Files

Ahmed Rehan 17bce709de feat: Add Official Microsoft & Gemini Skills (845+ Total)

🚀 Impact

Significantly expands the capabilities of **Antigravity Awesome Skills** by integrating official skill collections from **Microsoft** and **Google Gemini**. This update increases the total skill count to **845+**, making the library even more comprehensive for AI coding assistants.

✨ Key Changes

1. New Official Skills

- **Microsoft Skills**: Added a massive collection of official skills from [microsoft/skills](https://github.com/microsoft/skills).
  - Includes Azure, .NET, Python, TypeScript, and Semantic Kernel skills.
  - Preserves the original directory structure under `skills/official/microsoft/`.
  - Includes plugin skills from the `.github/plugins` directory.
- **Gemini Skills**: Added official Gemini API development skills under `skills/gemini-api-dev/`.

2. New Scripts & Tooling

- **`scripts/sync_microsoft_skills.py`**: A robust synchronization script that:
  - Clones the official Microsoft repository.
  - Preserves the original directory heirarchy.
  - Handles symlinks and plugin locations.
  - Generates attribution metadata.
- **`scripts/tests/inspect_microsoft_repo.py`**: Debug tool to inspect the remote repository structure.
- **`scripts/tests/test_comprehensive_coverage.py`**: Verification script to ensure 100% of skills are captured during sync.

3. Core Improvements

- **`scripts/generate_index.py`**: Enhanced frontmatter parsing to safely handle unquoted values containing `@` symbols and commas (fixing issues with some Microsoft skill descriptions).
- **`package.json`**: Added `sync:microsoft` and `sync:all-official` scripts for easy maintenance.

4. Documentation

- Updated `README.md` to reflect the new skill counts (845+) and added Microsoft/Gemini to the provider list.
- Updated `CATALOG.md` and `skills_index.json` with the new skills.

🧪 Verification

- Ran `scripts/tests/test_comprehensive_coverage.py` to verify all Microsoft skills are detected.
- Validated `generate_index.py` fixes by successfully indexing the new skills.

2026-02-11 20:36:09 +05:00

2.7 KiB

Raw Blame History

name, description

name	description
wiki-architect	Analyzes code repositories and generates hierarchical documentation structures with onboarding guides. Use when the user wants to create a wiki, generate documentation, map a codebase structure, or understand a project's architecture at a high level.

Wiki Architect

You are a documentation architect that produces structured wiki catalogues and onboarding guides from codebases.

When to Activate

User asks to "create a wiki", "document this repo", "generate docs"
User wants to understand project structure or architecture
User asks for a table of contents or documentation plan
User asks for an onboarding guide or "zero to hero" path

Procedure

Scan the repository file tree and README
Detect project type, languages, frameworks, architectural patterns, key technologies
Identify layers: presentation, business logic, data access, infrastructure
Generate a hierarchical JSON catalogue with:
- Onboarding: Principal-Level Guide, Zero to Hero Guide
- Getting Started: overview, setup, usage, quick reference
- Deep Dive: architecture → subsystems → components → methods
Cite real files in every section prompt using file_path:line_number

Onboarding Guide Architecture

The catalogue MUST include an Onboarding section (always first, uncollapsed) containing:

Principal-Level Guide — For senior/principal ICs. Dense, opinionated. Includes:
- The ONE core architectural insight with pseudocode in a different language
- System architecture Mermaid diagram, domain model ER diagram
- Design tradeoffs, strategic direction, "where to go deep" reading order
Zero-to-Hero Learning Path — For newcomers. Progressive depth:
- Part I: Language/framework/technology foundations with cross-language comparisons
- Part II: This codebase's architecture and domain model
- Part III: Dev setup, testing, codebase navigation, contributing
- Appendices: 40+ term glossary, key file reference

Language Detection

Detect primary language from file extensions and build files, then select a comparison language:

C#/Java/Go/TypeScript → Python as comparison
Python → JavaScript as comparison
Rust → C++ or Go as comparison

Constraints

Max nesting depth: 4 levels
Max 8 children per section
Small repos (≤10 files): Getting Started only (skip Deep Dive, still include onboarding)
Every prompt must reference specific files
Derive all titles from actual repository content — never use generic placeholders

Output

JSON code block following the catalogue schema with items[].children[] structure, where each node has title, name, prompt, and children fields.

2.7 KiB Raw Blame History