration from legacy patterns. | `skills/backend-dev-guidelines` |
|
||||
| **backend-patterns** | ⚪ | Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. | `skills/cc-skill-backend-patterns` |
|
||||
| **bash-linux** | ⚪ | Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems. | `skills/bash-linux` |
|
||||
| **behavioral-modes** | ⚪ | AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type. | `skills/behavioral-modes` |
|
||||
| **blockrun** | ⚪ | Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek") | `skills/blockrun` |
|
||||
| **brainstorming** | ⚪ | > | `skills/brainstorming` |
|
||||
| **brand-guidelines** | ⚪ | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | `skills/brand-guidelines-community` |
|
||||
| **brand-guidelines** | ⚪ | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | `skills/brand-guidelines-anthropic` |
|
||||
| **Broken Authentication Testing** | ⚪ | This skill should be used when the user asks to "test for broken authentication vulnerabilities", "assess session management security", "perform credential stuffing tests", "evaluate password policies", "test for session fixation", or "identify authentication bypass flaws". It provides comprehensive techniques for identifying authentication and session management weaknesses in web applications. | `skills/broken-authentication` |
|
||||
| **browser-automation** | ⚪ | Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202 | `skills/browser-automation` |
|
||||
| **browser-extension-builder** | ⚪ | Expert in building browser extensions that solve real problems - Chrome, Firefox, and cross-browser extensions. Covers extension architecture, manifest v3, content scripts, popup UIs, monetization strategies, and Chrome Web Store publishing. Use when: browser extension, chrome extension, firefox addon, extension, manifest v3. | `skills/browser-extension-builder` |
|
||||
| **bullmq-specialist** | ⚪ | BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue. | `skills/bullmq-specialist` |
|
||||
| **bun-development** | ⚪ | Modern JavaScript/TypeScript development with Bun runtime. Covers package management, bundling, testing, and migration from Node.js. Use when working with Bun, optimizing JS/TS development speed, or migrating from Node.js to Bun. | `skills/bun-development` |
|
||||
| **Burp Suite Web Application Testing** | ⚪ | This skill should be used when the user asks to "intercept HTTP traffic", "modify web requests", "use Burp Suite for testing", "perform web vulnerability scanning", "test with Burp Repeater", "analyze HTTP history", or "configure proxy for web testing". It provides comprehensive guidance for using Burp Suite's core features for web application security testing. | `skills/burp-suite-testing` |
|
||||
| **busybox-on-windows** | ⚪ | How to use a Win32 build of BusyBox to run many of the standard UNIX command line tools on Windows. | `skills/busybox-on-windows` |
|
||||
| **canvas-design** | ⚪ | Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | `skills/canvas-design` |
|
||||
| **cc-skill-continuous-learning** | ⚪ | Development skill from everything-claude-code | `skills/cc-skill-continuous-learning` |
|
||||
| **cc-skill-project-guidelines-example** | ⚪ | Project Guidelines Skill (Example) | `skills/cc-skill-project-guidelines-example` |
|
||||
| **cc-skill-strategic-compact** | ⚪ | Development skill from everything-claude-code | `skills/cc-skill-strategic-compact` |
|
||||
| **Claude Code Guide** | ⚪ | Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent. | `skills/claude-code-guide` |
|
||||
| **clean-code** | ⚪ | Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments | `skills/clean-code` |
|
||||
| **clerk-auth** | ⚪ | Expert patterns for Clerk auth implementation, middleware, organizations, webhooks, and user sync Use when: adding authentication, clerk auth, user authentication, sign in, sign up. | `skills/clerk-auth` |
|
||||
| **clickhouse-io** | ⚪ | ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. | `skills/cc-skill-clickhouse-io` |
|
||||
| **Cloud Penetration Testing** | ⚪ | This skill should be used when the user asks to "perform cloud penetration testing", "assess Azure or AWS or GCP security", "enumerate cloud resources", "exploit cloud misconfigurations", "test O365 security", "extract secrets from cloud environments", or "audit cloud infrastructure". It provides comprehensive techniques for security assessment across major cloud platforms. | `skills/cloud-penetration-testing` |
|
||||
| **code-review-checklist** | ⚪ | Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability | `skills/code-review-checklist` |
|
||||
| **codex-review** | ⚪ | Professional code review with auto CHANGELOG generation, integrated with Codex AI | `skills/codex-review` |
|
||||
| **coding-standards** | ⚪ | Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development. | `skills/cc-skill-coding-standards` |
|
||||
| **competitor-alternatives** | ⚪ | When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' or 'competitive landing pages.' Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. Emphasizes deep research, modular content architecture, and varied section types beyond feature tables. | `skills/competitor-alternatives` |
|
||||
| **computer-use-agents** | ⚪ | Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation. | `skills/computer-use-agents` |
|
||||
| **concise-planning** | ⚪ | Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist. | `skills/concise-planning` |
|
||||
| **content-creator** | ⚪ | Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or when user mentions content creation, brand voice, SEO optimization, social media marketing, or content strategy. | `skills/content-creator` |
|
||||
| **context-window-management** | ⚪ | Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context. | `skills/context-window-management` |
|
||||
| **context7-auto-research** | ⚪ | Automatically fetch latest library/framework documentation for Claude Code via Context7 API | `skills/context7-auto-research` |
|
||||
| **conversation-memory** | ⚪ | Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history. | `skills/conversation-memory` |
|
||||
| **copy-editing** | ⚪ | When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes. | `skills/copy-editing` |
|
||||
| **copywriting** | ⚪ | > | `skills/copywriting` |
|
||||
| **core-components** | ⚪ | Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library. | `skills/core-components` |
|
||||
| **crewai** | ⚪ | Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents. | `skills/crewai` |
|
||||
| **Cross-Site Scripting and HTML Injection Testing** | ⚪ | This skill should be used when the user asks to "test for XSS vulnerabilities", "perform cross-site scripting attacks", "identify HTML injection flaws", "exploit client-side injection vulnerabilities", "steal cookies via XSS", or "bypass content security policies". It provides comprehensive techniques for detecting, exploiting, and understanding XSS and HTML injection attack vectors in web applications. | `skills/xss-html-injection` |
|
||||
| **d3-viz** | ⚪ | Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment. | `skills/claude-d3js-skill` |
|
||||
| **database-design** | ⚪ | Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases. | `skills/database-design` |
|
||||
| **deployment-procedures** | ⚪ | Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts. | `skills/deployment-procedures` |
|
||||
| **design-orchestration** | ⚪ | > | `skills/design-orchestration` |
|
||||
| **discord-bot-architect** | ⚪ | Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding. | `skills/discord-bot-architect` |
|
||||
| **dispatching-parallel-agents** | ⚪ | Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | `skills/dispatching-parallel-agents` |
|
||||
| **doc-coauthoring** | ⚪ | Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | `skills/doc-coauthoring` |
|
||||
| **docker-expert** | ⚪ | Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY for Dockerfile optimization, container issues, image size problems, security hardening, networking, and orchestration challenges. | `skills/docker-expert` |
|
||||
| **documentation-templates** | ⚪ | Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation. | `skills/documentation-templates` |
|
||||
| **docx** | ⚪ | Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks | `skills/docx-official` |
|
||||
| **email-sequence** | ⚪ | When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle emails." For in-app onboarding, see onboarding-cro. | `skills/email-sequence` |
|
||||
| **email-systems** | ⚪ | Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns. | `skills/email-systems` |
|
||||
| **environment-setup-guide** | ⚪ | Guide developers through setting up development environments with proper tools, dependencies, and configurations | `skills/environment-setup-guide` |
|
||||
| **Ethical Hacking Methodology** | ⚪ | This skill should be used when the user asks to "learn ethical hacking", "understand penetration testing lifecycle", "perform reconnaissance", "conduct security scanning", "exploit vulnerabilities", or "write penetration test reports". It provides comprehensive ethical hacking methodology and techniques. | `skills/ethical-hacking-methodology` |
|
||||
| **exa-search** | ⚪ | Semantic search, similar content discovery, and structured research using Exa API | `skills/exa-search` |
|
||||
| **executing-plans** | ⚪ | Use when you have a written implementation plan to execute in a separate session with review checkpoints | `skills/executing-plans` |
|
||||
| **File Path Traversal Testing** | ⚪ | This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies. | `skills/file-path-traversal` |
|
||||
| **file-organizer** | ⚪ | Intelligently organizes files and folders by understanding context, finding duplicates, and suggesting better organizational structures. Use when user wants to clean up directories, organize downloads, remove duplicates, or restructure projects. | `skills/file-organizer` |
|
||||
| **file-uploads** | ⚪ | Expert at handling file uploads and cloud storage. Covers S3, Cloudflare R2, presigned URLs, multipart uploads, and image optimization. Knows how to handle large files without blocking. Use when: file upload, S3, R2, presigned URL, multipart. | `skills/file-uploads` |
|
||||
| **finishing-a-development-branch** | ⚪ | Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup | `skills/finishing-a-development-branch` |
|
||||
| **firebase** | ⚪ | Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data. I | `skills/firebase` |
|
||||
| **firecrawl-scraper** | ⚪ | Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API | `skills/firecrawl-scraper` |
|
||||
| **form-cro** | ⚪ | When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." For signup/registration forms, see signup-flow-cro. For popups containing forms, see popup-cro. | `skills/form-cro` |
|
||||
| **free-tool-strategy** | ⚪ | When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," or "free resource." This skill bridges engineering and marketing — useful for founders and technical marketers. | `skills/free-tool-strategy` |
|
||||
| **frontend-design** | ⚪ | Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. | `skills/frontend-design` |
|
||||
| **frontend-dev-guidelines** | ⚪ | Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code. | `skills/frontend-dev-guidelines` |
|
||||
| **frontend-patterns** | ⚪ | Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. | `skills/cc-skill-frontend-patterns` |
|
||||
| **game-art** | ⚪ | Game art principles. Visual style selection, asset pipeline, animation workflow. | `skills/game-development/game-art` |
|
||||
| **game-audio** | ⚪ | Game audio principles. Sound design, music integration, adaptive audio systems. | `skills/game-development/game-audio` |
|
||||
| **game-design** | ⚪ | Game design principles. GDD structure, balancing, player psychology, progression. | `skills/game-development/game-design` |
|
||||
| **game-development** | ⚪ | Game development orchestrator. Routes to platform-specific skills based on project needs. | `skills/game-development` |
|
||||
| **gcp-cloud-run** | ⚪ | Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functions (event-driven), cold start optimization, and event-driven architecture with Pub/Sub. | `skills/gcp-cloud-run` |
|
||||
| **geo-fundamentals** | ⚪ | Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity). | `skills/geo-fundamentals` |
|
||||
| **git-pushing** | ⚪ | Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests. | `skills/git-pushing` |
|
||||
| **github-workflow-automation** | ⚪ | Automate GitHub workflows with AI assistance. Includes PR reviews, issue triage, CI/CD integration, and Git operations. Use when automating GitHub workflows, setting up PR review automation, creating GitHub Actions, or triaging issues. | `skills/github-workflow-automation` |
|
||||
| **graphql** | ⚪ | GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper controls, clients can craft queries that bring down your server. This skill covers schema design, resolvers, DataLoader for N+1 prevention, federation for microservices, and client integration with Apollo/urql. Key insight: GraphQL is a contract. The schema is the API documentation. Design it carefully. | `skills/graphql` |
|
||||
| **HTML Injection Testing** | ⚪ | This skill should be used when the user asks to "test for HTML injection", "inject HTML into web pages", "perform HTML injection attacks", "deface web applications", or "test content injection vulnerabilities". It provides comprehensive HTML injection attack techniques and testing methodologies. | `skills/html-injection-testing` |
|
||||
| **hubspot-integration** | ⚪ | Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers Node.js and Python SDKs. Use when: hubspot, hubspot api, hubspot crm, hubspot integration, contacts api. | `skills/hubspot-integration` |
|
||||
| **i18n-localization** | ⚪ | Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support. | `skills/i18n-localization` |
|
||||
| **IDOR Vulnerability Testing** | ⚪ | This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control," "enumerate user IDs or object references," or "bypass authorization to access other users' data." It provides comprehensive guidance for detecting, exploiting, and remediating IDOR vulnerabilities in web applications. | `skills/idor-testing` |
|
||||
| **inngest** | ⚪ | Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution. | `skills/inngest` |
|
||||
| **interactive-portfolio** | ⚪ | Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, designer portfolios, creative portfolios, and portfolios that convert visitors into opportunities. Use when: portfolio, personal website, showcase work, developer portfolio, designer portfolio. | `skills/interactive-portfolio` |
|
||||
| **internal-comms** | ⚪ | A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | `skills/internal-comms-anthropic` |
|
||||
| **internal-comms** | ⚪ | A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | `skills/internal-comms-community` |
|
||||
| **javascript-mastery** | ⚪ | Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced patterns like async/await and functional programming. Use when explaining JS concepts, debugging JavaScript issues, or teaching JavaScript fundamentals. | `skills/javascript-mastery` |
|
||||
| **kaizen** | ⚪ | Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements. | `skills/kaizen` |
|
||||
| **langfuse** | ⚪ | Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation. | `skills/langfuse` |
|
||||
| **langgraph** | ⚪ | Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent. | `skills/langgraph` |
|
||||
| **launch-strategy** | ⚪ | When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum. | `skills/launch-strategy` |
|
||||
| **lint-and-validate** | ⚪ | Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis. | `skills/lint-and-validate` |
|
||||
| **Linux Privilege Escalation** | ⚪ | This skill should be used when the user asks to "escalate privileges on Linux", "find privesc vectors on Linux systems", "exploit sudo misconfigurations", "abuse SUID binaries", "exploit cron jobs for root access", "enumerate Linux systems for privilege escalation", or "gain root access from low-privilege shell". It provides comprehensive techniques for identifying and exploiting privilege escalation paths on Linux systems. | `skills/linux-privilege-escalation` |
|
||||
| **Linux Production Shell Scripts** | ⚪ | This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration. | `skills/linux-shell-scripting` |
|
||||
| **llm-app-patterns** | ⚪ | Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability. | `skills/llm-app-patterns` |
|
||||
| **loki-mode** | ⚪ | Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag. | `skills/loki-mode` |
|
||||
| **marketing-ideas** | ⚪ | When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing strategies,' 'marketing tactics,' 'ways to promote,' or 'ideas to grow.' This skill provides 140 proven marketing approaches organized by category. | `skills/marketing-ideas` |
|
||||
| **marketing-psychology** | ⚪ | When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application. | `skills/marketing-psychology` |
|
||||
| **mcp-builder** | ⚪ | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | `skills/mcp-builder` |
|
||||
| **Metasploit Framework** | ⚪ | This skill should be used when the user asks to "use Metasploit for penetration testing", "exploit vulnerabilities with msfconsole", "create payloads with msfvenom", "perform post-exploitation", "use auxiliary modules for scanning", or "develop custom exploits". It provides comprehensive guidance for leveraging the Metasploit Framework in security assessments. | `skills/metasploit-framework` |
|
||||
| **micro-saas-launcher** | ⚪ | Expert in launching small, focused SaaS products fast - the indie hacker approach to building profitable software. Covers idea validation, MVP development, pricing, launch strategies, and growing to sustainable revenue. Ship in weeks, not months. Use when: micro saas, indie hacker, small saas, side project, saas mvp. | `skills/micro-saas-launcher` |
|
||||
| **mobile-design** | ⚪ | Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps. | `skills/mobile-design` |
|
||||
| **mobile-games** | ⚪ | Mobile game development principles. Touch input, battery, performance, app stores. | `skills/game-development/mobile-games` |
|
||||
| **moodle-external-api-development** | ⚪ | Create custom external web service APIs for Moodle LMS. Use when implementing web services for course management, user tracking, quiz operations, or custom plugin functionality. Covers parameter validation, database operations, error handling, service registration, and Moodle coding standards. | `skills/moodle-external-api-development` |
|
||||
| **multi-agent-brainstorming** | ⚪ | > | `skills/multi-agent-brainstorming` |
|
||||
| **multiplayer** | ⚪ | Multiplayer game development principles. Architecture, networking, synchronization. | `skills/game-development/multiplayer` |
|
||||
| **neon-postgres** | ⚪ | Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration Use when: neon database, serverless postgres, database branching, neon postgres, postgres serverless. | `skills/neon-postgres` |
|
||||
| **nestjs-expert** | ⚪ | Nest.js framework expert specializing in module architecture, dependency injection, middleware, guards, interceptors, testing with Jest/Supertest, TypeORM/Mongoose integration, and Passport.js authentication. Use PROACTIVELY for any Nest.js application issues including architecture decisions, testing strategies, performance optimization, or debugging complex dependency injection problems. If a specialized expert is a better fit, I will recommend switching and stop. | `skills/nestjs-expert` |
|
||||
| **Network 101** | ⚪ | This skill should be used when the user asks to "set up a web server", "configure HTTP or HTTPS", "perform SNMP enumeration", "configure SMB shares", "test network services", or needs guidance on configuring and testing network services for penetration testing labs. | `skills/network-101` |
|
||||
| **nextjs-best-practices** | ⚪ | Next.js App Router principles. Server Components, data fetching, routing patterns. | `skills/nextjs-best-practices` |
|
||||
| **nextjs-supabase-auth** | ⚪ | Expert integration of Supabase Auth with Next.js App Router Use when: supabase auth next, authentication next.js, login supabase, auth middleware, protected route. | `skills/nextjs-supabase-auth` |
|
||||
| **nodejs-best-practices** | ⚪ | Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying. | `skills/nodejs-best-practices` |
|
||||
| **nosql-expert** | ⚪ | Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems. | `skills/nosql-expert` |
|
||||
| **notebooklm** | ⚪ | Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses. | `skills/notebooklm` |
|
||||
| **notion-template-business** | ⚪ | Expert in building and selling Notion templates as a business - not just making templates, but building a sustainable digital product business. Covers template design, pricing, marketplaces, marketing, and scaling to real revenue. Use when: notion template, sell templates, digital product, notion business, gumroad. | `skills/notion-template-business` |
|
||||
| **obsidian-clipper-template-creator** | ⚪ | Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content. | `skills/obsidian-clipper-template-creator` |
|
||||
| **onboarding-cro** | ⚪ | When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence. | `skills/onboarding-cro` |
|
||||
| **page-cro** | ⚪ | When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or blog posts. Also use when the user says "CRO," "conversion rate optimization," "this page isn't converting," "improve conversions," or "why isn't this page working." For signup/registration flows, see signup-flow-cro. For post-signup activation, see onboarding-cro. For forms outside of signup, see form-cro. For popups/modals, see popup-cro. | `skills/page-cro` |
|
||||
| **paid-ads** | ⚪ | When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization. | `skills/paid-ads` |
|
||||
| **parallel-agents** | ⚪ | Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives. | `skills/parallel-agents` |
|
||||
| **paywall-upgrade-cro** | ⚪ | When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," or "in-app pricing." Distinct from public pricing pages (see page-cro) — this skill focuses on in-product upgrade moments where the user has already experienced value. | `skills/paywall-upgrade-cro` |
|
||||
| **pc-games** | ⚪ | PC and console game development principles. Engine selection, platform features, optimization strategies. | `skills/game-development/pc-games` |
|
||||
| **pdf** | ⚪ | Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. | `skills/pdf-official` |
|
||||
| **Pentest Checklist** | ⚪ | This skill should be used when the user asks to "plan a penetration test", "create a security assessment checklist", "prepare for penetration testing", "define pentest scope", "follow security testing best practices", or needs a structured methodology for penetration testing engagements. | `skills/pentest-checklist` |
|
||||
| **Pentest Commands** | ⚪ | This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references. | `skills/pentest-commands` |
|
||||
| **performance-profiling** | ⚪ | Performance profiling principles. Measurement, analysis, and optimization techniques. | `skills/performance-profiling` |
|
||||
| **personal-tool-builder** | ⚪ | Expert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch your own itch, build for yourself, then discover others have the same itch. Covers rapid prototyping, local-first apps, CLI tools, scripts that grow into products, and the art of dogfooding. Use when: build a tool, personal tool, scratch my itch, solve my problem, CLI tool. | `skills/personal-tool-builder` |
|
||||
| **plaid-fintech** | ⚪ | Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech compliance best practices. Use when: plaid, bank account linking, bank connection, ach, account aggregation. | `skills/plaid-fintech` |
|
||||
| **plan-writing** | ⚪ | Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work. | `skills/plan-writing` |
|
||||
| **planning-with-files** | ⚪ | Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. | `skills/planning-with-files` |
|
||||
| **playwright-skill** | ⚪ | Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing. | `skills/playwright-skill` |
|
||||
| **popup-cro** | ⚪ | When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," or "overlay." For forms outside of popups, see form-cro. For general page conversion optimization, see page-cro. | `skills/popup-cro` |
|
||||
| **powershell-windows** | ⚪ | PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling. | `skills/powershell-windows` |
|
||||
| **pptx** | ⚪ | Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks | `skills/pptx-official` |
|
||||
| **pricing-strategy** | ⚪ | When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' or 'monetization.' This skill covers pricing research, tier structure, and packaging strategy. | `skills/pricing-strategy` |
|
||||
| **prisma-expert** | ⚪ | Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance, relation design, or database connection issues. | `skills/prisma-expert` |
|
||||
| **Privilege Escalation Methods** | ⚪ | This skill should be used when the user asks to "escalate privileges", "get root access", "become administrator", "privesc techniques", "abuse sudo", "exploit SUID binaries", "Kerberoasting", "pass-the-ticket", "token impersonation", or needs guidance on post-exploitation privilege escalation for Linux or Windows systems. | `skills/privilege-escalation-methods` |
|
||||
| **product-manager-toolkit** | ⚪ | Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development. | `skills/product-manager-toolkit` |
|
||||
| **production-code-audit** | ⚪ | Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations | `skills/production-code-audit` |
|
||||
| **programmatic-seo** | ⚪ | When the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pages," "[keyword] + [city] pages," "comparison pages," "integration pages," or "building many pages for SEO." For auditing existing SEO issues, see seo-audit. | `skills/programmatic-seo` |
|
||||
| **prompt-caching** | ⚪ | Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented. | `skills/prompt-caching` |
|
||||
| **prompt-engineer** | ⚪ | Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design. | `skills/prompt-engineer` |
|
||||
| **prompt-engineering** | ⚪ | Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior. | `skills/prompt-engineering` |
|
||||
| **prompt-library** | ⚪ | Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks. | `skills/prompt-library` |
|
||||
| **python-patterns** | ⚪ | Python development principles and decision-making. Framework selection, async patterns, type hints, project structure. Teaches thinking, not copying. | `skills/python-patterns` |
|
||||
| **rag-engineer** | ⚪ | Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval. | `skills/rag-engineer` |
|
||||
| **rag-implementation** | ⚪ | Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search. | `skills/rag-implementation` |
|
||||
| **react-patterns** | ⚪ | Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices. | `skills/react-patterns` |
|
||||
| **react-ui-patterns** | ⚪ | Modern React UI patterns for loading states, error handling, and data fetching. Use when building UI components, handling async data, or managing UI states. | `skills/react-ui-patterns` |
|
||||
| **receiving-code-review** | ⚪ | Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | `skills/receiving-code-review` |
|
||||
| **Red Team Tools and Methodology** | ⚪ | This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters. | `skills/red-team-tools` |
|
||||
| **red-team-tactics** | ⚪ | Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting. | `skills/red-team-tactics` |
|
||||
| **referral-program** | ⚪ | When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization. | `skills/referral-program` |
|
||||
| **remotion-best-practices** | ⚪ | Best practices for Remotion - Video creation in React | `skills/remotion-best-practices` |
|
||||
| **requesting-code-review** | ⚪ | Use when completing tasks, implementing major features, or before merging to verify work meets requirements | `skills/requesting-code-review` |
|
||||
| **research-engineer** | ⚪ | An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology. | `skills/research-engineer` |
|
||||
| **salesforce-development** | ⚪ | Expert patterns for Salesforce platform development including Lightning Web Components (LWC), Apex triggers and classes, REST/Bulk APIs, Connected Apps, and Salesforce DX with scratch orgs and 2nd generation packages (2GP). Use when: salesforce, sfdc, apex, lwc, lightning web components. | `skills/salesforce-development` |
|
||||
| **schema-markup** | ⚪ | When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit. | `skills/schema-markup` |
|
||||
| **scroll-experience** | ⚪ | Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences. Makes websites feel like experiences, not just pages. Use when: scroll animation, parallax, scroll storytelling, interactive story, cinematic website. | `skills/scroll-experience` |
|
||||
| **Security Scanning Tools** | ⚪ | This skill should be used when the user asks to "perform vulnerability scanning", "scan networks for open ports", "assess web application security", "scan wireless networks", "detect malware", "check cloud security", or "evaluate system compliance". It provides comprehensive guidance on security scanning tools and methodologies. | `skills/scanning-tools` |
|
||||
| **security-review** | ⚪ | Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns. | `skills/cc-skill-security-review` |
|
||||
| **segment-cdp** | ⚪ | Expert patterns for Segment Customer Data Platform including Analytics.js, server-side tracking, tracking plans with Protocols, identity resolution, destinations configuration, and data governance best practices. Use when: segment, analytics.js, customer data platform, cdp, tracking plan. | `skills/segment-cdp` |
|
||||
| **senior-architect** | ⚪ | Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns. | `skills/senior-architect` |
|
||||
| **senior-fullstack** | ⚪ | Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows. | `skills/senior-fullstack` |
|
||||
| **seo-audit** | ⚪ | When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," or "SEO health check." For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema-markup. | `skills/seo-audit` |
|
||||
| **seo-fundamentals** | ⚪ | SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles. | `skills/seo-fundamentals` |
|
||||
| **server-management** | ⚪ | Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands. | `skills/server-management` |
|
||||
| **Shodan Reconnaissance and Pentesting** | ⚪ | This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using Shodan," "scan IP ranges with Shodan," or "discover IoT devices and open ports." It provides comprehensive guidance for using Shodan's search engine, CLI, and API for penetration testing reconnaissance. | `skills/shodan-reconnaissance` |
|
||||
| **shopify-apps** | ⚪ | Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. Use when: shopify app, shopify, embedded app, polaris, app bridge. | `skills/shopify-apps` |
|
||||
| **shopify-development** | ⚪ | \| | `skills/shopify-development` |
|
||||
| **signup-flow-cro** | ⚪ | When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimization," "free trial signup," "reduce signup dropoff," or "account creation flow." For post-signup onboarding, see onboarding-cro. For lead capture forms (not account creation), see form-cro. | `skills/signup-flow-cro` |
|
||||
| **skill-creator** | ⚪ | Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. | `skills/skill-creator` |
|
||||
| **skill-developer** | ⚪ | Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule. | `skills/skill-developer` |
|
||||
| **slack-bot-builder** | ⚪ | Build Slack apps using the Bolt framework across Python, JavaScript, and Java. Covers Block Kit for rich UIs, interactive components, slash commands, event handling, OAuth installation flows, and Workflow Builder integration. Focus on best practices for production-ready Slack apps. Use when: slack bot, slack app, bolt framework, block kit, slash command. | `skills/slack-bot-builder` |
|
||||
| **slack-gif-creator** | ⚪ | Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack. | `skills/slack-gif-creator` |
|
||||
| **SMTP Penetration Testing** | ⚪ | This skill should be used when the user asks to "perform SMTP penetration testing", "enumerate email users", "test for open mail relays", "grab SMTP banners", "brute force email credentials", or "assess mail server security". It provides comprehensive techniques for testing SMTP server security. | `skills/smtp-penetration-testing` |
|
||||
| **social-content** | ⚪ | When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' or 'viral content.' This skill covers content creation, repurposing, and platform-specific strategies. | `skills/social-content` |
|
||||
| **software-architecture** | ⚪ | Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development. | `skills/software-architecture` |
|
||||
| **SQL Injection Testing** | ⚪ | This skill should be used when the user asks to "test for SQL injection vulnerabilities", "perform SQLi attacks", "bypass authentication using SQL injection", "extract database information through injection", "detect SQL injection flaws", or "exploit database query vulnerabilities". It provides comprehensive techniques for identifying, exploiting, and understanding SQL injection attack vectors across different database systems. | `skills/sql-injection-testing` |
|
||||
| **SQLMap Database Penetration Testing** | ⚪ | This skill should be used when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities. | `skills/sqlmap-database-pentesting` |
|
||||
| **SSH Penetration Testing** | ⚪ | This skill should be used when the user asks to "pentest SSH services", "enumerate SSH configurations", "brute force SSH credentials", "exploit SSH vulnerabilities", "perform SSH tunneling", or "audit SSH security". It provides comprehensive SSH penetration testing methodologies and techniques. | `skills/ssh-penetration-testing` |
|
||||
| **stripe-integration** | ⚪ | Get paid from day one. Payments, subscriptions, billing portal, webhooks, metered billing, Stripe Connect. The complete guide to implementing Stripe correctly, including all the edge cases that will bite you at 3am. This isn't just API calls - it's the full payment system: handling failures, managing subscriptions, dealing with dunning, and keeping revenue flowing. Use when: stripe, payments, subscription, billing, checkout. | `skills/stripe-integration` |
|
||||
| **subagent-driven-development** | ⚪ | Use when executing implementation plans with independent tasks in the current session | `skills/subagent-driven-development` |
|
||||
| **supabase-postgres-best-practices** | ⚪ | Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations. | `skills/postgres-best-practices` |
|
||||
| **systematic-debugging** | ⚪ | Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes | `skills/systematic-debugging` |
|
||||
| **tailwind-patterns** | ⚪ | Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture. | `skills/tailwind-patterns` |
|
||||
| **tavily-web** | ⚪ | Web search, content extraction, crawling, and research capabilities using Tavily API | `skills/tavily-web` |
|
||||
| **tdd-workflow** | ⚪ | Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle. | `skills/tdd-workflow` |
|
||||
| **telegram-bot-builder** | ⚪ | Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot. | `skills/telegram-bot-builder` |
|
||||
| **telegram-mini-app** | ⚪ | Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON ecosystem, Telegram Web App API, payments, user authentication, and building viral mini apps that monetize. Use when: telegram mini app, TWA, telegram web app, TON app, mini app. | `skills/telegram-mini-app` |
|
||||
| **templates** | ⚪ | Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks. | `skills/app-builder/templates` |
|
||||
| **test-driven-development** | ⚪ | Use when implementing any feature or bugfix, before writing implementation code | `skills/test-driven-development` |
|
||||
| **test-fixing** | ⚪ | Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass. | `skills/test-fixing` |
|
||||
| **testing-patterns** | ⚪ | Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD red-green-refactor cycle. | `skills/testing-patterns` |
|
||||
| **theme-factory** | ⚪ | Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly. | `skills/theme-factory` |
|
||||
| **Top 100 Web Vulnerabilities Reference** | ⚪ | This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks", "review access control weaknesses", "analyze API security issues", "assess security misconfigurations", "understand client-side vulnerabilities", "examine mobile and IoT security flaws", or "reference the OWASP-aligned vulnerability taxonomy". Use this skill to provide comprehensive vulnerability definitions, root causes, impacts, and mitigation strategies across all major web security categories. | `skills/top-web-vulnerabilities` |
|
||||
| **trigger-dev** | ⚪ | Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task. | `skills/trigger-dev` |
|
||||
| **twilio-communications** | ⚪ | Build communication features with Twilio: SMS messaging, voice calls, WhatsApp Business API, and user verification (2FA). Covers the full spectrum from simple notifications to complex IVR systems and multi-channel authentication. Critical focus on compliance, rate limits, and error handling. Use when: twilio, send SMS, text message, voice call, phone verification. | `skills/twilio-communications` |
|
||||
| **typescript-expert** | ⚪ | >- | `skills/typescript-expert` |
|
||||
| **ui-ux-pro-max** | ⚪ | UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples. | `skills/ui-ux-pro-max` |
|
||||
| **upstash-qstash** | ⚪ | Upstash QStash expert for serverless message queues, scheduled jobs, and reliable HTTP-based task delivery without managing infrastructure. Use when: qstash, upstash queue, serverless cron, scheduled http, message queue serverless. | `skills/upstash-qstash` |
|
||||
| **using-git-worktrees** | ⚪ | Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification | `skills/using-git-worktrees` |
|
||||
| **using-superpowers** | ⚪ | Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | `skills/using-superpowers` |
|
||||
| **vercel-deployment** | ⚪ | Expert knowledge for deploying to Vercel with Next.js Use when: vercel, deploy, deployment, hosting, production. | `skills/vercel-deployment` |
|
||||
| **vercel-react-best-practices** | ⚪ | React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements. | `skills/react-best-practices` |
|
||||
| **verification-before-completion** | ⚪ | Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | `skills/verification-before-completion` |
|
||||
| **viral-generator-builder** | ⚪ | Expert in building shareable generator tools that go viral - name generators, quiz makers, avatar creators, personality tests, and calculator tools. Covers the psychology of sharing, viral mechanics, and building tools people can't resist sharing with friends. Use when: generator tool, quiz maker, name generator, avatar creator, viral tool. | `skills/viral-generator-builder` |
|
||||
| **voice-agents** | ⚪ | Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu | `skills/voice-agents` |
|
||||
| **voice-ai-development** | ⚪ | Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice. | `skills/voice-ai-development` |
|
||||
| **vr-ar** | ⚪ | VR/AR development principles. Comfort, interaction, performance requirements. | `skills/game-development/vr-ar` |
|
||||
| **vulnerability-scanner** | ⚪ | Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization. | `skills/vulnerability-scanner` |
|
||||
| **web-artifacts-builder** | ⚪ | Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts. | `skills/web-artifacts-builder` |
|
||||
| **web-design-guidelines** | ⚪ | Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". | `skills/web-design-guidelines` |
|
||||
| **web-games** | ⚪ | Web browser game development principles. Framework selection, WebGPU, optimization, PWA. | `skills/game-development/web-games` |
|
||||
| **web-performance-optimization** | ⚪ | Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance | `skills/web-performance-optimization` |
|
||||
| **webapp-testing** | ⚪ | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. | `skills/webapp-testing` |
|
||||
| **Windows Privilege Escalation** | ⚪ | This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments. | `skills/windows-privilege-escalation` |
|
||||
| **Wireshark Network Traffic Analysis** | ⚪ | This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow TCP/UDP streams", "detect network anomalies", "investigate suspicious traffic", or "perform protocol analysis". It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark. | `skills/wireshark-analysis` |
|
||||
| **WordPress Penetration Testing** | ⚪ | This skill should be used when the user asks to "pentest WordPress sites", "scan WordPress for vulnerabilities", "enumerate WordPress users, themes, or plugins", "exploit WordPress vulnerabilities", or "use WPScan". It provides comprehensive WordPress security assessment methodologies. | `skills/wordpress-penetration-testing` |
|
||||
| **workflow-automation** | ⚪ | Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility | `skills/workflow-automation` |
|
||||
| **writing-plans** | ⚪ | Use when you have a spec or requirements for a multi-step task, before touching code | `skills/writing-plans` |
|
||||
| **writing-skills** | ⚪ | Use when creating new skills, editing existing skills, or verifying skills work before deployment | `skills/writing-skills` |
|
||||
| **xlsx** | ⚪ | Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas | `skills/xlsx-official` |
|
||||
| **zapier-make-patterns** | ⚪ | No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power | `skills/zapier-make-patterns` |
|
||||
|
||||
## Installation
|
||||
|
||||
@@ -409,6 +412,17 @@ Please ensure your skill follows the Antigravity/Claude Code best practices.
|
||||
|
||||
## Credits & Sources
|
||||
|
||||
We stand on the shoulders of giants.
|
||||
|
||||
👉 **[View the Full Attribution Ledger](docs/SOURCES.md)**
|
||||
|
||||
Key contributors and sources include:
|
||||
|
||||
- **HackTricks**
|
||||
- **OWASP**
|
||||
- **Anthropic / OpenAI / Google**
|
||||
- **The Open Source Community**
|
||||
|
||||
This collection would not be possible without the incredible work of the Claude Code community and official sources:
|
||||
|
||||
### Official Sources
|
||||
@@ -465,3 +479,31 @@ ai-developer-tools, ai-pair-programming, vibe-coding, skill, skills, SKILL.md, r
|
||||
claude-code, gemini-cli, codex-cli, antigravity, cursor, github-copilot, opencode,
|
||||
agentic-skills, ai-coding, llm-tools, ai-agents, autonomous-coding, mcp
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 👥 Repo Contributors
|
||||
|
||||
We officially thank the following contributors for their help in making this repository awesome!
|
||||
|
||||
- [1bcMax](https://github.com/1bcMax)
|
||||
- [Ahmed Rehan](https://github.com/ar27111994)
|
||||
- [arathiesh](https://github.com/arathiesh)
|
||||
- [BenedictKing](https://github.com/BenedictKing)
|
||||
- [GuppyTheCat](https://github.com/GuppyTheCat)
|
||||
- [Ianj332](https://github.com/Ianj332)
|
||||
- [krisnasantosa15](https://github.com/krisnasantosa15)
|
||||
- [Mohammad Faiz](https://github.com/mohdfaiz2k9)
|
||||
- [Nguyen Huu Loc](https://github.com/LocNguyenSGU)
|
||||
- [Owen Wu](https://github.com/yubing744)
|
||||
- [sck_0](https://github.com/sck_0)
|
||||
- [sickn33](https://github.com/sickn33)
|
||||
- [SuperJMN](https://github.com/SuperJMN)
|
||||
- [Tiger-Foxx](https://github.com/Tiger-Foxx)
|
||||
- [Viktor Ferenczi](https://github.com/viktor-ferenczi)
|
||||
- [vuth-dogo](https://github.com/vuth-dogo)
|
||||
- [zebbern](https://github.com/zebbern)
|
||||
|
||||
## Star History
|
||||
|
||||
[](https://www.star-history.com/#sickn33/antigravity-awesome-skills&type=date&legend=top-left)
|
||||
|
||||
47
RELEASE_NOTES.md
Normal file
47
RELEASE_NOTES.md
Normal file
@@ -0,0 +1,47 @@
|
||||
# 🚀 RELEASE NOTES: Antigravity Awesome Skills V3.0.0
|
||||
|
||||
**"The Governance Update"**
|
||||
|
||||
This release transforms the repository from a simple collection of scripts into a trusted, battle-tested platform for AI Agents.
|
||||
|
||||
## 🌟 Headline Features
|
||||
|
||||
### 1. Trusted Quality Bar (`docs/QUALITY_BAR.md`)
|
||||
|
||||
Every skill now undergoes a strict 5-point validation check.
|
||||
|
||||
- **Why?** No more broken scripts or vague instructions.
|
||||
- **For You:** Look for the 🟣 **Official** or 🔵 **Safe** badges.
|
||||
|
||||
### 2. Security Guardrails (`docs/SECURITY_GUARDRAILS.md`)
|
||||
|
||||
We introduced "Risk Labels" to protect you.
|
||||
|
||||
- 🔴 **Offensive** skills (Pentesting) now require explicit authorization mechanisms.
|
||||
- 🟢 **Safe** skills are guaranteed non-destructive.
|
||||
|
||||
### 3. Starter Packs (`docs/BUNDLES.md`)
|
||||
|
||||
Don't know where to start? We now have **9 Curated Bundles**:
|
||||
|
||||
- **Essentials Pack**: `concise-planning`, `clean-code`, `lint-and-validate`.
|
||||
- **Web Wizard**: `react-patterns`, `tailwind-mastery`, `frontend-design`.
|
||||
- **Agent Architect**: `mcp-builder`, `agent-evaluation`.
|
||||
- ...plus **DevOps**, **Game Dev**, **Data Science**, **Testing**, and more.
|
||||
|
||||
## 🛠️ For Developers & Contributors
|
||||
|
||||
- **New CI/CD**: Pull Requests are now automatically validated (`.github/workflows/ci.yml`).
|
||||
- **Strict Linting**: `scripts/validate_skills.py --strict` is the new sheriff in town.
|
||||
- **Attribution**: We now have a clear ledger of sources in `docs/SOURCES.md`.
|
||||
|
||||
## 📦 How to Update
|
||||
|
||||
```bash
|
||||
cd .agent/skills
|
||||
git pull origin main
|
||||
# (Optional) Verify your local skills
|
||||
python3 scripts/validate_skills.py
|
||||
```
|
||||
|
||||
_Built with ❤️ by the Antigravity Team._
|
||||
19
SECURITY.md
Normal file
19
SECURITY.md
Normal file
@@ -0,0 +1,19 @@
|
||||
# Security Policy
|
||||
|
||||
## Supported Versions
|
||||
|
||||
We track the `main` branch.
|
||||
|
||||
## Reporting a Vulnerability
|
||||
|
||||
**DO NOT** open a public Issue for security exploits.
|
||||
|
||||
If you find a security vulnerability (e.g., a skill that bypasses the "Authorized Use Only" check or executes malicious code without warning):
|
||||
|
||||
1. Email: `security@antigravity.dev` (Placeholder)
|
||||
2. Or open a **Private Advisory** on this repository.
|
||||
|
||||
## Offensive Skills Policy
|
||||
|
||||
Please read our [Security Guardrails](docs/SECURITY_GUARDRAILS.md).
|
||||
All offensive skills are strictly for **authorized educational and professional use only**.
|
||||
124
docs/BUNDLES.md
Normal file
124
docs/BUNDLES.md
Normal file
@@ -0,0 +1,124 @@
|
||||
# 📦 Antigravity Skill Bundles
|
||||
|
||||
Don't know where to start? Pick a bundle below to get a curated set of skills for your role.
|
||||
|
||||
## 🚀 The "Essentials" Starter Pack
|
||||
|
||||
_For everyone. Install these first._
|
||||
|
||||
- `concise-planning`: Always start with a plan.
|
||||
- `lint-and-validate`: Keep your code clean automatically.
|
||||
- `git-pushing`: Save your work safely.
|
||||
- `kaizen`: Continuous improvement mindset.
|
||||
|
||||
## 🛡️ The "Security Engineer" Pack
|
||||
|
||||
_For pentesting, auditing, and hardening._
|
||||
|
||||
- `ethical-hacking-methodology`: The Bible of ethical hacking.
|
||||
- `burp-suite-testing`: Web vulnerability scanning.
|
||||
- `owasp-top-10`: Check for the most common flaws.
|
||||
- `linux-privilege-escalation`: Advanced Linux security assessment.
|
||||
- `cloud-penetration-testing`: AWS/Azure/GCP security.
|
||||
|
||||
## 🌐 The "Web Wizard" Pack
|
||||
|
||||
_For building modern, high-performance web apps._
|
||||
|
||||
- `frontend-design`: UI guidelines and aesthetics.
|
||||
- `react-patterns`: Best practices for React (if available).
|
||||
- `tailwind-mastery`: Styling superpowers.
|
||||
- `form-cro`: Optimize your forms for conversion.
|
||||
- `seo-audit`: Get found on Google.
|
||||
|
||||
## 🤖 The "Agent Architect" Pack
|
||||
|
||||
_For building AI systems._
|
||||
|
||||
- `agent-evaluation`: Test your agents.
|
||||
- `langgraph`: Build stateful agent workflows.
|
||||
- `mcp-builder`: Create your own tools.
|
||||
- `prompt-engineering`: Master the art of talking to LLMs.
|
||||
|
||||
## 🎮 The "Indie Game Dev" Pack
|
||||
|
||||
_For building games with AI assistants._
|
||||
|
||||
- `game-development/game-design`: Mechanics and loops.
|
||||
- `game-development/2d-games`: Sprites and physics.
|
||||
- `game-development/3d-games`: Models and shaders.
|
||||
- `game-development/unity-csharp`: C# scripting mastery.
|
||||
- `algorithmic-art`: Generate assets with code.
|
||||
|
||||
## 🐍 The "Python Pro" Pack
|
||||
|
||||
_For backend heavyweights and data scientists._
|
||||
|
||||
- `python-patterns`: Idiomatic Python code.
|
||||
- `poetry-manager`: Dependency management that works.
|
||||
- `pytest-mastery`: Testing frameworks.
|
||||
- `fastapi-expert`: High-performance APIs.
|
||||
- `django-guide`: The battery-included framework.
|
||||
|
||||
## 🦄 The "Startup Founder" Pack
|
||||
|
||||
_For building products, not just code._
|
||||
|
||||
- `product-requirements-doc`: Define what to build.
|
||||
- `competitor-analysis`: Know who you are fighting.
|
||||
- `pitch-deck-creator`: Raise capital (or just explain your idea).
|
||||
- `landing-page-copy`: Write words that sell.
|
||||
- `stripe-integration`: Get paid.
|
||||
|
||||
## 🌧️ The "DevOps & Cloud" Pack
|
||||
|
||||
_For infrastructure and scaling._
|
||||
|
||||
- `docker-expert`: Master containers and multi-stage builds.
|
||||
- `aws-serverless`: Go serverless on AWS (Lambda, DynamoDB).
|
||||
- `environment-setup-guide`: Standardization for teams.
|
||||
- `deployment-procedures`: Safe rollout strategies.
|
||||
- `bash-linux`: Terminal wizardry.
|
||||
|
||||
## 📊 The "Data & Analytics" Pack
|
||||
|
||||
_For making sense of the numbers._
|
||||
|
||||
- `analytics-tracking`: Set up GA4/PostHog correctly.
|
||||
- `d3-viz`: Beautiful custom visualizations.
|
||||
- `sql-mastery`: Write better queries (Community skill).
|
||||
- `ab-test-setup`: Validated learning.
|
||||
|
||||
## 🎨 The "Creative Director" Pack
|
||||
|
||||
_For visuals, content, and branding._
|
||||
|
||||
- `canvas-design`: Generate posters and diagrams.
|
||||
- `frontend-design`: UI aesthetics.
|
||||
- `content-creator`: SEO-optimized blog posts.
|
||||
- `copy-editing`: Polish your prose.
|
||||
- `algorithmic-art`: Code-generated masterpieces.
|
||||
|
||||
## 🐞 The "QA & Testing" Pack
|
||||
|
||||
_For breaking things before users do._
|
||||
|
||||
- `test-driven-development`: Red, Green, Refactor.
|
||||
- `systematic-debugging`: Sherlock Holmes for code.
|
||||
- `browser-automation`: End-to-end testing with Playwright.
|
||||
- `ab-test-setup`: Validated experiments.
|
||||
- `code-review-checklist`: Catch bugs in PRs.
|
||||
|
||||
## 🖌️ The "Web Designer" Pack
|
||||
|
||||
_For pixel-perfect experiences._
|
||||
|
||||
- `ui-ux-pro-max`: Premium design systems/tokens.
|
||||
- `frontend-design`: The base layer of aesthetics.
|
||||
- `3d-web-experience`: Three.js & R3F magic.
|
||||
- `canvas-design`: Static visuals/posters.
|
||||
- `responsive-layout`: Mobile-first principles.
|
||||
|
||||
---
|
||||
|
||||
_To use a bundle, simply copy the skill names into your `.agent/skills` folder or use them with your agent._
|
||||
782
docs/EXAMPLES.md
782
docs/EXAMPLES.md
@@ -1,760 +1,56 @@
|
||||
# 💡 Real-World Examples - See Skills in Action
|
||||
# 🧪 Real-World Examples ("The Antigravity Cookbook")
|
||||
|
||||
**Learn by example!** This guide shows you real conversations using different skills.
|
||||
Skills are powerful on their own, but unstoppable when combined.
|
||||
Here are three common scenarios and how to solve them using this repository.
|
||||
|
||||
## 🥘 Recipe 1: The "Legacy Code Audit"
|
||||
|
||||
_Scenario: You just inherited a messy 5-year-old Node.js repo. You need to fix it safely._
|
||||
|
||||
**Skills Used:**
|
||||
|
||||
1. `concise-planning` (To map the chaos)
|
||||
2. `lint-and-validate` (To find the bugs)
|
||||
3. `security-audit` (To find the holes)
|
||||
|
||||
**The Workflow:**
|
||||
|
||||
1. **Plan**: "Agent, use `concise-planning` to create a checklist for refactoring `src/legacy-api.js`."
|
||||
2. **Audit**: "Run `security-audit` on the `package.json` to find vulnerable dependencies."
|
||||
3. **Fix**: "Use `lint-and-validate` rules to auto-fix the formatting issues in `src/`."
|
||||
|
||||
---
|
||||
|
||||
## Example 1: Designing a Feature with @brainstorming
|
||||
## 🥘 Recipe 2: The "Modern Web App"
|
||||
|
||||
### The Scenario
|
||||
You want to add a "dark mode" feature to your app, but you're not sure how to approach it.
|
||||
_Scenario: You need to build a high-performance Landing Page in 2 hours._
|
||||
|
||||
### The Conversation
|
||||
**Skills Used:**
|
||||
|
||||
```
|
||||
You: @brainstorming I want to add dark mode to my React app
|
||||
1. `frontend-design` (For aesthetics)
|
||||
2. `react-patterns` (For structure)
|
||||
3. `tailwind-mastery` (For speed)
|
||||
|
||||
AI: Great! Let me help you think through this. First, let me check your
|
||||
current project structure...
|
||||
|
||||
[AI examines your files]
|
||||
|
||||
I see you're using React with Tailwind CSS. Now, let's understand
|
||||
your requirements:
|
||||
|
||||
What's your primary goal for dark mode?
|
||||
a) User preference (toggle in settings)
|
||||
b) System preference (follow OS setting)
|
||||
c) Both (with manual override)
|
||||
**The Workflow:**
|
||||
|
||||
You: c) Both
|
||||
|
||||
AI: Perfect! That's the best user experience. Next question:
|
||||
|
||||
Where should the dark mode toggle be located?
|
||||
a) In the main navigation
|
||||
b) In a settings page
|
||||
c) In a dropdown menu
|
||||
d) Multiple locations
|
||||
|
||||
You: a) In the main navigation
|
||||
|
||||
AI: Good choice for accessibility. One more question:
|
||||
|
||||
Should dark mode preference persist across sessions?
|
||||
a) Yes, save to localStorage
|
||||
b) Yes, save to user account (requires backend)
|
||||
c) No, reset each session
|
||||
|
||||
You: a) Yes, save to localStorage
|
||||
|
||||
AI: Excellent! Now I have a clear picture. Let me present the design...
|
||||
|
||||
## Dark Mode Implementation Design
|
||||
|
||||
### Architecture Overview
|
||||
We'll use React Context for state management, Tailwind's dark mode
|
||||
utilities, and localStorage for persistence. The system will:
|
||||
1. Check OS preference on first visit
|
||||
2. Allow manual override via toggle
|
||||
3. Persist preference in localStorage
|
||||
|
||||
Does this approach look good so far?
|
||||
|
||||
You: Yes, continue
|
||||
|
||||
AI: [Continues with detailed design sections...]
|
||||
|
||||
[After design is complete]
|
||||
|
||||
I've saved the design to docs/plans/2026-01-20-dark-mode-design.md
|
||||
|
||||
Ready to set up for implementation?
|
||||
|
||||
You: Yes
|
||||
|
||||
AI: I'll create an isolated workspace using git worktrees and write an
|
||||
implementation plan. One moment...
|
||||
```
|
||||
|
||||
### What Happened
|
||||
- ✅ AI asked focused questions one at a time
|
||||
- ✅ Explored your specific context
|
||||
- ✅ Presented design in sections
|
||||
- ✅ Saved documentation
|
||||
- ✅ Prepared for implementation
|
||||
1. **Design**: "Use `frontend-design` to generate a color palette and typography for a 'Cyberpunk Coffee Shop'."
|
||||
2. **Scaffold**: "Initialize a Vite project. Then apply `react-patterns` to create the 'Hero' component."
|
||||
3. **Style**: "Use `tailwind-mastery` to make the buttons glassmorphic and responsive."
|
||||
|
||||
---
|
||||
|
||||
## Example 2: Debugging with @systematic-debugging
|
||||
## 🥘 Recipe 3: The "Agent Architect"
|
||||
|
||||
### The Scenario
|
||||
Your tests are failing, but you're not sure why.
|
||||
_Scenario: You want to build a custom AI agent that can verify its own code._
|
||||
|
||||
### The Conversation
|
||||
**Skills Used:**
|
||||
|
||||
```
|
||||
You: @systematic-debugging My tests are failing with "Cannot read property
|
||||
'map' of undefined"
|
||||
1. `mcp-builder` (To build tools)
|
||||
2. `agent-evaluation` (To test reliability)
|
||||
3. `prompt-engineering` (To refine instructions)
|
||||
|
||||
AI: Let me help you debug this systematically. First, I'll gather information:
|
||||
|
||||
1. Running the failing test to see the full error...
|
||||
|
||||
[AI runs: npm test]
|
||||
|
||||
I see the error occurs in UserList.test.tsx at line 45. Let me examine
|
||||
the test file and the component...
|
||||
|
||||
[AI reads both files]
|
||||
|
||||
## Hypothesis
|
||||
The test is failing because `users` prop is undefined when the component
|
||||
renders. This suggests the mock data isn't being passed correctly.
|
||||
|
||||
## Verification
|
||||
Let me check the test setup...
|
||||
|
||||
[AI examines test]
|
||||
|
||||
Found it! The test is calling:
|
||||
```typescript
|
||||
render(<UserList />)
|
||||
```
|
||||
|
||||
But UserList requires a `users` prop. The component expects:
|
||||
```typescript
|
||||
interface UserListProps {
|
||||
users: User[];
|
||||
}
|
||||
```
|
||||
|
||||
## Solution
|
||||
The test should pass the users prop:
|
||||
```typescript
|
||||
const mockUsers = [
|
||||
{ id: 1, name: 'Alice' },
|
||||
{ id: 2, name: 'Bob' }
|
||||
];
|
||||
|
||||
render(<UserList users={mockUsers} />)
|
||||
```
|
||||
|
||||
Should I apply this fix?
|
||||
**The Workflow:**
|
||||
|
||||
You: Yes
|
||||
|
||||
AI: [Applies fix and runs tests]
|
||||
|
||||
✅ All tests passing!
|
||||
|
||||
## Root Cause
|
||||
The test was missing required props. This is a common issue when
|
||||
components are refactored to require props that were previously optional.
|
||||
|
||||
## Prevention
|
||||
Consider adding TypeScript strict mode to catch these at compile time:
|
||||
```json
|
||||
"strict": true,
|
||||
"strictNullChecks": true
|
||||
```
|
||||
|
||||
Would you like me to add this to your tsconfig.json?
|
||||
```
|
||||
|
||||
### What Happened
|
||||
- ✅ Systematic investigation
|
||||
- ✅ Clear hypothesis
|
||||
- ✅ Verification before fixing
|
||||
- ✅ Root cause analysis
|
||||
- ✅ Prevention suggestions
|
||||
|
||||
---
|
||||
|
||||
## Example 3: Adding Payments with @stripe-integration
|
||||
|
||||
### The Scenario
|
||||
You need to add subscription billing to your SaaS app.
|
||||
|
||||
### The Conversation
|
||||
|
||||
```
|
||||
You: @stripe-integration I need to add monthly subscription billing
|
||||
|
||||
AI: I'll help you implement Stripe subscriptions. Let me understand your
|
||||
requirements:
|
||||
|
||||
Current stack detected:
|
||||
- Next.js 14 (App Router)
|
||||
- TypeScript
|
||||
- Prisma with PostgreSQL
|
||||
|
||||
For subscription billing, we'll need:
|
||||
|
||||
1. **Stripe Setup**
|
||||
- Stripe account and API keys
|
||||
- Webhook endpoint for events
|
||||
- Product and price IDs
|
||||
|
||||
2. **Backend Implementation**
|
||||
- API routes for checkout
|
||||
- Webhook handler
|
||||
- Database schema for subscriptions
|
||||
|
||||
3. **Frontend Implementation**
|
||||
- Pricing page
|
||||
- Checkout flow
|
||||
- Subscription management
|
||||
|
||||
Let's start with the backend. First, install dependencies:
|
||||
|
||||
```bash
|
||||
npm install stripe @stripe/stripe-js
|
||||
```
|
||||
|
||||
Now, let's create the database schema...
|
||||
|
||||
[AI provides Prisma schema]
|
||||
|
||||
```prisma
|
||||
model User {
|
||||
id String @id @default(cuid())
|
||||
email String @unique
|
||||
stripeCustomerId String? @unique
|
||||
subscriptions Subscription[]
|
||||
}
|
||||
|
||||
model Subscription {
|
||||
id String @id @default(cuid())
|
||||
userId String
|
||||
user User @relation(fields: [userId], references: [id])
|
||||
stripeSubscriptionId String @unique
|
||||
status String
|
||||
priceId String
|
||||
currentPeriodEnd DateTime
|
||||
createdAt DateTime @default(now())
|
||||
updatedAt DateTime @updatedAt
|
||||
}
|
||||
```
|
||||
|
||||
Next, let's create the checkout API route...
|
||||
|
||||
[AI provides complete implementation with:]
|
||||
- API route for creating checkout sessions
|
||||
- Webhook handler for subscription events
|
||||
- Helper functions for Stripe operations
|
||||
- Error handling and logging
|
||||
- TypeScript types
|
||||
|
||||
Now for the frontend...
|
||||
|
||||
[AI provides:]
|
||||
- Pricing page component
|
||||
- Checkout button component
|
||||
- Subscription status display
|
||||
- Tailwind styling
|
||||
|
||||
Finally, let's set up the webhook:
|
||||
|
||||
1. In Stripe Dashboard, add webhook endpoint:
|
||||
`https://yourdomain.com/api/webhooks/stripe`
|
||||
|
||||
2. Select these events:
|
||||
- customer.subscription.created
|
||||
- customer.subscription.updated
|
||||
- customer.subscription.deleted
|
||||
- invoice.payment_succeeded
|
||||
- invoice.payment_failed
|
||||
|
||||
3. Copy the webhook secret to your .env:
|
||||
```
|
||||
STRIPE_WEBHOOK_SECRET=whsec_...
|
||||
```
|
||||
|
||||
## Testing
|
||||
|
||||
Test locally with Stripe CLI:
|
||||
```bash
|
||||
stripe listen --forward-to localhost:3000/api/webhooks/stripe
|
||||
stripe trigger customer.subscription.created
|
||||
```
|
||||
|
||||
## Security Checklist
|
||||
- ✅ API keys in environment variables
|
||||
- ✅ Webhook signature verification
|
||||
- ✅ Server-side price validation
|
||||
- ✅ Idempotency keys for operations
|
||||
|
||||
Ready to test the implementation?
|
||||
```
|
||||
|
||||
### What Happened
|
||||
- ✅ Detected existing stack
|
||||
- ✅ Provided complete implementation
|
||||
- ✅ Included database schema
|
||||
- ✅ Added security best practices
|
||||
- ✅ Included testing instructions
|
||||
|
||||
---
|
||||
|
||||
## Example 4: Writing Copy with @copywriting
|
||||
|
||||
### The Scenario
|
||||
You need compelling copy for your SaaS landing page.
|
||||
|
||||
### The Conversation
|
||||
|
||||
```
|
||||
You: @copywriting Write homepage copy for my project management tool
|
||||
|
||||
AI: I'll help you create compelling homepage copy. First, let me understand
|
||||
your product:
|
||||
|
||||
What makes your project management tool different from competitors
|
||||
like Asana, Trello, or Monday.com?
|
||||
|
||||
You: It's specifically built for remote teams with built-in video standups
|
||||
and async communication features
|
||||
|
||||
AI: Excellent differentiator! Who is your primary target audience?
|
||||
a) Startups and small teams (2-20 people)
|
||||
b) Mid-size companies (20-200 people)
|
||||
c) Enterprise (200+ people)
|
||||
d) Freelancers and agencies
|
||||
|
||||
You: a) Startups and small teams
|
||||
|
||||
AI: Perfect. What's the main pain point you solve?
|
||||
|
||||
You: Remote teams waste time in unnecessary meetings and lose context
|
||||
in async communication
|
||||
|
||||
AI: Great! Now I have what I need. Here's your homepage copy:
|
||||
|
||||
---
|
||||
|
||||
## Hero Section
|
||||
|
||||
**Headline:**
|
||||
Run Your Remote Team Without the Meeting Overload
|
||||
|
||||
**Subheadline:**
|
||||
The project management tool built for distributed teams. Replace
|
||||
status meetings with async video standups and keep everyone in sync
|
||||
without the Zoom fatigue.
|
||||
|
||||
**CTA:**
|
||||
Start Free Trial → (No credit card required)
|
||||
|
||||
---
|
||||
|
||||
## Problem Section
|
||||
|
||||
**Headline:**
|
||||
Remote Work Shouldn't Mean More Meetings
|
||||
|
||||
**Body:**
|
||||
Your team is distributed across time zones. You're spending hours in
|
||||
status meetings just to stay aligned. Async updates get lost in Slack.
|
||||
Context disappears. Productivity suffers.
|
||||
|
||||
Sound familiar?
|
||||
|
||||
---
|
||||
|
||||
## Solution Section
|
||||
|
||||
**Headline:**
|
||||
Stay Aligned Without the Meeting Marathon
|
||||
|
||||
**Features:**
|
||||
|
||||
📹 **Async Video Standups**
|
||||
Record quick video updates on your schedule. Your team watches when
|
||||
it works for them. No more 9am calls for your teammate in Tokyo.
|
||||
|
||||
💬 **Context-Rich Communication**
|
||||
Every task, comment, and decision stays connected. No more hunting
|
||||
through Slack threads or email chains.
|
||||
|
||||
📊 **Visual Progress Tracking**
|
||||
See what's happening at a glance. Kanban boards, timelines, and
|
||||
dashboards that actually make sense.
|
||||
|
||||
🔔 **Smart Notifications**
|
||||
Get notified about what matters. Ignore the rest. Your focus time
|
||||
is sacred.
|
||||
|
||||
---
|
||||
|
||||
## Social Proof Section
|
||||
|
||||
**Headline:**
|
||||
Trusted by Remote Teams Worldwide
|
||||
|
||||
[Testimonial placeholders with structure]
|
||||
|
||||
---
|
||||
|
||||
## CTA Section
|
||||
|
||||
**Headline:**
|
||||
Ready to Reclaim Your Calendar?
|
||||
|
||||
**Body:**
|
||||
Join 500+ remote teams who've cut meeting time by 60% while staying
|
||||
more aligned than ever.
|
||||
|
||||
**CTA:**
|
||||
Start Your Free 14-Day Trial →
|
||||
|
||||
No credit card required. Cancel anytime.
|
||||
|
||||
---
|
||||
|
||||
## Copy Notes
|
||||
|
||||
**Tone:** Professional but conversational
|
||||
**Focus:** Pain point (too many meetings) → Solution (async video)
|
||||
**Differentiation:** Built specifically for remote teams
|
||||
**Social proof:** Quantified benefit (60% fewer meetings)
|
||||
|
||||
Would you like me to:
|
||||
1. Write alternative versions for A/B testing?
|
||||
2. Create copy for specific feature pages?
|
||||
3. Write email sequences for onboarding?
|
||||
```
|
||||
|
||||
### What Happened
|
||||
- ✅ Asked clarifying questions
|
||||
- ✅ Identified unique value proposition
|
||||
- ✅ Created benefit-focused copy
|
||||
- ✅ Included clear CTAs
|
||||
- ✅ Provided copy notes for consistency
|
||||
|
||||
---
|
||||
|
||||
## Example 5: Test-Driven Development with @test-driven-development
|
||||
|
||||
### The Scenario
|
||||
You need to implement a new feature: user authentication.
|
||||
|
||||
### The Conversation
|
||||
|
||||
```
|
||||
You: @test-driven-development I need to implement user login functionality
|
||||
|
||||
AI: Perfect! Let's use TDD to build this. Following the Red-Green-Refactor
|
||||
cycle, we'll write tests first, then implement.
|
||||
|
||||
## Step 1: Write the First Test (RED)
|
||||
|
||||
Let's start with the simplest case - successful login:
|
||||
|
||||
```typescript
|
||||
// auth.test.ts
|
||||
import { login } from './auth';
|
||||
|
||||
describe('login', () => {
|
||||
it('should return user data for valid credentials', async () => {
|
||||
const result = await login({
|
||||
email: 'user@example.com',
|
||||
password: 'correct-password'
|
||||
});
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.user).toHaveProperty('id');
|
||||
expect(result.user).toHaveProperty('email');
|
||||
expect(result.token).toBeDefined();
|
||||
});
|
||||
});
|
||||
```
|
||||
|
||||
Let's run this test to see it fail:
|
||||
|
||||
[AI runs: npm test]
|
||||
|
||||
✅ Test fails as expected (auth.ts doesn't exist yet)
|
||||
|
||||
## Step 2: Write Minimal Implementation (GREEN)
|
||||
|
||||
Now let's write just enough code to make this test pass:
|
||||
|
||||
```typescript
|
||||
// auth.ts
|
||||
interface LoginCredentials {
|
||||
email: string;
|
||||
password: string;
|
||||
}
|
||||
|
||||
interface LoginResult {
|
||||
success: boolean;
|
||||
user?: {
|
||||
id: string;
|
||||
email: string;
|
||||
};
|
||||
token?: string;
|
||||
}
|
||||
|
||||
export async function login(
|
||||
credentials: LoginCredentials
|
||||
): Promise<LoginResult> {
|
||||
// Minimal implementation to pass the test
|
||||
return {
|
||||
success: true,
|
||||
user: {
|
||||
id: '1',
|
||||
email: credentials.email
|
||||
},
|
||||
token: 'fake-token'
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
[AI runs: npm test]
|
||||
|
||||
✅ Test passes!
|
||||
|
||||
## Step 3: Add Next Test (RED)
|
||||
|
||||
Now let's test the failure case:
|
||||
|
||||
```typescript
|
||||
it('should return error for invalid credentials', async () => {
|
||||
const result = await login({
|
||||
email: 'user@example.com',
|
||||
password: 'wrong-password'
|
||||
});
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.error).toBe('Invalid credentials');
|
||||
expect(result.user).toBeUndefined();
|
||||
expect(result.token).toBeUndefined();
|
||||
});
|
||||
```
|
||||
|
||||
[AI runs: npm test]
|
||||
|
||||
❌ Test fails (always returns success)
|
||||
|
||||
## Step 4: Implement Real Logic (GREEN)
|
||||
|
||||
Now let's add actual authentication:
|
||||
|
||||
```typescript
|
||||
import bcrypt from 'bcrypt';
|
||||
import jwt from 'jsonwebtoken';
|
||||
import { db } from './db';
|
||||
|
||||
export async function login(
|
||||
credentials: LoginCredentials
|
||||
): Promise<LoginResult> {
|
||||
// Find user
|
||||
const user = await db.user.findUnique({
|
||||
where: { email: credentials.email }
|
||||
});
|
||||
|
||||
if (!user) {
|
||||
return {
|
||||
success: false,
|
||||
error: 'Invalid credentials'
|
||||
};
|
||||
}
|
||||
|
||||
// Verify password
|
||||
const validPassword = await bcrypt.compare(
|
||||
credentials.password,
|
||||
user.passwordHash
|
||||
);
|
||||
|
||||
if (!validPassword) {
|
||||
return {
|
||||
success: false,
|
||||
error: 'Invalid credentials'
|
||||
};
|
||||
}
|
||||
|
||||
// Generate token
|
||||
const token = jwt.sign(
|
||||
{ userId: user.id },
|
||||
process.env.JWT_SECRET!,
|
||||
{ expiresIn: '7d' }
|
||||
);
|
||||
|
||||
return {
|
||||
success: true,
|
||||
user: {
|
||||
id: user.id,
|
||||
email: user.email
|
||||
},
|
||||
token
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
[AI runs: npm test]
|
||||
|
||||
✅ All tests pass!
|
||||
|
||||
## Step 5: Add Edge Cases
|
||||
|
||||
Let's add more tests for edge cases:
|
||||
|
||||
```typescript
|
||||
it('should handle missing email', async () => {
|
||||
const result = await login({
|
||||
email: '',
|
||||
password: 'password'
|
||||
});
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.error).toBe('Email is required');
|
||||
});
|
||||
|
||||
it('should handle missing password', async () => {
|
||||
const result = await login({
|
||||
email: 'user@example.com',
|
||||
password: ''
|
||||
});
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.error).toBe('Password is required');
|
||||
});
|
||||
|
||||
it('should handle database errors gracefully', async () => {
|
||||
// Mock database error
|
||||
jest.spyOn(db.user, 'findUnique').mockRejectedValue(
|
||||
new Error('Database connection failed')
|
||||
);
|
||||
|
||||
const result = await login({
|
||||
email: 'user@example.com',
|
||||
password: 'password'
|
||||
});
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.error).toBe('An error occurred');
|
||||
});
|
||||
```
|
||||
|
||||
[AI implements validation and error handling]
|
||||
|
||||
## Step 6: Refactor (REFACTOR)
|
||||
|
||||
Now that all tests pass, let's refactor for better code quality:
|
||||
|
||||
```typescript
|
||||
// Extract validation
|
||||
function validateCredentials(credentials: LoginCredentials): string | null {
|
||||
if (!credentials.email) return 'Email is required';
|
||||
if (!credentials.password) return 'Password is required';
|
||||
return null;
|
||||
}
|
||||
|
||||
// Extract user verification
|
||||
async function verifyUser(
|
||||
email: string,
|
||||
password: string
|
||||
): Promise<User | null> {
|
||||
const user = await db.user.findUnique({ where: { email } });
|
||||
if (!user) return null;
|
||||
|
||||
const valid = await bcrypt.compare(password, user.passwordHash);
|
||||
return valid ? user : null;
|
||||
}
|
||||
|
||||
// Main function is now cleaner
|
||||
export async function login(
|
||||
credentials: LoginCredentials
|
||||
): Promise<LoginResult> {
|
||||
try {
|
||||
const validationError = validateCredentials(credentials);
|
||||
if (validationError) {
|
||||
return { success: false, error: validationError };
|
||||
}
|
||||
|
||||
const user = await verifyUser(
|
||||
credentials.email,
|
||||
credentials.password
|
||||
);
|
||||
|
||||
if (!user) {
|
||||
return { success: false, error: 'Invalid credentials' };
|
||||
}
|
||||
|
||||
const token = generateToken(user.id);
|
||||
|
||||
return {
|
||||
success: true,
|
||||
user: { id: user.id, email: user.email },
|
||||
token
|
||||
};
|
||||
} catch (error) {
|
||||
console.error('Login error:', error);
|
||||
return { success: false, error: 'An error occurred' };
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
[AI runs: npm test]
|
||||
|
||||
✅ All tests still pass after refactoring!
|
||||
|
||||
## Summary
|
||||
|
||||
We've implemented login functionality using TDD:
|
||||
- ✅ 5 tests covering happy path, errors, and edge cases
|
||||
- ✅ Clean, testable code
|
||||
- ✅ Proper error handling
|
||||
- ✅ Type safety with TypeScript
|
||||
|
||||
Next steps:
|
||||
1. Add rate limiting tests
|
||||
2. Add session management tests
|
||||
3. Add logout functionality
|
||||
|
||||
Should I continue with these?
|
||||
```
|
||||
|
||||
### What Happened
|
||||
- ✅ Followed Red-Green-Refactor cycle
|
||||
- ✅ Wrote tests before implementation
|
||||
- ✅ Covered edge cases
|
||||
- ✅ Refactored with confidence
|
||||
- ✅ Maintained test coverage
|
||||
|
||||
---
|
||||
|
||||
## Key Takeaways
|
||||
|
||||
### What Makes These Examples Effective?
|
||||
|
||||
1. **Skills ask clarifying questions** before jumping to solutions
|
||||
2. **Skills provide context-aware help** based on your project
|
||||
3. **Skills follow best practices** for their domain
|
||||
4. **Skills include complete examples** not just snippets
|
||||
5. **Skills explain the "why"** not just the "how"
|
||||
|
||||
### How to Get Similar Results
|
||||
|
||||
1. **Be specific** in your requests
|
||||
2. **Provide context** about your project
|
||||
3. **Answer questions** the skill asks
|
||||
4. **Review suggestions** before applying
|
||||
5. **Iterate** based on results
|
||||
|
||||
---
|
||||
|
||||
## Try These Yourself!
|
||||
|
||||
Pick a skill and try it with your own project:
|
||||
|
||||
- **Planning:** `@brainstorming` or `@writing-plans`
|
||||
- **Development:** `@test-driven-development` or `@react-best-practices`
|
||||
- **Debugging:** `@systematic-debugging` or `@test-fixing`
|
||||
- **Integration:** `@stripe-integration` or `@firebase`
|
||||
- **Marketing:** `@copywriting` or `@seo-audit`
|
||||
|
||||
---
|
||||
|
||||
**Want more examples?** Check individual skill folders for additional examples and use cases!
|
||||
1. **Build**: "Use `mcp-builder` to create a `verify-file` tool."
|
||||
2. **Instruct**: "Apply `prompt-engineering` patterns to the System Prompt so the agent always checks file paths."
|
||||
3. **Test**: "Run `agent-evaluation` to benchmark how often the agent fails to find the file."
|
||||
|
||||
64
docs/QUALITY_BAR.md
Normal file
64
docs/QUALITY_BAR.md
Normal file
@@ -0,0 +1,64 @@
|
||||
# 🏆 Quality Bar & Validation Standards
|
||||
|
||||
To transform **Antigravity Awesome Skills** from a collection of scripts into a trusted platform, every skill must meet a specific standard of quality and safety.
|
||||
|
||||
## The "Validated" Badge ✅
|
||||
|
||||
A skill earns the "Validated" badge only if it passes these **5 automated checks**:
|
||||
|
||||
### 1. Metadata Integrity
|
||||
|
||||
The `SKILL.md` frontmatter must be valid YAML and contain:
|
||||
|
||||
- `name`: Kebab-case, matches folder name.
|
||||
- `description`: Under 200 chars, clear value prop.
|
||||
- `risk`: One of `[none, safe, critical, offensive]`.
|
||||
- `source`: URL to original source (or "self" if original).
|
||||
|
||||
### 2. Clear Triggers ("When to use")
|
||||
|
||||
The skill MUST have a section explicitly stating when to trigger it.
|
||||
|
||||
- **Good**: "Use when the user asks to debug a React component."
|
||||
- **Bad**: "This skill helps you with code."
|
||||
|
||||
### 3. Safety & Risk Classification
|
||||
|
||||
Every skill must declare its risk level:
|
||||
|
||||
- 🟢 **none**: Pure text/reasoning (e.g., Brainstorming).
|
||||
- 🔵 **safe**: Reads files, runs safe commands (e.g., Linter).
|
||||
- 🟠 **critical**: Modifies state, deletes files, pushes to prod (e.g., Git Push).
|
||||
- 🔴 **offensive**: Pentesting/Red Team tools. **MUST** have "Authorized Use Only" warning.
|
||||
|
||||
### 4. Copy-Pasteable Examples
|
||||
|
||||
At least one code block or interaction example that a user (or agent) can immediately use.
|
||||
|
||||
### 5. Explicit Limitations
|
||||
|
||||
A list of known edge cases or things the skill _cannot_ do.
|
||||
|
||||
- _Example_: "Does not work on Windows without WSL."
|
||||
|
||||
---
|
||||
|
||||
## Support Levels
|
||||
|
||||
We also categorize skills by who maintains them:
|
||||
|
||||
| Level | Badge | Meaning |
|
||||
| :------------ | :---- | :-------------------------------------------------- |
|
||||
| **Official** | 🟣 | Maintained by the core team. High reliability. |
|
||||
| **Community** | ⚪ | Contributed by the ecosystem. Best effort support. |
|
||||
| **Verified** | ✨ | Community skill that has passed deep manual review. |
|
||||
|
||||
---
|
||||
|
||||
## How to Validate Your Skill
|
||||
|
||||
Run the validator script before submitting a PR:
|
||||
|
||||
```bash
|
||||
python3 scripts/validate_skills.py --strict
|
||||
```
|
||||
51
docs/SECURITY_GUARDRAILS.md
Normal file
51
docs/SECURITY_GUARDRAILS.md
Normal file
@@ -0,0 +1,51 @@
|
||||
# 🛡️ Security Guardrails & Policy
|
||||
|
||||
Antigravity Awesome Skills is a powerful toolkit. With great power comes great responsibility. This document defines the **Rules of Engagement** for all security and offensive capabilities in this repository.
|
||||
|
||||
## 🔴 Offensive Skills Policy (The "Red Line")
|
||||
|
||||
**What is an Offensive Skill?**
|
||||
Any skill designed to penetrate, exploit, disrupt, or simulate attacks against systems.
|
||||
_Examples: Pentesting, SQL Injection, Phishing Simulation, Red Teaming._
|
||||
|
||||
### 1. The "Authorized Use Only" Disclaimer
|
||||
|
||||
Every offensive skill **MUST** begin with this exact disclaimer in its `SKILL.md`:
|
||||
|
||||
> **⚠️ AUTHORIZED USE ONLY**
|
||||
> This skill is for educational purposes or authorized security assessments only.
|
||||
> You must have explicit, written permission from the system owner before using this tool.
|
||||
> Misuse of this tool is illegal and strictly prohibited.
|
||||
|
||||
### 2. Mandatory User Confirmation
|
||||
|
||||
Offensive skills must **NEVER** run fully autonomously.
|
||||
|
||||
- **Requirement**: The skill description/instructions must explicitly tell the agent to _ask for user confirmation_ before executing any exploit or attack command.
|
||||
- **Agent Instruction**: "Ask the user to verify the target URL/IP before running."
|
||||
|
||||
### 3. Safe by Design
|
||||
|
||||
- **No Weaponized Payloads**: Skills should not include active malware, ransomware, or non-educational exploits.
|
||||
- **Sandbox Recommended**: Instructions should recommend running in a contained environment (Docker/VM).
|
||||
|
||||
---
|
||||
|
||||
## 🔵 Defensive Skills Policy
|
||||
|
||||
**What is a Defensive Skill?**
|
||||
Tools for hardening, auditing, monitoring, or protecting systems.
|
||||
_Examples: Linting, Log Analysis, Configuration Auditing._
|
||||
|
||||
- **Data Privacy**: Defensive skills must not upload data to 3rd party servers without explicit user consent.
|
||||
- **Non-Destructive**: Audits should be read-only by default.
|
||||
|
||||
---
|
||||
|
||||
## ⚖️ Legal Disclaimer
|
||||
|
||||
By using this repository, you agree that:
|
||||
|
||||
1. You are responsible for your own actions.
|
||||
2. The authors and contributors are not liable for any damage caused by these tools.
|
||||
3. You will comply with all local, state, and federal laws regarding cybersecurity.
|
||||
21
docs/SOURCES.md
Normal file
21
docs/SOURCES.md
Normal file
@@ -0,0 +1,21 @@
|
||||
# 📜 Sources & Attributions
|
||||
|
||||
We believe in giving credit where credit is due.
|
||||
If you recognize your work here and it is not properly attributed, please open an Issue.
|
||||
|
||||
| Skill / Category | Original Source | License | Notes |
|
||||
| :-------------------------- | :----------------------------------------------------- | :------------- | :---------------------------- |
|
||||
| `cloud-penetration-testing` | [HackTricks](https://book.hacktricks.xyz/) | MIT / CC-BY-SA | Adapted for agentic use. |
|
||||
| `active-directory-attacks` | [HackTricks](https://book.hacktricks.xyz/) | MIT / CC-BY-SA | Adapted for agentic use. |
|
||||
| `owasp-top-10` | [OWASP](https://owasp.org/) | CC-BY-SA | Methodology adapted. |
|
||||
| `burp-suite-testing` | [PortSwigger](https://portswigger.net/burp) | N/A | Usage guide only (no binary). |
|
||||
| `crewai` | [CrewAI](https://github.com/joaomdmoura/crewAI) | MIT | Framework guides. |
|
||||
| `langgraph` | [LangGraph](https://github.com/langchain-ai/langgraph) | MIT | Framework guides. |
|
||||
| `react-patterns` | [React Docs](https://react.dev/) | CC-BY | Official patterns. |
|
||||
| **All Official Skills** | [Anthropic / Google / OpenAI] | Proprietary | Usage encouraged by vendors. |
|
||||
|
||||
## License Policy
|
||||
|
||||
- **Code**: All original code in this repository is **MIT**.
|
||||
- **Content**: Documentation is **CC-BY-4.0**.
|
||||
- **Third Party**: We respect the upstream licenses. If an imported skill is GPL, it will be marked clearly or excluded (we aim for MIT/Apache compatibility).
|
||||
@@ -2,69 +2,90 @@ import os
|
||||
import json
|
||||
import re
|
||||
|
||||
def parse_frontmatter(content):
|
||||
"""
|
||||
Simple frontmatter parser using regex (consistent with validate_skills.py).
|
||||
"""
|
||||
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
|
||||
if not fm_match:
|
||||
return {}
|
||||
|
||||
fm_text = fm_match.group(1)
|
||||
metadata = {}
|
||||
for line in fm_text.split('\n'):
|
||||
if ':' in line:
|
||||
key, val = line.split(':', 1)
|
||||
metadata[key.strip()] = val.strip().strip('"').strip("'")
|
||||
return metadata
|
||||
|
||||
def generate_index(skills_dir, output_file):
|
||||
print(f"🏗️ Generating index from: {skills_dir}")
|
||||
skills = []
|
||||
|
||||
for root, dirs, files in os.walk(skills_dir):
|
||||
# Skip .disabled directories
|
||||
dirs[:] = [d for d in dirs if d != '.disabled']
|
||||
# Skip .disabled or hidden directories
|
||||
dirs[:] = [d for d in dirs if not d.startswith('.')]
|
||||
|
||||
if "SKILL.md" in files:
|
||||
skill_path = os.path.join(root, "SKILL.md")
|
||||
dir_name = os.path.basename(root)
|
||||
parent_dir = os.path.basename(os.path.dirname(root))
|
||||
|
||||
# Default values
|
||||
skill_info = {
|
||||
"id": dir_name,
|
||||
"path": os.path.relpath(root, os.path.dirname(skills_dir)),
|
||||
"category": parent_dir if parent_dir != "skills" else "uncategorized",
|
||||
"name": dir_name.replace("-", " ").title(),
|
||||
"description": ""
|
||||
"description": "",
|
||||
"risk": "unknown",
|
||||
"source": "unknown"
|
||||
}
|
||||
|
||||
with open(skill_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
|
||||
# Try to extract from frontmatter first
|
||||
fm_match = re.search(r'^---\s*(.*?)\s*---', content, re.DOTALL)
|
||||
if fm_match:
|
||||
fm_content = fm_match.group(1)
|
||||
name_fm = re.search(r'^name:\s*(.+)$', fm_content, re.MULTILINE)
|
||||
desc_fm = re.search(r'^description:\s*(.+)$', fm_content, re.MULTILINE)
|
||||
|
||||
if name_fm:
|
||||
skill_info["name"] = name_fm.group(1).strip()
|
||||
if desc_fm:
|
||||
skill_info["description"] = desc_fm.group(1).strip()
|
||||
|
||||
# Fallback to Header and First Paragraph if needed
|
||||
if not skill_info["description"] or skill_info["description"] == "":
|
||||
name_match = re.search(r'^#\s+(.+)$', content, re.MULTILINE)
|
||||
if name_match and not fm_match: # Only override if no frontmatter name
|
||||
skill_info["name"] = name_match.group(1).strip()
|
||||
|
||||
# Extract first paragraph
|
||||
body = content
|
||||
if fm_match:
|
||||
body = content[fm_match.end():].strip()
|
||||
|
||||
lines = body.split('\n')
|
||||
desc_lines = []
|
||||
for line in lines:
|
||||
if line.startswith('#') or not line.strip():
|
||||
if desc_lines: break
|
||||
continue
|
||||
desc_lines.append(line.strip())
|
||||
|
||||
if desc_lines:
|
||||
skill_info["description"] = " ".join(desc_lines)[:150] + "..."
|
||||
try:
|
||||
with open(skill_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
except Exception as e:
|
||||
print(f"⚠️ Error reading {skill_path}: {e}")
|
||||
continue
|
||||
|
||||
# Parse Metadata
|
||||
metadata = parse_frontmatter(content)
|
||||
|
||||
# Merge Metadata
|
||||
if "name" in metadata: skill_info["name"] = metadata["name"]
|
||||
if "description" in metadata: skill_info["description"] = metadata["description"]
|
||||
if "risk" in metadata: skill_info["risk"] = metadata["risk"]
|
||||
if "source" in metadata: skill_info["source"] = metadata["source"]
|
||||
|
||||
# Fallback for description if missing in frontmatter (legacy support)
|
||||
if not skill_info["description"]:
|
||||
body = content
|
||||
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
|
||||
if fm_match:
|
||||
body = content[fm_match.end():].strip()
|
||||
|
||||
# Simple extraction of first non-header paragraph
|
||||
lines = body.split('\n')
|
||||
desc_lines = []
|
||||
for line in lines:
|
||||
if line.startswith('#') or not line.strip():
|
||||
if desc_lines: break
|
||||
continue
|
||||
desc_lines.append(line.strip())
|
||||
|
||||
if desc_lines:
|
||||
skill_info["description"] = " ".join(desc_lines)[:250].strip()
|
||||
|
||||
skills.append(skill_info)
|
||||
|
||||
# Sort validation: by name
|
||||
skills.sort(key=lambda x: x["name"].lower())
|
||||
|
||||
with open(output_file, 'w', encoding='utf-8') as f:
|
||||
json.dump(skills, f, indent=2)
|
||||
|
||||
print(f"✅ Generated index with {len(skills)} skills at: {output_file}")
|
||||
print(f"✅ Generated rich index with {len(skills)} skills at: {output_file}")
|
||||
return skills
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -20,7 +20,6 @@ def update_readme():
|
||||
content = f.read()
|
||||
|
||||
# 1. Update Title Count
|
||||
# Pattern: # 🌌 Antigravity Awesome Skills: [NUM]+ Agentic Skills
|
||||
content = re.sub(
|
||||
r'(# 🌌 Antigravity Awesome Skills: )\d+(\+ Agentic Skills)',
|
||||
f'\\g<1>{total_skills}\\g<2>',
|
||||
@@ -28,7 +27,6 @@ def update_readme():
|
||||
)
|
||||
|
||||
# 2. Update Blockquote Count
|
||||
# Pattern: Collection of [NUM]+ Universal
|
||||
content = re.sub(
|
||||
r'(Collection of )\d+(\+ Universal)',
|
||||
f'\\g<1>{total_skills}\\g<2>',
|
||||
@@ -36,7 +34,6 @@ def update_readme():
|
||||
)
|
||||
|
||||
# 3. Update Intro Text Count
|
||||
# Pattern: library of **[NUM] high-performance skills**
|
||||
content = re.sub(
|
||||
r'(library of \*\*)\d+( high-performance skills\*\*)',
|
||||
f'\\g<1>{total_skills}\\g<2>',
|
||||
@@ -44,14 +41,21 @@ def update_readme():
|
||||
)
|
||||
|
||||
# 4. Update Registry Header Count
|
||||
# Pattern: ## Full Skill Registry ([NUM]/[NUM])
|
||||
content = re.sub(
|
||||
r'(## Full Skill Registry \()\d+/\d+(\))',
|
||||
f'\\g<1>{total_skills}/{total_skills}\\g<2>',
|
||||
content
|
||||
)
|
||||
|
||||
# 5. Generate New Registry Table
|
||||
# 5. Insert Collections / Bundles Section (New in Phase 3)
|
||||
# This logic checks if "## 📦 Curated Collections" exists. If not, it creates it before Full Registry.
|
||||
collections_header = "## 📦 Curated Collections"
|
||||
|
||||
if collections_header not in content:
|
||||
# Insert before Full Skill Registry
|
||||
content = content.replace("## Full Skill Registry", f"{collections_header}\n\n[Check out our Starter Packs in docs/BUNDLES.md](docs/BUNDLES.md) to find the perfect toolkit for your role.\n\n## Full Skill Registry")
|
||||
|
||||
# 6. Generate New Registry Table
|
||||
print("🔄 Generating new registry table...")
|
||||
|
||||
# Store the Note block to preserve it
|
||||
@@ -61,30 +65,34 @@ def update_readme():
|
||||
if note_match:
|
||||
note_block = note_match.group(1)
|
||||
else:
|
||||
# Fallback default note if not found (though it should be there)
|
||||
note_block = "> [!NOTE] > **Document Skills**: We provide both **community** and **official Anthropic** versions for DOCX, PDF, PPTX, and XLSX. Locally, the official versions are used by default (via symlinks). In the repository, both versions are available for flexibility."
|
||||
note_block = "> [!NOTE] > **Document Skills**: We provide both **community** and **official Anthropic** versions. Locally, the official versions are used by default."
|
||||
|
||||
table_header = "| Skill Name | Description | Path |\n| :--- | :--- | :--- |"
|
||||
table_header = "| Skill Name | Risk | Description | Path |\n| :--- | :--- | :--- | :--- |"
|
||||
table_rows = []
|
||||
|
||||
for skill in skills:
|
||||
name = skill.get('name', 'Unknown')
|
||||
desc = skill.get('description', '').replace('\n', ' ').strip()
|
||||
path = skill.get('path', '')
|
||||
risk = skill.get('risk', 'unknown')
|
||||
|
||||
# Escape pipes in description to strictly avoid breaking the table
|
||||
desc = desc.replace('|', '\|')
|
||||
# Risk Icons
|
||||
risk_icon = "⚪"
|
||||
if risk == "official": risk_icon = "🟣" # Mapping official to purple
|
||||
if risk == "none": risk_icon = "🟢"
|
||||
if risk == "safe": risk_icon = "🔵"
|
||||
if risk == "critical": risk_icon = "🟠"
|
||||
if risk == "offensive": risk_icon = "🔴"
|
||||
|
||||
row = f"| **{name}** | {desc} | `{path}` |"
|
||||
# Escape pipes
|
||||
desc = desc.replace('|', r'\|')
|
||||
|
||||
row = f"| **{name}** | {risk_icon} | {desc} | `{path}` |"
|
||||
table_rows.append(row)
|
||||
|
||||
new_table_section = f"{note_block}\n\n{table_header}\n" + "\n".join(table_rows)
|
||||
|
||||
# Replace the old table section
|
||||
# We look for the start of the section and the end (which is either the next H2 or EOF)
|
||||
# The section starts after "## Full Skill Registry (X/X)"
|
||||
|
||||
# First, find the header position
|
||||
header_pattern = r'## Full Skill Registry \(\d+/\d+\)'
|
||||
header_match = re.search(header_pattern, content)
|
||||
|
||||
@@ -99,18 +107,10 @@ def update_readme():
|
||||
|
||||
if next_section_match:
|
||||
end_pos = start_pos + next_section_match.start()
|
||||
# Keep everything after the table
|
||||
rest_of_file = content[end_pos:]
|
||||
else:
|
||||
# Table goes to end of file
|
||||
rest_of_file = ""
|
||||
|
||||
# Check for text between Header and Table (usually just newlines or the Note)
|
||||
# We replace everything from Header End to Next Section with our New Table Section
|
||||
# but we need to supply the pre-table Note which we extracted/re-generated above.
|
||||
|
||||
# Simplification: We construct the top part (before header), add header, add new table section, add rest.
|
||||
|
||||
before_header = content[:header_match.start()]
|
||||
new_header = f"## Full Skill Registry ({total_skills}/{total_skills})"
|
||||
|
||||
@@ -119,7 +119,7 @@ def update_readme():
|
||||
with open(readme_path, 'w', encoding='utf-8') as f:
|
||||
f.write(new_content)
|
||||
|
||||
print("✅ README.md updated successfully.")
|
||||
print("✅ README.md updated successfully with Collections link and Risk columns.")
|
||||
|
||||
if __name__ == "__main__":
|
||||
update_readme()
|
||||
|
||||
@@ -1,52 +1,124 @@
|
||||
import os
|
||||
import re
|
||||
import argparse
|
||||
import sys
|
||||
|
||||
def validate_skills(skills_dir):
|
||||
def parse_frontmatter(content):
|
||||
"""
|
||||
Simple frontmatter parser using regex to avoid external dependencies.
|
||||
Returns a dict of key-values.
|
||||
"""
|
||||
fm_match = re.search(r'^---\s*\n(.*?)\n---', content, re.DOTALL)
|
||||
if not fm_match:
|
||||
return None
|
||||
|
||||
fm_text = fm_match.group(1)
|
||||
metadata = {}
|
||||
for line in fm_text.split('\n'):
|
||||
if ':' in line:
|
||||
key, val = line.split(':', 1)
|
||||
metadata[key.strip()] = val.strip().strip('"').strip("'")
|
||||
return metadata
|
||||
|
||||
def validate_skills(skills_dir, strict_mode=False):
|
||||
print(f"🔍 Validating skills in: {skills_dir}")
|
||||
print(f"⚙️ Mode: {'STRICT (CI)' if strict_mode else 'Standard (Dev)'}")
|
||||
|
||||
errors = []
|
||||
warnings = []
|
||||
skill_count = 0
|
||||
|
||||
# Pre-compiled regex
|
||||
security_disclaimer_pattern = re.compile(r"AUTHORIZED USE ONLY", re.IGNORECASE)
|
||||
trigger_section_pattern = re.compile(r"^##\s+When to Use", re.MULTILINE | re.IGNORECASE)
|
||||
|
||||
valid_risk_levels = ["none", "safe", "critical", "offensive"]
|
||||
|
||||
for root, dirs, files in os.walk(skills_dir):
|
||||
# Skip .disabled directories
|
||||
dirs[:] = [d for d in dirs if d != '.disabled']
|
||||
# Skip .disabled or hidden directories
|
||||
dirs[:] = [d for d in dirs if not d.startswith('.')]
|
||||
|
||||
if "SKILL.md" in files:
|
||||
skill_count += 1
|
||||
skill_path = os.path.join(root, "SKILL.md")
|
||||
rel_path = os.path.relpath(skill_path, skills_dir)
|
||||
|
||||
with open(skill_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
try:
|
||||
with open(skill_path, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
except Exception as e:
|
||||
errors.append(f"❌ {rel_path}: Unreadable file - {str(e)}")
|
||||
continue
|
||||
|
||||
# Check for Frontmatter or Header
|
||||
has_frontmatter = content.strip().startswith("---")
|
||||
has_header = re.search(r'^#\s+', content, re.MULTILINE)
|
||||
|
||||
if not (has_frontmatter or has_header):
|
||||
errors.append(f"❌ {rel_path}: Missing frontmatter or top-level heading")
|
||||
|
||||
if has_frontmatter:
|
||||
# Basic check for name and description in frontmatter
|
||||
fm_match = re.search(r'^---\s*(.*?)\s*---', content, re.DOTALL)
|
||||
if fm_match:
|
||||
fm_content = fm_match.group(1)
|
||||
if "name:" not in fm_content:
|
||||
errors.append(f"⚠️ {rel_path}: Frontmatter missing 'name:'")
|
||||
if "description:" not in fm_content:
|
||||
errors.append(f"⚠️ {rel_path}: Frontmatter missing 'description:'")
|
||||
else:
|
||||
errors.append(f"❌ {rel_path}: Malformed frontmatter")
|
||||
# 1. Frontmatter Check
|
||||
metadata = parse_frontmatter(content)
|
||||
if not metadata:
|
||||
errors.append(f"❌ {rel_path}: Missing or malformed YAML frontmatter")
|
||||
continue # Cannot proceed without metadata
|
||||
|
||||
# 2. Metadata Schema Checks
|
||||
if "name" not in metadata:
|
||||
errors.append(f"❌ {rel_path}: Missing 'name' in frontmatter")
|
||||
elif metadata["name"] != os.path.basename(root):
|
||||
warnings.append(f"⚠️ {rel_path}: Name '{metadata['name']}' does not match folder name '{os.path.basename(root)}'")
|
||||
|
||||
if "description" not in metadata:
|
||||
errors.append(f"❌ {rel_path}: Missing 'description' in frontmatter")
|
||||
|
||||
# Risk Validation (Quality Bar)
|
||||
if "risk" not in metadata:
|
||||
msg = f"⚠️ {rel_path}: Missing 'risk' label (defaulting to 'unknown')"
|
||||
if strict_mode: errors.append(msg.replace("⚠️", "❌"))
|
||||
else: warnings.append(msg)
|
||||
elif metadata["risk"] not in valid_risk_levels:
|
||||
errors.append(f"❌ {rel_path}: Invalid risk level '{metadata['risk']}'. Must be one of {valid_risk_levels}")
|
||||
|
||||
# Source Validation
|
||||
if "source" not in metadata:
|
||||
msg = f"⚠️ {rel_path}: Missing 'source' attribution"
|
||||
if strict_mode: errors.append(msg.replace("⚠️", "❌"))
|
||||
else: warnings.append(msg)
|
||||
|
||||
# 3. Content Checks (Triggers)
|
||||
if not trigger_section_pattern.search(content):
|
||||
msg = f"⚠️ {rel_path}: Missing '## When to Use' section"
|
||||
if strict_mode: errors.append(msg.replace("⚠️", "❌"))
|
||||
else: warnings.append(msg)
|
||||
|
||||
# 4. Security Guardrails
|
||||
if metadata.get("risk") == "offensive":
|
||||
if not security_disclaimer_pattern.search(content):
|
||||
errors.append(f"🚨 {rel_path}: OFFENSIVE SKILL MISSING SECURITY DISCLAIMER! (Must contain 'AUTHORIZED USE ONLY')")
|
||||
|
||||
# Reporting
|
||||
print(f"\n📊 Checked {skill_count} skills.")
|
||||
|
||||
if warnings:
|
||||
print(f"\n⚠️ Found {len(warnings)} Warnings:")
|
||||
for w in warnings:
|
||||
print(w)
|
||||
|
||||
print(f"✅ Found and checked {skill_count} skills.")
|
||||
if errors:
|
||||
print("\n⚠️ Validation Results:")
|
||||
for err in errors:
|
||||
print(err)
|
||||
print(f"\n❌ Found {len(errors)} Critical Errors:")
|
||||
for e in errors:
|
||||
print(e)
|
||||
return False
|
||||
else:
|
||||
print("✨ All skills passed basic validation!")
|
||||
return True
|
||||
|
||||
if strict_mode and warnings:
|
||||
print("\n❌ STRICT MODE: Failed due to warnings.")
|
||||
return False
|
||||
|
||||
print("\n✨ All skills passed validation!")
|
||||
return True
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Validate Antigravity Skills")
|
||||
parser.add_argument("--strict", action="store_true", help="Fail on warnings (for CI)")
|
||||
args = parser.parse_args()
|
||||
|
||||
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
skills_path = os.path.join(base_dir, "skills")
|
||||
validate_skills(skills_path)
|
||||
|
||||
success = validate_skills(skills_path, strict_mode=args.strict)
|
||||
if not success:
|
||||
sys.exit(1)
|
||||
|
||||
@@ -1,508 +1,232 @@
|
||||
---
|
||||
name: ab-test-setup
|
||||
description: When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
|
||||
description: Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
|
||||
---
|
||||
|
||||
# A/B Test Setup
|
||||
|
||||
You are an expert in experimentation and A/B testing. Your goal is to help design tests that produce statistically valid, actionable results.
|
||||
## 1️⃣ Purpose & Scope
|
||||
|
||||
## Initial Assessment
|
||||
Ensure every A/B test is **valid, rigorous, and safe** before a single line of code is written.
|
||||
|
||||
Before designing a test, understand:
|
||||
|
||||
1. **Test Context**
|
||||
- What are you trying to improve?
|
||||
- What change are you considering?
|
||||
- What made you want to test this?
|
||||
|
||||
2. **Current State**
|
||||
- Baseline conversion rate?
|
||||
- Current traffic volume?
|
||||
- Any historical test data?
|
||||
|
||||
3. **Constraints**
|
||||
- Technical implementation complexity?
|
||||
- Timeline requirements?
|
||||
- Tools available?
|
||||
- Prevents "peeking"
|
||||
- Enforces statistical power
|
||||
- Blocks invalid hypotheses
|
||||
|
||||
---
|
||||
|
||||
## Core Principles
|
||||
## 2️⃣ Pre-Requisites
|
||||
|
||||
### 1. Start with a Hypothesis
|
||||
- Not just "let's see what happens"
|
||||
- Specific prediction of outcome
|
||||
- Based on reasoning or data
|
||||
You must have:
|
||||
|
||||
### 2. Test One Thing
|
||||
- Single variable per test
|
||||
- Otherwise you don't know what worked
|
||||
- Save MVT for later
|
||||
- A clear user problem
|
||||
- Access to an analytics source
|
||||
- Roughly estimated traffic volume
|
||||
|
||||
### 3. Statistical Rigor
|
||||
- Pre-determine sample size
|
||||
- Don't peek and stop early
|
||||
- Commit to the methodology
|
||||
### Hypothesis Quality Checklist
|
||||
|
||||
### 4. Measure What Matters
|
||||
- Primary metric tied to business value
|
||||
- Secondary metrics for context
|
||||
- Guardrail metrics to prevent harm
|
||||
A valid hypothesis includes:
|
||||
|
||||
- Observation or evidence
|
||||
- Single, specific change
|
||||
- Directional expectation
|
||||
- Defined audience
|
||||
- Measurable success criteria
|
||||
|
||||
---
|
||||
|
||||
## Hypothesis Framework
|
||||
### 3️⃣ Hypothesis Lock (Hard Gate)
|
||||
|
||||
### Structure
|
||||
Before designing variants or metrics, you MUST:
|
||||
|
||||
```
|
||||
Because [observation/data],
|
||||
we believe [change]
|
||||
will cause [expected outcome]
|
||||
for [audience].
|
||||
We'll know this is true when [metrics].
|
||||
```
|
||||
- Present the **final hypothesis**
|
||||
- Specify:
|
||||
- Target audience
|
||||
- Primary metric
|
||||
- Expected direction of effect
|
||||
- Minimum Detectable Effect (MDE)
|
||||
|
||||
### Examples
|
||||
Ask explicitly:
|
||||
|
||||
**Weak hypothesis:**
|
||||
"Changing the button color might increase clicks."
|
||||
> “Is this the final hypothesis we are committing to for this test?”
|
||||
|
||||
**Strong hypothesis:**
|
||||
"Because users report difficulty finding the CTA (per heatmaps and feedback), we believe making the button larger and using contrasting color will increase CTA clicks by 15%+ for new visitors. We'll measure click-through rate from page view to signup start."
|
||||
|
||||
### Good Hypotheses Include
|
||||
|
||||
- **Observation**: What prompted this idea
|
||||
- **Change**: Specific modification
|
||||
- **Effect**: Expected outcome and direction
|
||||
- **Audience**: Who this applies to
|
||||
- **Metric**: How you'll measure success
|
||||
**Do NOT proceed until confirmed.**
|
||||
|
||||
---
|
||||
|
||||
## Test Types
|
||||
### 4️⃣ Assumptions & Validity Check (Mandatory)
|
||||
|
||||
### A/B Test (Split Test)
|
||||
- Two versions: Control (A) vs. Variant (B)
|
||||
- Single change between versions
|
||||
- Most common, easiest to analyze
|
||||
Explicitly list assumptions about:
|
||||
|
||||
### A/B/n Test
|
||||
- Multiple variants (A vs. B vs. C...)
|
||||
- Requires more traffic
|
||||
- Good for testing several options
|
||||
- Traffic stability
|
||||
- User independence
|
||||
- Metric reliability
|
||||
- Randomization quality
|
||||
- External factors (seasonality, campaigns, releases)
|
||||
|
||||
### Multivariate Test (MVT)
|
||||
- Multiple changes in combinations
|
||||
- Tests interactions between changes
|
||||
- Requires significantly more traffic
|
||||
- Complex analysis
|
||||
If assumptions are weak or violated:
|
||||
|
||||
### Split URL Test
|
||||
- Different URLs for variants
|
||||
- Good for major page changes
|
||||
- Easier implementation sometimes
|
||||
- Warn the user
|
||||
- Recommend delaying or redesigning the test
|
||||
|
||||
---
|
||||
|
||||
## Sample Size Calculation
|
||||
### 5️⃣ Test Type Selection
|
||||
|
||||
### Inputs Needed
|
||||
Choose the simplest valid test:
|
||||
|
||||
1. **Baseline conversion rate**: Your current rate
|
||||
2. **Minimum detectable effect (MDE)**: Smallest change worth detecting
|
||||
3. **Statistical significance level**: Usually 95%
|
||||
4. **Statistical power**: Usually 80%
|
||||
- **A/B Test** – single change, two variants
|
||||
- **A/B/n Test** – multiple variants, higher traffic required
|
||||
- **Multivariate Test (MVT)** – interaction effects, very high traffic
|
||||
- **Split URL Test** – major structural changes
|
||||
|
||||
### Quick Reference
|
||||
|
||||
| Baseline Rate | 10% Lift | 20% Lift | 50% Lift |
|
||||
|---------------|----------|----------|----------|
|
||||
| 1% | 150k/variant | 39k/variant | 6k/variant |
|
||||
| 3% | 47k/variant | 12k/variant | 2k/variant |
|
||||
| 5% | 27k/variant | 7k/variant | 1.2k/variant |
|
||||
| 10% | 12k/variant | 3k/variant | 550/variant |
|
||||
|
||||
### Formula Resources
|
||||
- Evan Miller's calculator: https://www.evanmiller.org/ab-testing/sample-size.html
|
||||
- Optimizely's calculator: https://www.optimizely.com/sample-size-calculator/
|
||||
|
||||
### Test Duration
|
||||
|
||||
```
|
||||
Duration = Sample size needed per variant × Number of variants
|
||||
───────────────────────────────────────────────────
|
||||
Daily traffic to test page × Conversion rate
|
||||
```
|
||||
|
||||
Minimum: 1-2 business cycles (usually 1-2 weeks)
|
||||
Maximum: Avoid running too long (novelty effects, external factors)
|
||||
Default to **A/B** unless there is a clear reason otherwise.
|
||||
|
||||
---
|
||||
|
||||
## Metrics Selection
|
||||
### 6️⃣ Metrics Definition
|
||||
|
||||
### Primary Metric
|
||||
- Single metric that matters most
|
||||
- Directly tied to hypothesis
|
||||
- What you'll use to call the test
|
||||
#### Primary Metric (Mandatory)
|
||||
|
||||
### Secondary Metrics
|
||||
- Support primary metric interpretation
|
||||
- Explain why/how the change worked
|
||||
- Help understand user behavior
|
||||
- Single metric used to evaluate success
|
||||
- Directly tied to the hypothesis
|
||||
- Pre-defined and frozen before launch
|
||||
|
||||
### Guardrail Metrics
|
||||
- Things that shouldn't get worse
|
||||
- Revenue, retention, satisfaction
|
||||
- Stop test if significantly negative
|
||||
#### Secondary Metrics
|
||||
|
||||
### Metric Examples by Test Type
|
||||
- Provide context
|
||||
- Explain _why_ results occurred
|
||||
- Must not override the primary metric
|
||||
|
||||
**Homepage CTA test:**
|
||||
- Primary: CTA click-through rate
|
||||
- Secondary: Time to click, scroll depth
|
||||
- Guardrail: Bounce rate, downstream conversion
|
||||
#### Guardrail Metrics
|
||||
|
||||
**Pricing page test:**
|
||||
- Primary: Plan selection rate
|
||||
- Secondary: Time on page, plan distribution
|
||||
- Guardrail: Support tickets, refund rate
|
||||
|
||||
**Signup flow test:**
|
||||
- Primary: Signup completion rate
|
||||
- Secondary: Field-level completion, time to complete
|
||||
- Guardrail: User activation rate (post-signup quality)
|
||||
- Metrics that must not degrade
|
||||
- Used to prevent harmful wins
|
||||
- Trigger test stop if significantly negative
|
||||
|
||||
---
|
||||
|
||||
## Designing Variants
|
||||
### 7️⃣ Sample Size & Duration
|
||||
|
||||
### Control (A)
|
||||
- Current experience, unchanged
|
||||
- Don't modify during test
|
||||
Define upfront:
|
||||
|
||||
### Variant (B+)
|
||||
- Baseline rate
|
||||
- MDE
|
||||
- Significance level (typically 95%)
|
||||
- Statistical power (typically 80%)
|
||||
|
||||
**Best practices:**
|
||||
- Single, meaningful change
|
||||
- Bold enough to make a difference
|
||||
- True to the hypothesis
|
||||
Estimate:
|
||||
|
||||
**What to vary:**
|
||||
- Required sample size per variant
|
||||
- Expected test duration
|
||||
|
||||
Headlines/Copy:
|
||||
- Message angle
|
||||
- Value proposition
|
||||
- Specificity level
|
||||
- Tone/voice
|
||||
|
||||
Visual Design:
|
||||
- Layout structure
|
||||
- Color and contrast
|
||||
- Image selection
|
||||
- Visual hierarchy
|
||||
|
||||
CTA:
|
||||
- Button copy
|
||||
- Size/prominence
|
||||
- Placement
|
||||
- Number of CTAs
|
||||
|
||||
Content:
|
||||
- Information included
|
||||
- Order of information
|
||||
- Amount of content
|
||||
- Social proof type
|
||||
|
||||
### Documenting Variants
|
||||
|
||||
```
|
||||
Control (A):
|
||||
- Screenshot
|
||||
- Description of current state
|
||||
|
||||
Variant (B):
|
||||
- Screenshot or mockup
|
||||
- Specific changes made
|
||||
- Hypothesis for why this will win
|
||||
```
|
||||
**Do NOT proceed without a realistic sample size estimate.**
|
||||
|
||||
---
|
||||
|
||||
## Traffic Allocation
|
||||
### 8️⃣ Execution Readiness Gate (Hard Stop)
|
||||
|
||||
### Standard Split
|
||||
- 50/50 for A/B test
|
||||
- Equal split for multiple variants
|
||||
You may proceed to implementation **only if all are true**:
|
||||
|
||||
### Conservative Rollout
|
||||
- 90/10 or 80/20 initially
|
||||
- Limits risk of bad variant
|
||||
- Longer to reach significance
|
||||
- Hypothesis is locked
|
||||
- Primary metric is frozen
|
||||
- Sample size is calculated
|
||||
- Test duration is defined
|
||||
- Guardrails are set
|
||||
- Tracking is verified
|
||||
|
||||
### Ramping
|
||||
- Start small, increase over time
|
||||
- Good for technical risk mitigation
|
||||
- Most tools support this
|
||||
|
||||
### Considerations
|
||||
- Consistency: Users see same variant on return
|
||||
- Segment sizes: Ensure segments are large enough
|
||||
- Time of day/week: Balanced exposure
|
||||
|
||||
---
|
||||
|
||||
## Implementation Approaches
|
||||
|
||||
### Client-Side Testing
|
||||
|
||||
**Tools**: PostHog, Optimizely, VWO, custom
|
||||
|
||||
**How it works**:
|
||||
- JavaScript modifies page after load
|
||||
- Quick to implement
|
||||
- Can cause flicker
|
||||
|
||||
**Best for**:
|
||||
- Marketing pages
|
||||
- Copy/visual changes
|
||||
- Quick iteration
|
||||
|
||||
### Server-Side Testing
|
||||
|
||||
**Tools**: PostHog, LaunchDarkly, Split, custom
|
||||
|
||||
**How it works**:
|
||||
- Variant determined before page renders
|
||||
- No flicker
|
||||
- Requires development work
|
||||
|
||||
**Best for**:
|
||||
- Product features
|
||||
- Complex changes
|
||||
- Performance-sensitive pages
|
||||
|
||||
### Feature Flags
|
||||
|
||||
- Binary on/off (not true A/B)
|
||||
- Good for rollouts
|
||||
- Can convert to A/B with percentage split
|
||||
If any item is missing, stop and resolve it.
|
||||
|
||||
---
|
||||
|
||||
## Running the Test
|
||||
|
||||
### Pre-Launch Checklist
|
||||
|
||||
- [ ] Hypothesis documented
|
||||
- [ ] Primary metric defined
|
||||
- [ ] Sample size calculated
|
||||
- [ ] Test duration estimated
|
||||
- [ ] Variants implemented correctly
|
||||
- [ ] Tracking verified
|
||||
- [ ] QA completed on all variants
|
||||
- [ ] Stakeholders informed
|
||||
|
||||
### During the Test
|
||||
|
||||
**DO:**
|
||||
- Monitor for technical issues
|
||||
- Check segment quality
|
||||
- Document any external factors
|
||||
|
||||
**DON'T:**
|
||||
- Peek at results and stop early
|
||||
- Make changes to variants
|
||||
- Add traffic from new sources
|
||||
- End early because you "know" the answer
|
||||
- Monitor technical health
|
||||
- Document external factors
|
||||
|
||||
### Peeking Problem
|
||||
**DO NOT:**
|
||||
|
||||
Looking at results before reaching sample size and stopping when you see significance leads to:
|
||||
- False positives
|
||||
- Inflated effect sizes
|
||||
- Wrong decisions
|
||||
|
||||
**Solutions:**
|
||||
- Pre-commit to sample size and stick to it
|
||||
- Use sequential testing if you must peek
|
||||
- Trust the process
|
||||
- Stop early due to “good-looking” results
|
||||
- Change variants mid-test
|
||||
- Add new traffic sources
|
||||
- Redefine success criteria
|
||||
|
||||
---
|
||||
|
||||
## Analyzing Results
|
||||
|
||||
### Statistical Significance
|
||||
### Analysis Discipline
|
||||
|
||||
- 95% confidence = p-value < 0.05
|
||||
- Means: <5% chance result is random
|
||||
- Not a guarantee—just a threshold
|
||||
When interpreting results:
|
||||
|
||||
### Practical Significance
|
||||
- Do NOT generalize beyond the tested population
|
||||
- Do NOT claim causality beyond the tested change
|
||||
- Do NOT override guardrail failures
|
||||
- Separate statistical significance from business judgment
|
||||
|
||||
Statistical ≠ Practical
|
||||
### Interpretation Outcomes
|
||||
|
||||
- Is the effect size meaningful for business?
|
||||
- Is it worth the implementation cost?
|
||||
- Is it sustainable over time?
|
||||
|
||||
### What to Look At
|
||||
|
||||
1. **Did you reach sample size?**
|
||||
- If not, result is preliminary
|
||||
|
||||
2. **Is it statistically significant?**
|
||||
- Check confidence intervals
|
||||
- Check p-value
|
||||
|
||||
3. **Is the effect size meaningful?**
|
||||
- Compare to your MDE
|
||||
- Project business impact
|
||||
|
||||
4. **Are secondary metrics consistent?**
|
||||
- Do they support the primary?
|
||||
- Any unexpected effects?
|
||||
|
||||
5. **Any guardrail concerns?**
|
||||
- Did anything get worse?
|
||||
- Long-term risks?
|
||||
|
||||
6. **Segment differences?**
|
||||
- Mobile vs. desktop?
|
||||
- New vs. returning?
|
||||
- Traffic source?
|
||||
|
||||
### Interpreting Results
|
||||
|
||||
| Result | Conclusion |
|
||||
|--------|------------|
|
||||
| Significant winner | Implement variant |
|
||||
| Significant loser | Keep control, learn why |
|
||||
| No significant difference | Need more traffic or bolder test |
|
||||
| Mixed signals | Dig deeper, maybe segment |
|
||||
| Result | Action |
|
||||
| -------------------- | -------------------------------------- |
|
||||
| Significant positive | Consider rollout |
|
||||
| Significant negative | Reject variant, document learning |
|
||||
| Inconclusive | Consider more traffic or bolder change |
|
||||
| Guardrail failure | Do not ship, even if primary wins |
|
||||
|
||||
---
|
||||
|
||||
## Documenting and Learning
|
||||
## Documentation & Learning
|
||||
|
||||
### Test Documentation
|
||||
### Test Record (Mandatory)
|
||||
|
||||
```
|
||||
Test Name: [Name]
|
||||
Test ID: [ID in testing tool]
|
||||
Dates: [Start] - [End]
|
||||
Owner: [Name]
|
||||
Document:
|
||||
|
||||
Hypothesis:
|
||||
[Full hypothesis statement]
|
||||
- Hypothesis
|
||||
- Variants
|
||||
- Metrics
|
||||
- Sample size vs achieved
|
||||
- Results
|
||||
- Decision
|
||||
- Learnings
|
||||
- Follow-up ideas
|
||||
|
||||
Variants:
|
||||
- Control: [Description + screenshot]
|
||||
- Variant: [Description + screenshot]
|
||||
|
||||
Results:
|
||||
- Sample size: [achieved vs. target]
|
||||
- Primary metric: [control] vs. [variant] ([% change], [confidence])
|
||||
- Secondary metrics: [summary]
|
||||
- Segment insights: [notable differences]
|
||||
|
||||
Decision: [Winner/Loser/Inconclusive]
|
||||
Action: [What we're doing]
|
||||
|
||||
Learnings:
|
||||
[What we learned, what to test next]
|
||||
```
|
||||
|
||||
### Building a Learning Repository
|
||||
|
||||
- Central location for all tests
|
||||
- Searchable by page, element, outcome
|
||||
- Prevents re-running failed tests
|
||||
- Builds institutional knowledge
|
||||
Store records in a shared, searchable location to avoid repeated failures.
|
||||
|
||||
---
|
||||
|
||||
## Output Format
|
||||
## Refusal Conditions (Safety)
|
||||
|
||||
### Test Plan Document
|
||||
Refuse to proceed if:
|
||||
|
||||
```
|
||||
# A/B Test: [Name]
|
||||
- Baseline rate is unknown and cannot be estimated
|
||||
- Traffic is insufficient to detect the MDE
|
||||
- Primary metric is undefined
|
||||
- Multiple variables are changed without proper design
|
||||
- Hypothesis cannot be clearly stated
|
||||
|
||||
## Hypothesis
|
||||
[Full hypothesis using framework]
|
||||
|
||||
## Test Design
|
||||
- Type: A/B / A/B/n / MVT
|
||||
- Duration: X weeks
|
||||
- Sample size: X per variant
|
||||
- Traffic allocation: 50/50
|
||||
|
||||
## Variants
|
||||
[Control and variant descriptions with visuals]
|
||||
|
||||
## Metrics
|
||||
- Primary: [metric and definition]
|
||||
- Secondary: [list]
|
||||
- Guardrails: [list]
|
||||
|
||||
## Implementation
|
||||
- Method: Client-side / Server-side
|
||||
- Tool: [Tool name]
|
||||
- Dev requirements: [If any]
|
||||
|
||||
## Analysis Plan
|
||||
- Success criteria: [What constitutes a win]
|
||||
- Segment analysis: [Planned segments]
|
||||
```
|
||||
|
||||
### Results Summary
|
||||
When test is complete
|
||||
|
||||
### Recommendations
|
||||
Next steps based on results
|
||||
Explain why and recommend next steps.
|
||||
|
||||
---
|
||||
|
||||
## Common Mistakes
|
||||
## Key Principles (Non-Negotiable)
|
||||
|
||||
### Test Design
|
||||
- Testing too small a change (undetectable)
|
||||
- Testing too many things (can't isolate)
|
||||
- No clear hypothesis
|
||||
- Wrong audience
|
||||
|
||||
### Execution
|
||||
- Stopping early
|
||||
- Changing things mid-test
|
||||
- Not checking implementation
|
||||
- Uneven traffic allocation
|
||||
|
||||
### Analysis
|
||||
- Ignoring confidence intervals
|
||||
- Cherry-picking segments
|
||||
- Over-interpreting inconclusive results
|
||||
- Not considering practical significance
|
||||
- One hypothesis per test
|
||||
- One primary metric
|
||||
- Commit before launch
|
||||
- No peeking
|
||||
- Learning over winning
|
||||
- Statistical rigor first
|
||||
|
||||
---
|
||||
|
||||
## Questions to Ask
|
||||
## Final Reminder
|
||||
|
||||
If you need more context:
|
||||
1. What's your current conversion rate?
|
||||
2. How much traffic does this page get?
|
||||
3. What change are you considering and why?
|
||||
4. What's the smallest improvement worth detecting?
|
||||
5. What tools do you have for testing?
|
||||
6. Have you tested this area before?
|
||||
A/B testing is not about proving ideas right.
|
||||
It is about **learning the truth with confidence**.
|
||||
|
||||
---
|
||||
|
||||
## Related Skills
|
||||
|
||||
- **page-cro**: For generating test ideas based on CRO principles
|
||||
- **analytics-tracking**: For setting up test measurement
|
||||
- **copywriting**: For creating variant copy
|
||||
If you feel tempted to rush, simplify, or “just try it” —
|
||||
that is the signal to **slow down and re-check the design**.
|
||||
|
||||
@@ -1,54 +1,230 @@
|
||||
---
|
||||
name: brainstorming
|
||||
description: "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
|
||||
description: >
|
||||
Use this skill before any creative or constructive work
|
||||
(features, components, architecture, behavior changes, or functionality).
|
||||
This skill transforms vague ideas into validated designs through
|
||||
disciplined, incremental reasoning and collaboration.
|
||||
---
|
||||
|
||||
# Brainstorming Ideas Into Designs
|
||||
|
||||
## Overview
|
||||
## Purpose
|
||||
|
||||
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
|
||||
Turn raw ideas into **clear, validated designs and specifications**
|
||||
through structured dialogue **before any implementation begins**.
|
||||
|
||||
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far.
|
||||
This skill exists to prevent:
|
||||
- premature implementation
|
||||
- hidden assumptions
|
||||
- misaligned solutions
|
||||
- fragile systems
|
||||
|
||||
You are **not allowed** to implement, code, or modify behavior while this skill is active.
|
||||
|
||||
---
|
||||
|
||||
## Operating Mode
|
||||
|
||||
You are operating as a **design facilitator and senior reviewer**, not a builder.
|
||||
|
||||
- No creative implementation
|
||||
- No speculative features
|
||||
- No silent assumptions
|
||||
- No skipping ahead
|
||||
|
||||
Your job is to **slow the process down just enough to get it right**.
|
||||
|
||||
---
|
||||
|
||||
## The Process
|
||||
|
||||
**Understanding the idea:**
|
||||
- Check out the current project state first (files, docs, recent commits)
|
||||
- Ask questions one at a time to refine the idea
|
||||
- Prefer multiple choice questions when possible, but open-ended is fine too
|
||||
- Only one question per message - if a topic needs more exploration, break it into multiple questions
|
||||
- Focus on understanding: purpose, constraints, success criteria
|
||||
### 1️⃣ Understand the Current Context (Mandatory First Step)
|
||||
|
||||
**Exploring approaches:**
|
||||
- Propose 2-3 different approaches with trade-offs
|
||||
- Present options conversationally with your recommendation and reasoning
|
||||
- Lead with your recommended option and explain why
|
||||
Before asking any questions:
|
||||
|
||||
**Presenting the design:**
|
||||
- Once you believe you understand what you're building, present the design
|
||||
- Break it into sections of 200-300 words
|
||||
- Ask after each section whether it looks right so far
|
||||
- Cover: architecture, components, data flow, error handling, testing
|
||||
- Be ready to go back and clarify if something doesn't make sense
|
||||
- Review the current project state (if available):
|
||||
- files
|
||||
- documentation
|
||||
- plans
|
||||
- prior decisions
|
||||
- Identify what already exists vs. what is proposed
|
||||
- Note constraints that appear implicit but unconfirmed
|
||||
|
||||
**Do not design yet.**
|
||||
|
||||
---
|
||||
|
||||
### 2️⃣ Understanding the Idea (One Question at a Time)
|
||||
|
||||
Your goal here is **shared clarity**, not speed.
|
||||
|
||||
**Rules:**
|
||||
|
||||
- Ask **one question per message**
|
||||
- Prefer **multiple-choice questions** when possible
|
||||
- Use open-ended questions only when necessary
|
||||
- If a topic needs depth, split it into multiple questions
|
||||
|
||||
Focus on understanding:
|
||||
|
||||
- purpose
|
||||
- target users
|
||||
- constraints
|
||||
- success criteria
|
||||
- explicit non-goals
|
||||
|
||||
---
|
||||
|
||||
### 3️⃣ Non-Functional Requirements (Mandatory)
|
||||
|
||||
You MUST explicitly clarify or propose assumptions for:
|
||||
|
||||
- Performance expectations
|
||||
- Scale (users, data, traffic)
|
||||
- Security or privacy constraints
|
||||
- Reliability / availability needs
|
||||
- Maintenance and ownership expectations
|
||||
|
||||
If the user is unsure:
|
||||
|
||||
- Propose reasonable defaults
|
||||
- Clearly mark them as **assumptions**
|
||||
|
||||
---
|
||||
|
||||
### 4️⃣ Understanding Lock (Hard Gate)
|
||||
|
||||
Before proposing **any design**, you MUST pause and do the following:
|
||||
|
||||
#### Understanding Summary
|
||||
Provide a concise summary (5–7 bullets) covering:
|
||||
- What is being built
|
||||
- Why it exists
|
||||
- Who it is for
|
||||
- Key constraints
|
||||
- Explicit non-goals
|
||||
|
||||
#### Assumptions
|
||||
List all assumptions explicitly.
|
||||
|
||||
#### Open Questions
|
||||
List unresolved questions, if any.
|
||||
|
||||
Then ask:
|
||||
|
||||
> “Does this accurately reflect your intent?
|
||||
> Please confirm or correct anything before we move to design.”
|
||||
|
||||
**Do NOT proceed until explicit confirmation is given.**
|
||||
|
||||
---
|
||||
|
||||
### 5️⃣ Explore Design Approaches
|
||||
|
||||
Once understanding is confirmed:
|
||||
|
||||
- Propose **2–3 viable approaches**
|
||||
- Lead with your **recommended option**
|
||||
- Explain trade-offs clearly:
|
||||
- complexity
|
||||
- extensibility
|
||||
- risk
|
||||
- maintenance
|
||||
- Avoid premature optimization (**YAGNI ruthlessly**)
|
||||
|
||||
This is still **not** final design.
|
||||
|
||||
---
|
||||
|
||||
### 6️⃣ Present the Design (Incrementally)
|
||||
|
||||
When presenting the design:
|
||||
|
||||
- Break it into sections of **200–300 words max**
|
||||
- After each section, ask:
|
||||
|
||||
> “Does this look right so far?”
|
||||
|
||||
Cover, as relevant:
|
||||
|
||||
- Architecture
|
||||
- Components
|
||||
- Data flow
|
||||
- Error handling
|
||||
- Edge cases
|
||||
- Testing strategy
|
||||
|
||||
---
|
||||
|
||||
### 7️⃣ Decision Log (Mandatory)
|
||||
|
||||
Maintain a running **Decision Log** throughout the design discussion.
|
||||
|
||||
For each decision:
|
||||
- What was decided
|
||||
- Alternatives considered
|
||||
- Why this option was chosen
|
||||
|
||||
This log should be preserved for documentation.
|
||||
|
||||
---
|
||||
|
||||
## After the Design
|
||||
|
||||
**Documentation:**
|
||||
- Write the validated design to `docs/plans/YYYY-MM-DD-<topic>-design.md`
|
||||
- Use elements-of-style:writing-clearly-and-concisely skill if available
|
||||
- Commit the design document to git
|
||||
### 📄 Documentation
|
||||
|
||||
**Implementation (if continuing):**
|
||||
- Ask: "Ready to set up for implementation?"
|
||||
- Use superpowers:using-git-worktrees to create isolated workspace
|
||||
- Use superpowers:writing-plans to create detailed implementation plan
|
||||
Once the design is validated:
|
||||
|
||||
## Key Principles
|
||||
- Write the final design to a durable, shared format (e.g. Markdown)
|
||||
- Include:
|
||||
- Understanding summary
|
||||
- Assumptions
|
||||
- Decision log
|
||||
- Final design
|
||||
|
||||
- **One question at a time** - Don't overwhelm with multiple questions
|
||||
- **Multiple choice preferred** - Easier to answer than open-ended when possible
|
||||
- **YAGNI ruthlessly** - Remove unnecessary features from all designs
|
||||
- **Explore alternatives** - Always propose 2-3 approaches before settling
|
||||
- **Incremental validation** - Present design in sections, validate each
|
||||
- **Be flexible** - Go back and clarify when something doesn't make sense
|
||||
Persist the document according to the project’s standard workflow.
|
||||
|
||||
---
|
||||
|
||||
### 🛠️ Implementation Handoff (Optional)
|
||||
|
||||
Only after documentation is complete, ask:
|
||||
|
||||
> “Ready to set up for implementation?”
|
||||
|
||||
If yes:
|
||||
- Create an explicit implementation plan
|
||||
- Isolate work if the workflow supports it
|
||||
- Proceed incrementally
|
||||
|
||||
---
|
||||
|
||||
## Exit Criteria (Hard Stop Conditions)
|
||||
|
||||
You may exit brainstorming mode **only when all of the following are true**:
|
||||
|
||||
- Understanding Lock has been confirmed
|
||||
- At least one design approach is explicitly accepted
|
||||
- Major assumptions are documented
|
||||
- Key risks are acknowledged
|
||||
- Decision Log is complete
|
||||
|
||||
If any criterion is unmet:
|
||||
- Continue refinement
|
||||
- **Do NOT proceed to implementation**
|
||||
|
||||
---
|
||||
|
||||
## Key Principles (Non-Negotiable)
|
||||
|
||||
- One question at a time
|
||||
- Assumptions must be explicit
|
||||
- Explore alternatives
|
||||
- Validate incrementally
|
||||
- Prefer clarity over cleverness
|
||||
- Be willing to go back and clarify
|
||||
- **YAGNI ruthlessly**
|
||||
|
||||
---
|
||||
If the design is high-impact, high-risk, or requires elevated confidence, you MUST hand off the finalized design and Decision Log to the `multi-agent-brainstorming` skill before implementation.
|
||||
|
||||
@@ -1,366 +1,162 @@
|
||||
---
|
||||
name: copywriting
|
||||
description: When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.
|
||||
description: >
|
||||
Use this skill when writing, rewriting, or improving marketing copy
|
||||
for any page (homepage, landing page, pricing, feature, product, or about page).
|
||||
This skill produces clear, compelling, and testable copy while enforcing
|
||||
alignment, honesty, and conversion best practices.
|
||||
---
|
||||
|
||||
# Copywriting
|
||||
|
||||
You are an expert conversion copywriter. Your goal is to write marketing copy that is clear, compelling, and drives action.
|
||||
## Purpose
|
||||
|
||||
## Before Writing
|
||||
Produce **clear, credible, and action-oriented marketing copy** that aligns with
|
||||
user intent and business goals.
|
||||
|
||||
Gather this context (ask if not provided):
|
||||
This skill exists to prevent:
|
||||
- writing before understanding the audience
|
||||
- vague or hype-driven messaging
|
||||
- misaligned CTAs
|
||||
- overclaiming or fabricated proof
|
||||
- untestable copy
|
||||
|
||||
### 1. Page Purpose
|
||||
- What type of page is this? (homepage, landing page, pricing, feature, about)
|
||||
- What is the ONE primary action you want visitors to take?
|
||||
- What's the secondary action (if any)?
|
||||
|
||||
### 2. Audience
|
||||
- Who is the ideal customer for this page?
|
||||
- What problem are they trying to solve?
|
||||
- What have they already tried?
|
||||
- What objections or hesitations do they have?
|
||||
- What language do they use to describe their problem?
|
||||
|
||||
### 3. Product/Offer
|
||||
- What are you selling or offering?
|
||||
- What makes it different from alternatives?
|
||||
- What's the key transformation or outcome?
|
||||
- Any proof points (numbers, testimonials, case studies)?
|
||||
|
||||
### 4. Context
|
||||
- Where is traffic coming from? (ads, organic, email)
|
||||
- What do visitors already know before arriving?
|
||||
- What messaging are they seeing before this page?
|
||||
You may **not** fabricate claims, statistics, testimonials, or guarantees.
|
||||
|
||||
---
|
||||
|
||||
## Copywriting Principles
|
||||
## Operating Mode
|
||||
|
||||
### Clarity Over Cleverness
|
||||
- If you have to choose between clear and creative, choose clear
|
||||
- Every sentence should have one job
|
||||
- Remove words that don't add meaning
|
||||
You are operating as an **expert conversion copywriter**, not a brand poet.
|
||||
|
||||
### Benefits Over Features
|
||||
- Features: What it does
|
||||
- Benefits: What that means for the customer
|
||||
- Always connect features to outcomes
|
||||
- Clarity beats cleverness
|
||||
- Outcomes beat features
|
||||
- Specificity beats buzzwords
|
||||
- Honesty beats hype
|
||||
|
||||
### Specificity Over Vagueness
|
||||
- Vague: "Save time on your workflow"
|
||||
- Specific: "Cut your weekly reporting from 4 hours to 15 minutes"
|
||||
Your job is to **help the right reader take the right action**.
|
||||
|
||||
### Customer Language Over Company Language
|
||||
- Use words your customers use
|
||||
- Avoid jargon unless your audience uses it
|
||||
- Mirror voice-of-customer from reviews, interviews, support tickets
|
||||
---
|
||||
|
||||
### One Idea Per Section
|
||||
- Don't try to say everything everywhere
|
||||
- Each section should advance one argument
|
||||
- Build a logical flow down the page
|
||||
## Phase 1 — Context Gathering (Mandatory)
|
||||
|
||||
Before writing any copy, gather or confirm the following.
|
||||
If information is missing, ask for it **before proceeding**.
|
||||
|
||||
### 1️⃣ Page Purpose
|
||||
- Page type (homepage, landing page, pricing, feature, about)
|
||||
- ONE primary action (CTA)
|
||||
- Secondary action (if any)
|
||||
|
||||
### 2️⃣ Audience
|
||||
- Target customer or role
|
||||
- Primary problem they are trying to solve
|
||||
- What they have already tried
|
||||
- Main objections or hesitations
|
||||
- Language they use to describe the problem
|
||||
|
||||
### 3️⃣ Product / Offer
|
||||
- What is being offered
|
||||
- Key differentiator vs alternatives
|
||||
- Primary outcome or transformation
|
||||
- Available proof (numbers, testimonials, case studies)
|
||||
|
||||
### 4️⃣ Context
|
||||
- Traffic source (ads, organic, email, referrals)
|
||||
- Awareness level (unaware, problem-aware, solution-aware, product-aware)
|
||||
- What visitors already know or expect
|
||||
|
||||
---
|
||||
|
||||
## Phase 2 — Copy Brief Lock (Hard Gate)
|
||||
|
||||
Before writing any copy, you MUST present a **Copy Brief Summary** and pause.
|
||||
|
||||
### Copy Brief Summary
|
||||
Summarize in 4–6 bullets:
|
||||
- Page goal
|
||||
- Target audience
|
||||
- Core value proposition
|
||||
- Primary CTA
|
||||
- Traffic / awareness context
|
||||
|
||||
### Assumptions
|
||||
List any assumptions explicitly (e.g. awareness level, urgency, sophistication).
|
||||
|
||||
Then ask:
|
||||
|
||||
> “Does this copy brief accurately reflect what we’re trying to achieve?
|
||||
> Please confirm or correct anything before I write copy.”
|
||||
|
||||
**Do NOT proceed until confirmation is given.**
|
||||
|
||||
---
|
||||
|
||||
## Phase 3 — Copywriting Principles
|
||||
|
||||
### Core Principles (Non-Negotiable)
|
||||
|
||||
- **Clarity over cleverness**
|
||||
- **Benefits over features**
|
||||
- **Specificity over vagueness**
|
||||
- **Customer language over company language**
|
||||
- **One idea per section**
|
||||
|
||||
Always connect:
|
||||
> Feature → Benefit → Outcome
|
||||
|
||||
---
|
||||
|
||||
## Writing Style Rules
|
||||
|
||||
Follow these core principles. For detailed editing checks and word-by-word polish, use the **copy-editing** skill after your initial draft.
|
||||
### Style Guidelines
|
||||
- Simple over complex
|
||||
- Active over passive
|
||||
- Confident over hedged
|
||||
- Show outcomes instead of adjectives
|
||||
- Avoid buzzwords unless customers use them
|
||||
|
||||
### Core Style Principles
|
||||
|
||||
1. **Simple over complex** — Use everyday words. "Use" instead of "utilize," "help" instead of "facilitate."
|
||||
|
||||
2. **Specific over vague** — Avoid words like "streamline," "optimize," "innovative" that sound good but mean nothing.
|
||||
|
||||
3. **Active over passive** — "We generate reports" not "Reports are generated."
|
||||
|
||||
4. **Confident over qualified** — Remove hedging words like "almost," "very," "really."
|
||||
|
||||
5. **Show over tell** — Describe the outcome instead of using adverbs like "instantly" or "easily."
|
||||
|
||||
6. **Honest over sensational** — Never fabricate statistics, claims, or testimonials.
|
||||
|
||||
### Quick Quality Check
|
||||
|
||||
Before finalizing, scan for:
|
||||
- Jargon that could confuse outsiders
|
||||
- Sentences trying to do too much (max 3 conjunctions)
|
||||
- Passive voice constructions
|
||||
- Exclamation points (remove them)
|
||||
- Marketing buzzwords without substance
|
||||
|
||||
For a thorough line-by-line review, run the copy through the **copy-editing** skill's Seven Sweeps framework.
|
||||
### Claim Discipline
|
||||
- No fabricated data or testimonials
|
||||
- No implied guarantees unless explicitly stated
|
||||
- No exaggerated speed or certainty
|
||||
- If proof is missing, mark placeholders clearly
|
||||
|
||||
---
|
||||
|
||||
## Best Practices
|
||||
## Phase 4 — Page Structure Framework
|
||||
|
||||
### Be Direct
|
||||
Get to the point. Don't bury the value in qualifications.
|
||||
|
||||
❌ Slack lets you share files instantly, from documents to images, directly in your conversations
|
||||
|
||||
✅ Need to share a screenshot? Send as many documents, images, and audio files as your heart desires.
|
||||
|
||||
### Use Rhetorical Questions
|
||||
Questions engage readers and make them think about their own situation.
|
||||
|
||||
✅ Hate returning stuff to Amazon?
|
||||
|
||||
✅ Need to share a screenshot?
|
||||
|
||||
✅ Tired of chasing approvals?
|
||||
|
||||
### Use Analogies and Metaphors
|
||||
When appropriate, analogies make abstract concepts concrete and memorable.
|
||||
|
||||
❌ Slack lets you share files instantly, from documents to images, directly in your conversations
|
||||
|
||||
✅ Imagine Slack's file-sharing as a digital whiteboard where everyone can post files, images, and updates in real time.
|
||||
|
||||
### Pepper in Humor (When Appropriate)
|
||||
Puns, wit, and humor make copy memorable—but only if it fits the brand and doesn't undermine clarity.
|
||||
|
||||
---
|
||||
|
||||
## Page Structure Framework
|
||||
|
||||
### Above the Fold (First Screen)
|
||||
### Above the Fold
|
||||
|
||||
**Headline**
|
||||
- Your single most important message
|
||||
- Should communicate core value proposition
|
||||
- Specific > generic
|
||||
|
||||
**Headline Formulas:**
|
||||
|
||||
**{Achieve desirable outcome} without {pain point}**
|
||||
*Example: Understand how users are really experiencing your site without drowning in numbers*
|
||||
|
||||
**The {opposite of usual process} way to {achieve desirable outcome}**
|
||||
*Example: The easiest way to turn your passion into income*
|
||||
|
||||
**Never {unpleasant event} again**
|
||||
*Example: Never miss a sales opportunity again*
|
||||
|
||||
**{Key feature/product type} for {target audience}**
|
||||
*Example: Advanced analytics for Shopify e-commerce*
|
||||
|
||||
**{Key feature/product type} for {target audience} to {what it's used for}**
|
||||
*Example: An online whiteboard for teams to ideate and brainstorm together*
|
||||
|
||||
**You don't have to {skills or resources} to {achieve desirable outcome}**
|
||||
*Example: With Ahrefs, you don't have to be an SEO pro to rank higher and get more traffic*
|
||||
|
||||
**{Achieve desirable outcome} by {how product makes it possible}**
|
||||
*Example: Generate more leads by seeing which companies visit your site*
|
||||
|
||||
**{Key benefit of your product}**
|
||||
*Example: Sound clear in online meetings*
|
||||
|
||||
**{Question highlighting the main pain point}**
|
||||
*Example: Hate returning stuff to Amazon?*
|
||||
|
||||
**Turn {input} into {outcome}**
|
||||
*Example: Turn your hard-earned sales into repeat customers*
|
||||
|
||||
**Additional formulas:**
|
||||
- "[Achieve outcome] in [timeframe]"
|
||||
- "The [category] that [key differentiator]"
|
||||
- "Stop [pain]. Start [pleasure]."
|
||||
- "[Number] [people] use [product] to [outcome]"
|
||||
- Single most important message
|
||||
- Specific value proposition
|
||||
- Outcome-focused
|
||||
|
||||
**Subheadline**
|
||||
- Expands on the headline
|
||||
- Adds specificity or addresses secondary concern
|
||||
- 1-2 sentences max
|
||||
- Adds clarity or context
|
||||
- 1–2 sentences max
|
||||
|
||||
**Primary CTA**
|
||||
- Action-oriented button text
|
||||
- Communicate what they get, not what they do
|
||||
- "Start Free Trial" > "Sign Up"
|
||||
- "Get Your Report" > "Submit"
|
||||
|
||||
**Supporting Visual**
|
||||
- Product screenshot, demo, or hero image
|
||||
- Should reinforce the message, not distract
|
||||
|
||||
### Social Proof Section
|
||||
|
||||
Options (use 1-2):
|
||||
- Customer logos (recognizable > many)
|
||||
- Key metric ("10,000+ teams")
|
||||
- Short testimonial with attribution
|
||||
- Star rating with review count
|
||||
|
||||
### Problem/Pain Section
|
||||
|
||||
- Articulate the problem better than they can
|
||||
- Show you understand their situation
|
||||
- Create recognition ("that's exactly my problem")
|
||||
|
||||
Structure:
|
||||
- "You know the feeling..." or "If you're like most [role]..."
|
||||
- Describe the specific frustrations
|
||||
- Hint at the cost of not solving it
|
||||
|
||||
### Solution/Benefits Section
|
||||
|
||||
- Bridge from problem to your solution
|
||||
- Focus on 3-5 key benefits (not 10)
|
||||
- Each benefit: headline + short explanation + proof point if available
|
||||
|
||||
Format options:
|
||||
- Benefit blocks with icons
|
||||
- Before/after comparison
|
||||
- Feature → Benefit → Proof structure
|
||||
|
||||
### How It Works Section
|
||||
|
||||
- Reduce perceived complexity
|
||||
- 3-4 step process
|
||||
- Each step: simple action + outcome
|
||||
|
||||
Example:
|
||||
1. "Connect your tools (2 minutes)"
|
||||
2. "Set your preferences"
|
||||
3. "Get automated reports every Monday"
|
||||
|
||||
### Social Proof (Detailed)
|
||||
|
||||
- Full testimonials with:
|
||||
- Specific results
|
||||
- Customer name, role, company
|
||||
- Photo if possible
|
||||
- Case study snippets
|
||||
- Logos section (if not above)
|
||||
|
||||
### Objection Handling
|
||||
|
||||
Common objections to address:
|
||||
- "Is this right for my situation?"
|
||||
- "What if it doesn't work?"
|
||||
- "Is it hard to set up?"
|
||||
- "How is this different from X?"
|
||||
|
||||
Formats:
|
||||
- FAQ section
|
||||
- Comparison table
|
||||
- Guarantee/promise section
|
||||
- "Built for [specific audience]" section
|
||||
|
||||
### Final CTA Section
|
||||
|
||||
- Recap the value proposition
|
||||
- Repeat the primary CTA
|
||||
- Add urgency if genuine (deadline, limited availability)
|
||||
- Risk reversal (guarantee, free trial, no credit card)
|
||||
- Action-oriented
|
||||
- Describes what the user gets
|
||||
|
||||
---
|
||||
|
||||
## Landing Page Section Variety
|
||||
### Core Sections (Use as Appropriate)
|
||||
|
||||
A great landing page isn't just a list of features. Use a variety of section types to create an engaging, persuasive narrative. Mix and match from these:
|
||||
- Social proof (logos, stats, testimonials)
|
||||
- Problem / pain articulation
|
||||
- Solution & key benefits (3–5 max)
|
||||
- How it works (3–4 steps)
|
||||
- Objection handling (FAQ, comparisons, guarantees)
|
||||
- Final CTA with recap and risk reduction
|
||||
|
||||
### Section Types to Include
|
||||
|
||||
**How It Works (Numbered Steps)**
|
||||
Walk users through the process in 3-4 clear steps. Reduces perceived complexity and shows the path to value.
|
||||
|
||||
**Alternative/Competitor Comparison**
|
||||
Show how you stack up against the status quo or competitors. Tables, side-by-side comparisons, or "Unlike X, we..." sections.
|
||||
|
||||
**Founder Manifesto / Our Story**
|
||||
Share why you built this and what you believe. Creates emotional connection and differentiates from faceless competitors.
|
||||
|
||||
**Testimonials**
|
||||
Customer quotes with names, photos, and specific results. Multiple formats: quote cards, video testimonials, tweet embeds.
|
||||
|
||||
**Case Studies**
|
||||
Deeper stories of customer success. Problem → Solution → Results format with specific metrics.
|
||||
|
||||
**Use Cases**
|
||||
Show different ways the product is used. Helps visitors self-identify: "This is for people like me."
|
||||
|
||||
**Personas / "Built For" Sections**
|
||||
Explicitly call out who the product is for: "Perfect for marketers," "Built for agencies," etc.
|
||||
|
||||
**Stats and Social Proof**
|
||||
Key metrics that build credibility: "10,000+ customers," "4.9/5 rating," "$2M saved for customers."
|
||||
|
||||
**Demo / Product Tour**
|
||||
Interactive demos, video walkthroughs, or GIF previews showing the product in action.
|
||||
|
||||
**FAQ Section**
|
||||
Address common objections and questions. Good for SEO and reducing support burden.
|
||||
|
||||
**Integrations / Partners**
|
||||
Show what tools you connect with. Logos build credibility and answer "Will this work with my stack?"
|
||||
|
||||
**Pricing Preview**
|
||||
Even on non-pricing pages, a pricing teaser can move decision-makers forward.
|
||||
|
||||
**Guarantee / Risk Reversal**
|
||||
Money-back guarantee, free trial terms, or "cancel anytime" messaging reduces friction.
|
||||
|
||||
### Recommended Section Mix
|
||||
|
||||
For a landing page, aim for variety. Don't just stack features:
|
||||
|
||||
**Typical Feature-Heavy Page (Weak):**
|
||||
1. Hero
|
||||
2. Feature 1
|
||||
3. Feature 2
|
||||
4. Feature 3
|
||||
5. Feature 4
|
||||
6. CTA
|
||||
|
||||
**Varied, Engaging Page (Strong):**
|
||||
1. Hero with clear value prop
|
||||
2. Social proof bar (logos or stats)
|
||||
3. Problem/pain section
|
||||
4. How it works (3 steps)
|
||||
5. Key benefits (2-3, not 10)
|
||||
6. Testimonial
|
||||
7. Use cases or personas
|
||||
8. Comparison to alternatives
|
||||
9. Case study snippet
|
||||
10. FAQ
|
||||
11. Final CTA with guarantee
|
||||
Avoid stacking features without narrative flow.
|
||||
|
||||
---
|
||||
|
||||
## CTA Copy Guidelines
|
||||
|
||||
**Weak CTAs (avoid):**
|
||||
- Submit
|
||||
- Sign Up
|
||||
- Learn More
|
||||
- Click Here
|
||||
- Get Started
|
||||
|
||||
**Strong CTAs (use):**
|
||||
- Start Free Trial
|
||||
- Get [Specific Thing]
|
||||
- See [Product] in Action
|
||||
- Create Your First [Thing]
|
||||
- Book My Demo
|
||||
- Download the Guide
|
||||
- Try It Free
|
||||
|
||||
**CTA formula:**
|
||||
[Action Verb] + [What They Get] + [Qualifier if needed]
|
||||
|
||||
Examples:
|
||||
- "Start My Free Trial"
|
||||
- "Get the Complete Checklist"
|
||||
- "See Pricing for My Team"
|
||||
|
||||
---
|
||||
|
||||
## Output Format
|
||||
## Phase 5 — Writing the Copy
|
||||
|
||||
When writing copy, provide:
|
||||
|
||||
@@ -368,88 +164,62 @@ When writing copy, provide:
|
||||
Organized by section with clear labels:
|
||||
- Headline
|
||||
- Subheadline
|
||||
- CTA
|
||||
- CTAs
|
||||
- Section headers
|
||||
- Body copy
|
||||
- Secondary CTAs
|
||||
|
||||
### Annotations
|
||||
For key elements, explain:
|
||||
- Why you made this choice
|
||||
- What principle it applies
|
||||
- Alternatives considered
|
||||
|
||||
### Alternatives
|
||||
For headlines and CTAs, provide 2-3 options:
|
||||
- Option A: [copy] — [rationale]
|
||||
- Option B: [copy] — [rationale]
|
||||
- Option C: [copy] — [rationale]
|
||||
Provide 2–3 options for:
|
||||
- Headlines
|
||||
- Primary CTAs
|
||||
|
||||
### Meta Content (if relevant)
|
||||
- Page title (for SEO)
|
||||
- Meta description
|
||||
Each option must include a brief rationale.
|
||||
|
||||
### Annotations
|
||||
For key sections, explain:
|
||||
- Why this copy was chosen
|
||||
- Which principle it applies
|
||||
- What alternatives were considered
|
||||
|
||||
---
|
||||
|
||||
## Page-Specific Guidance
|
||||
## Testability Guidance
|
||||
|
||||
### Homepage Copy
|
||||
- Serve multiple audiences without being generic
|
||||
- Lead with broadest value proposition
|
||||
- Provide clear paths for different visitor intents
|
||||
- Balance "ready to buy" and "still researching"
|
||||
Write copy with testing in mind:
|
||||
- Clear, isolated value propositions
|
||||
- Headlines and CTAs that can be A/B tested
|
||||
- Avoid combining multiple messages into one element
|
||||
|
||||
### Landing Page Copy
|
||||
- Single message, single CTA
|
||||
- Match headline to ad/traffic source
|
||||
- Complete argument on one page
|
||||
- Remove distractions (often no nav)
|
||||
|
||||
### Pricing Page Copy
|
||||
- Help visitors choose the right plan
|
||||
- Clarify what's included at each level
|
||||
- Address "which is right for me?" anxiety
|
||||
- Make recommended plan obvious
|
||||
|
||||
### Feature Page Copy
|
||||
- Connect feature to benefit to outcome
|
||||
- Show use cases and examples
|
||||
- Differentiate from competitors' versions
|
||||
- Clear path to try or buy
|
||||
|
||||
### About Page Copy
|
||||
- Tell the story of why you exist
|
||||
- Connect company mission to customer benefit
|
||||
- Build trust through transparency
|
||||
- Still include a CTA (it's still a marketing page)
|
||||
If the copy is intended for experimentation, recommend next-step testing.
|
||||
|
||||
---
|
||||
|
||||
## Voice and Tone Considerations
|
||||
## Completion Criteria (Hard Stop)
|
||||
|
||||
Before writing, establish:
|
||||
|
||||
**Formality level:**
|
||||
- Casual/conversational
|
||||
- Professional but friendly
|
||||
- Formal/enterprise
|
||||
|
||||
**Brand personality:**
|
||||
- Playful or serious?
|
||||
- Bold or understated?
|
||||
- Technical or accessible?
|
||||
|
||||
Maintain consistency throughout, but adjust intensity:
|
||||
- Headlines can be bolder
|
||||
- Body copy should be clearer
|
||||
- CTAs should be action-oriented
|
||||
This skill is complete ONLY when:
|
||||
- Copy brief has been confirmed
|
||||
- Page copy is delivered in structured form
|
||||
- Headline and CTA alternatives are provided
|
||||
- Assumptions are documented
|
||||
- Copy is ready for review, editing, or testing
|
||||
|
||||
---
|
||||
|
||||
## Related Skills
|
||||
## Key Principles (Summary)
|
||||
|
||||
- **copy-editing**: For polishing and improving existing copy (use after writing your first draft)
|
||||
- **page-cro**: If the page structure/strategy needs work, not just copy
|
||||
- **email-sequence**: For email copywriting
|
||||
- **popup-cro**: For popup and modal copy
|
||||
- **ab-test-setup**: To test copy variations properly
|
||||
- Understand before writing
|
||||
- Make assumptions explicit
|
||||
- One page, one goal
|
||||
- One section, one idea
|
||||
- Benefits before features
|
||||
- Honest claims only
|
||||
|
||||
---
|
||||
|
||||
## Final Reminder
|
||||
|
||||
Good copy does not persuade everyone.
|
||||
It persuades **the right person** to take **the right action**.
|
||||
|
||||
If the copy feels clever but unclear,
|
||||
rewrite it until it feels obvious.
|
||||
|
||||
167
skills/design-orchestration/SKILL.md
Normal file
167
skills/design-orchestration/SKILL.md
Normal file
@@ -0,0 +1,167 @@
|
||||
---
|
||||
name: design-orchestration
|
||||
description: >
|
||||
Orchestrates design workflows by routing work through
|
||||
brainstorming, multi-agent review, and execution readiness
|
||||
in the correct order. Prevents premature implementation,
|
||||
skipped validation, and unreviewed high-risk designs.
|
||||
---
|
||||
|
||||
# Design Orchestration (Meta-Skill)
|
||||
|
||||
## Purpose
|
||||
|
||||
Ensure that **ideas become designs**, **designs are reviewed**, and
|
||||
**only validated designs reach implementation**.
|
||||
|
||||
This skill does not generate designs.
|
||||
It **controls the flow between other skills**.
|
||||
|
||||
---
|
||||
|
||||
## Operating Model
|
||||
|
||||
This is a **routing and enforcement skill**, not a creative one.
|
||||
|
||||
It decides:
|
||||
- which skill must run next
|
||||
- whether escalation is required
|
||||
- whether execution is permitted
|
||||
|
||||
---
|
||||
|
||||
## Controlled Skills
|
||||
|
||||
This meta-skill coordinates the following:
|
||||
|
||||
- `brainstorming` — design generation
|
||||
- `multi-agent-brainstorming` — design validation
|
||||
- downstream implementation or planning skills
|
||||
|
||||
---
|
||||
|
||||
## Entry Conditions
|
||||
|
||||
Invoke this skill when:
|
||||
- a user proposes a new feature, system, or change
|
||||
- a design decision carries meaningful risk
|
||||
- correctness matters more than speed
|
||||
|
||||
---
|
||||
|
||||
## Routing Logic
|
||||
|
||||
### Step 1 — Brainstorming (Mandatory)
|
||||
|
||||
If no validated design exists:
|
||||
|
||||
- Invoke `brainstorming`
|
||||
- Require:
|
||||
- Understanding Lock
|
||||
- Initial Design
|
||||
- Decision Log started
|
||||
|
||||
You may NOT proceed without these artifacts.
|
||||
|
||||
---
|
||||
|
||||
### Step 2 — Risk Assessment
|
||||
|
||||
After brainstorming completes, classify the design as:
|
||||
|
||||
- **Low risk**
|
||||
- **Moderate risk**
|
||||
- **High risk**
|
||||
|
||||
Use factors such as:
|
||||
- user impact
|
||||
- irreversibility
|
||||
- operational cost
|
||||
- complexity
|
||||
- uncertainty
|
||||
- novelty
|
||||
|
||||
---
|
||||
|
||||
### Step 3 — Conditional Escalation
|
||||
|
||||
- **Low risk**
|
||||
→ Proceed to implementation planning
|
||||
|
||||
- **Moderate risk**
|
||||
→ Recommend `multi-agent-brainstorming`
|
||||
|
||||
- **High risk**
|
||||
→ REQUIRE `multi-agent-brainstorming`
|
||||
|
||||
Skipping escalation when required is prohibited.
|
||||
|
||||
---
|
||||
|
||||
### Step 4 — Multi-Agent Review (If Invoked)
|
||||
|
||||
If `multi-agent-brainstorming` is run:
|
||||
|
||||
Require:
|
||||
- completed Understanding Lock
|
||||
- current Design
|
||||
- Decision Log
|
||||
|
||||
Do NOT allow:
|
||||
- new ideation
|
||||
- scope expansion
|
||||
- reopening problem definition
|
||||
|
||||
Only critique, revision, and decision resolution are allowed.
|
||||
|
||||
---
|
||||
|
||||
### Step 5 — Execution Readiness Check
|
||||
|
||||
Before allowing implementation:
|
||||
|
||||
Confirm:
|
||||
- design is approved (single-agent or multi-agent)
|
||||
- Decision Log is complete
|
||||
- major assumptions are documented
|
||||
- known risks are acknowledged
|
||||
|
||||
If any condition fails:
|
||||
- block execution
|
||||
- return to the appropriate skill
|
||||
|
||||
---
|
||||
|
||||
## Enforcement Rules
|
||||
|
||||
- Do NOT allow implementation without a validated design
|
||||
- Do NOT allow skipping required review
|
||||
- Do NOT allow silent escalation or de-escalation
|
||||
- Do NOT merge design and implementation phases
|
||||
|
||||
---
|
||||
|
||||
## Exit Conditions
|
||||
|
||||
This meta-skill exits ONLY when:
|
||||
- the next step is explicitly identified, AND
|
||||
- all required prior steps are complete
|
||||
|
||||
Possible exits:
|
||||
- “Proceed to implementation planning”
|
||||
- “Run multi-agent-brainstorming”
|
||||
- “Return to brainstorming for clarification”
|
||||
- "If a reviewed design reports a final disposition of APPROVED, REVISE, or REJECT, you MUST route the workflow accordingly and state the chosen next step explicitly."
|
||||
---
|
||||
|
||||
## Design Philosophy
|
||||
|
||||
This skill exists to:
|
||||
- slow down the right decisions
|
||||
- speed up the right execution
|
||||
- prevent costly mistakes
|
||||
|
||||
Good systems fail early.
|
||||
Bad systems fail in production.
|
||||
|
||||
This meta-skill exists to enforce the former.
|
||||
256
skills/multi-agent-brainstorming/SKILL.md
Normal file
256
skills/multi-agent-brainstorming/SKILL.md
Normal file
@@ -0,0 +1,256 @@
|
||||
---
|
||||
name: multi-agent-brainstorming
|
||||
description: >
|
||||
Use this skill when a design or idea requires higher confidence,
|
||||
risk reduction, or formal review. This skill orchestrates a
|
||||
structured, sequential multi-agent design review where each agent
|
||||
has a strict, non-overlapping role. It prevents blind spots,
|
||||
false confidence, and premature convergence.
|
||||
---
|
||||
|
||||
# Multi-Agent Brainstorming (Structured Design Review)
|
||||
|
||||
## Purpose
|
||||
|
||||
Transform a single-agent design into a **robust, review-validated design**
|
||||
by simulating a formal peer-review process using multiple constrained agents.
|
||||
|
||||
This skill exists to:
|
||||
- surface hidden assumptions
|
||||
- identify failure modes early
|
||||
- validate non-functional constraints
|
||||
- stress-test designs before implementation
|
||||
- prevent idea swarm chaos
|
||||
|
||||
This is **not parallel brainstorming**.
|
||||
It is **sequential design review with enforced roles**.
|
||||
|
||||
---
|
||||
|
||||
## Operating Model
|
||||
|
||||
- One agent designs.
|
||||
- Other agents review.
|
||||
- No agent may exceed its mandate.
|
||||
- Creativity is centralized; critique is distributed.
|
||||
- Decisions are explicit and logged.
|
||||
|
||||
The process is **gated** and **terminates by design**.
|
||||
|
||||
---
|
||||
|
||||
## Agent Roles (Non-Negotiable)
|
||||
|
||||
Each agent operates under a **hard scope limit**.
|
||||
|
||||
### 1️⃣ Primary Designer (Lead Agent)
|
||||
|
||||
**Role:**
|
||||
- Owns the design
|
||||
- Runs the standard `brainstorming` skill
|
||||
- Maintains the Decision Log
|
||||
|
||||
**May:**
|
||||
- Ask clarification questions
|
||||
- Propose designs and alternatives
|
||||
- Revise designs based on feedback
|
||||
|
||||
**May NOT:**
|
||||
- Self-approve the final design
|
||||
- Ignore reviewer objections
|
||||
- Invent requirements post-lock
|
||||
|
||||
---
|
||||
|
||||
### 2️⃣ Skeptic / Challenger Agent
|
||||
|
||||
**Role:**
|
||||
- Assume the design will fail
|
||||
- Identify weaknesses and risks
|
||||
|
||||
**May:**
|
||||
- Question assumptions
|
||||
- Identify edge cases
|
||||
- Highlight ambiguity or overconfidence
|
||||
- Flag YAGNI violations
|
||||
|
||||
**May NOT:**
|
||||
- Propose new features
|
||||
- Redesign the system
|
||||
- Offer alternative architectures
|
||||
|
||||
Prompting guidance:
|
||||
> “Assume this design fails in production. Why?”
|
||||
|
||||
---
|
||||
|
||||
### 3️⃣ Constraint Guardian Agent
|
||||
|
||||
**Role:**
|
||||
- Enforce non-functional and real-world constraints
|
||||
|
||||
Focus areas:
|
||||
- performance
|
||||
- scalability
|
||||
- reliability
|
||||
- security & privacy
|
||||
- maintainability
|
||||
- operational cost
|
||||
|
||||
**May:**
|
||||
- Reject designs that violate constraints
|
||||
- Request clarification of limits
|
||||
|
||||
**May NOT:**
|
||||
- Debate product goals
|
||||
- Suggest feature changes
|
||||
- Optimize beyond stated requirements
|
||||
|
||||
---
|
||||
|
||||
### 4️⃣ User Advocate Agent
|
||||
|
||||
**Role:**
|
||||
- Represent the end user
|
||||
|
||||
Focus areas:
|
||||
- cognitive load
|
||||
- usability
|
||||
- clarity of flows
|
||||
- error handling from user perspective
|
||||
- mismatch between intent and experience
|
||||
|
||||
**May:**
|
||||
- Identify confusing or misleading aspects
|
||||
- Flag poor defaults or unclear behavior
|
||||
|
||||
**May NOT:**
|
||||
- Redesign architecture
|
||||
- Add features
|
||||
- Override stated user goals
|
||||
|
||||
---
|
||||
|
||||
### 5️⃣ Integrator / Arbiter Agent
|
||||
|
||||
**Role:**
|
||||
- Resolve conflicts
|
||||
- Finalize decisions
|
||||
- Enforce exit criteria
|
||||
|
||||
**May:**
|
||||
- Accept or reject objections
|
||||
- Require design revisions
|
||||
- Declare the design complete
|
||||
|
||||
**May NOT:**
|
||||
- Invent new ideas
|
||||
- Add requirements
|
||||
- Reopen locked decisions without cause
|
||||
|
||||
---
|
||||
|
||||
## The Process
|
||||
|
||||
### Phase 1 — Single-Agent Design
|
||||
|
||||
1. Primary Designer runs the **standard `brainstorming` skill**
|
||||
2. Understanding Lock is completed and confirmed
|
||||
3. Initial design is produced
|
||||
4. Decision Log is started
|
||||
|
||||
No other agents participate yet.
|
||||
|
||||
---
|
||||
|
||||
### Phase 2 — Structured Review Loop
|
||||
|
||||
Agents are invoked **one at a time**, in the following order:
|
||||
|
||||
1. Skeptic / Challenger
|
||||
2. Constraint Guardian
|
||||
3. User Advocate
|
||||
|
||||
For each reviewer:
|
||||
- Feedback must be explicit and scoped
|
||||
- Objections must reference assumptions or decisions
|
||||
- No new features may be introduced
|
||||
|
||||
Primary Designer must:
|
||||
- Respond to each objection
|
||||
- Revise the design if required
|
||||
- Update the Decision Log
|
||||
|
||||
---
|
||||
|
||||
### Phase 3 — Integration & Arbitration
|
||||
|
||||
The Integrator / Arbiter reviews:
|
||||
- the final design
|
||||
- the Decision Log
|
||||
- unresolved objections
|
||||
|
||||
The Arbiter must explicitly decide:
|
||||
- which objections are accepted
|
||||
- which are rejected (with rationale)
|
||||
|
||||
---
|
||||
|
||||
## Decision Log (Mandatory Artifact)
|
||||
|
||||
The Decision Log must record:
|
||||
|
||||
- Decision made
|
||||
- Alternatives considered
|
||||
- Objections raised
|
||||
- Resolution and rationale
|
||||
|
||||
No design is considered valid without a completed log.
|
||||
|
||||
---
|
||||
|
||||
## Exit Criteria (Hard Stop)
|
||||
|
||||
You may exit multi-agent brainstorming **only when all are true**:
|
||||
|
||||
- Understanding Lock was completed
|
||||
- All reviewer agents have been invoked
|
||||
- All objections are resolved or explicitly rejected
|
||||
- Decision Log is complete
|
||||
- Arbiter has declared the design acceptable
|
||||
-
|
||||
If any criterion is unmet:
|
||||
- Continue review
|
||||
- Do NOT proceed to implementation
|
||||
If this skill was invoked by a routing or orchestration layer, you MUST report the final disposition explicitly as one of: APPROVED, REVISE, or REJECT, with a brief rationale.
|
||||
---
|
||||
|
||||
## Failure Modes This Skill Prevents
|
||||
|
||||
- Idea swarm chaos
|
||||
- Hallucinated consensus
|
||||
- Overconfident single-agent designs
|
||||
- Hidden assumptions
|
||||
- Premature implementation
|
||||
- Endless debate
|
||||
|
||||
---
|
||||
|
||||
## Key Principles
|
||||
|
||||
- One designer, many reviewers
|
||||
- Creativity is centralized
|
||||
- Critique is constrained
|
||||
- Decisions are explicit
|
||||
- Process must terminate
|
||||
|
||||
---
|
||||
|
||||
## Final Reminder
|
||||
|
||||
This skill exists to answer one question with confidence:
|
||||
|
||||
> “If this design fails, did we do everything reasonable to catch it early?”
|
||||
|
||||
If the answer is unclear, **do not exit this skill**.
|
||||
|
||||
@@ -9,20 +9,29 @@ This skill helps you create importable JSON templates for the Obsidian Web Clipp
|
||||
|
||||
## Workflow
|
||||
|
||||
1. **Identify User Intent:** specific site (YouTube), specific type (Recipe), or general clipping?
|
||||
2. **Check Existing Bases:** The user likely has a "Base" schema defined in `Templates/Bases/`.
|
||||
* **Action:** Read `Templates/Bases/*.base` to find a matching category (e.g., `Recipes.base`).
|
||||
* **Action:** Use the properties defined in the Base to structure the Clipper template properties.
|
||||
* See [references/bases-workflow.md](references/bases-workflow.md) for details.
|
||||
3. **Fetch & Analyze Reference URL:** Validate variables against a real page.
|
||||
* **Action:** Ask the user for a sample URL of the content they want to clip (if not provided).
|
||||
* **Action:** Use `WebFetch` to retrieve the page HTML.
|
||||
* **Action:** Analyze the HTML for Schema.org JSON, Meta tags, and CSS selectors.
|
||||
* See [references/analysis-workflow.md](references/analysis-workflow.md) for analysis techniques.
|
||||
4. **Draft the JSON:** Create a valid JSON object following the schema.
|
||||
* See [references/json-schema.md](references/json-schema.md).
|
||||
5. **Verify Variables:** Ensure the chosen variables (Preset, Schema, Selector) exist in your analysis.
|
||||
* See [references/variables.md](references/variables.md).
|
||||
1. **Identify User Intent:** specific site (YouTube), specific type (Recipe), or general clipping?
|
||||
2. **Check Existing Bases:** The user likely has a "Base" schema defined in `Templates/Bases/`.
|
||||
- **Action:** Read `Templates/Bases/*.base` to find a matching category (e.g., `Recipes.base`).
|
||||
- **Action:** Use the properties defined in the Base to structure the Clipper template properties.
|
||||
- See [references/bases-workflow.md](references/bases-workflow.md) for details.
|
||||
3. **Fetch & Analyze Reference URL:** Validate variables against a real page.
|
||||
- **Action:** Ask the user for a sample URL of the content they want to clip (if not provided).
|
||||
- **Action (REQUIRED):** Use `WebFetch` or a browser DOM snapshot to retrieve page content before choosing any selector.
|
||||
- **Action:** Analyze the HTML for Schema.org JSON, Meta tags, and CSS selectors.
|
||||
- **Action (REQUIRED):** Verify each selector against the fetched content. Do not guess selectors.
|
||||
- See [references/analysis-workflow.md](references/analysis-workflow.md) for analysis techniques.
|
||||
4. **Draft the JSON:** Create a valid JSON object following the schema.
|
||||
- See [references/json-schema.md](references/json-schema.md).
|
||||
5. **Verify Variables:** Ensure the chosen variables (Preset, Schema, Selector) exist in your analysis.
|
||||
- **Action (REQUIRED):** If a selector cannot be verified from the fetched content, state that explicitly and ask for another URL.
|
||||
- See [references/variables.md](references/variables.md).
|
||||
|
||||
## Selector Verification Rules
|
||||
|
||||
- **Always verify selectors** against live page content before responding.
|
||||
- **Never guess selectors.** If the DOM cannot be accessed or the element is missing, ask for another URL or a screenshot.
|
||||
- **Prefer stable selectors** (data attributes, semantic roles, unique IDs) over fragile class chains.
|
||||
- **Document the target element** in your reasoning (e.g., "About sidebar paragraph") to reduce mismatch.
|
||||
|
||||
## Output Format
|
||||
|
||||
@@ -38,16 +47,17 @@ This skill helps you create importable JSON templates for the Obsidian Web Clipp
|
||||
|
||||
## Resources
|
||||
|
||||
* [references/variables.md](references/variables.md) - Available data variables.
|
||||
* [references/filters.md](references/filters.md) - Formatting filters.
|
||||
* [references/json-schema.md](references/json-schema.md) - JSON structure documentation.
|
||||
* [references/bases-workflow.md](references/bases-workflow.md) - How to map Bases to Templates.
|
||||
* [references/analysis-workflow.md](references/analysis-workflow.md) - How to validate page data.
|
||||
- [references/variables.md](references/variables.md) - Available data variables.
|
||||
- [references/filters.md](references/filters.md) - Formatting filters.
|
||||
- [references/json-schema.md](references/json-schema.md) - JSON structure documentation.
|
||||
- [references/bases-workflow.md](references/bases-workflow.md) - How to map Bases to Templates.
|
||||
- [references/analysis-workflow.md](references/analysis-workflow.md) - How to validate page data.
|
||||
|
||||
### Official Documentation
|
||||
* [Variables](https://help.obsidian.md/web-clipper/variables)
|
||||
* [Filters](https://help.obsidian.md/web-clipper/filters)
|
||||
* [Templates](https://help.obsidian.md/web-clipper/templates)
|
||||
|
||||
- [Variables](https://help.obsidian.md/web-clipper/variables)
|
||||
- [Filters](https://help.obsidian.md/web-clipper/filters)
|
||||
- [Templates](https://help.obsidian.md/web-clipper/templates)
|
||||
|
||||
## Examples
|
||||
|
||||
|
||||
@@ -3,18 +3,21 @@
|
||||
To ensure your template works correctly, you must validate that the target page actually contains the data you want to extract.
|
||||
|
||||
## 1. Fetch the Page
|
||||
Use the `WebFetch` tool to retrieve the content of a representative URL provided by the user.
|
||||
|
||||
```
|
||||
Use the `WebFetch` tool or a browser DOM snapshot to retrieve the content of a representative URL provided by the user.
|
||||
|
||||
```text
|
||||
WebFetch(url="https://example.com/recipe/chocolate-cake")
|
||||
```
|
||||
|
||||
## 2. Analyze the Output
|
||||
|
||||
### Check for Schema.org (Recommended)
|
||||
|
||||
Look for `<script type="application/ld+json">`. This contains structured data which is the most reliable way to extract info.
|
||||
|
||||
**Example Found in HTML:**
|
||||
|
||||
```html
|
||||
<script type="application/ld+json">
|
||||
{
|
||||
@@ -29,27 +32,34 @@ Look for `<script type="application/ld+json">`. This contains structured data wh
|
||||
```
|
||||
|
||||
**Conclusion:**
|
||||
* `{{schema:Recipe:name}}` is valid.
|
||||
* `{{schema:Recipe:author.name}}` is valid.
|
||||
* **Tip:** You can use `schema:Recipe` in the `triggers` array to automatically select this template for any page with this schema.
|
||||
|
||||
- `{{schema:Recipe:name}}` is valid.
|
||||
- `{{schema:Recipe:author.name}}` is valid.
|
||||
- **Tip:** You can use `schema:Recipe` in the `triggers` array to automatically select this template for any page with this schema.
|
||||
|
||||
### Check for Meta Tags
|
||||
|
||||
Look for `<meta>` tags in the `<head>` section.
|
||||
|
||||
**Example Found in HTML:**
|
||||
|
||||
```html
|
||||
<meta property="og:title" content="The Best Chocolate Cake" />
|
||||
<meta name="description" content="A rich, moist chocolate cake recipe." />
|
||||
```
|
||||
|
||||
**Conclusion:**
|
||||
* `{{meta:og:title}}` is valid.
|
||||
* `{{meta:description}}` is valid.
|
||||
|
||||
### Check for CSS Selectors (Fallback)
|
||||
- `{{meta:og:title}}` is valid.
|
||||
- `{{meta:description}}` is valid.
|
||||
|
||||
### Check for CSS Selectors (Verified)
|
||||
|
||||
If Schema and Meta tags are missing, look for HTML structure (classes and IDs) to use with `{{selector:...}}`.
|
||||
Selectors must be verified against the fetched HTML or DOM snapshot. Do not guess selectors.
|
||||
|
||||
**Example Found in HTML:**
|
||||
|
||||
```html
|
||||
<div class="article-body">
|
||||
<h1 id="main-title">Chocolate Cake</h1>
|
||||
@@ -58,10 +68,12 @@ If Schema and Meta tags are missing, look for HTML structure (classes and IDs) t
|
||||
```
|
||||
|
||||
**Conclusion:**
|
||||
* `{{selector:h1#main-title}}` or `{{selector:h1}}` can extract the title.
|
||||
* `{{selector:.author-name}}` can extract the author.
|
||||
|
||||
- `{{selector:h1#main-title}}` or `{{selector:h1}}` can extract the title.
|
||||
- `{{selector:.author-name}}` can extract the author.
|
||||
|
||||
## 3. Verify Against Base
|
||||
|
||||
Compare the available data from your analysis with the properties required by the user's Base (see `references/bases-workflow.md`).
|
||||
|
||||
* If the Base requires `ingredients` but the page has no Schema or clear list structure, warn the user that this field might need manual entry or a prompt variable.
|
||||
- If the Base requires `ingredients` but the page has no Schema or clear list structure, warn the user that this field might need manual entry or a prompt variable.
|
||||
|
||||
1273
skills_index.json
1273
skills_index.json
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user