chore(release): v5.6.0

Co-authored-by: Ogie <hidayah.anka@gmail.com>

CATALOG.md

@@ -2,7 +2,7 @@
 
 Generated at: 2026-02-08T00:00:00.000Z
 
-Total skills: 845
+Total skills: 864
 
 ## architecture (64)
 
@@ -116,7 +116,7 @@ Total skills: 845
 | `team-composition-analysis` | This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity a... | team, composition | team, composition, analysis, skill, should, used, user, asks, plan, structure, determine, hiring |
 | `whatsapp-automation` | Automate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts. Always search tools first for c... | whatsapp | whatsapp, automation, automate, business, tasks, via, rube, mcp, composio, send, messages, upload |
 
-## data-ai (153)
+## data-ai (159)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -134,6 +134,9 @@ Use when creating hosted agents that run custom code i... | agents, v2, py | age
 | `audio-transcriber` | Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration | audio, transcription, whisper, meeting-minutes, speech-to-text | audio, transcription, whisper, meeting-minutes, speech-to-text, transcriber, transform, recordings, professional, markdown, documentation, intelligent |
 | `autonomous-agent-patterns` | Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use ... | autonomous, agent | autonomous, agent, building, coding, agents, covers, integration, permission, browser, automation, human, loop |
 | `autonomous-agents` | Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The c... | autonomous, agents | autonomous, agents, ai, independently, decompose, goals, plan, actions, execute, self, correct, without |
+| `azure-ai-agents-persistent-dotnet` | Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conve... | azure, ai, agents, persistent, dotnet | azure, ai, agents, persistent, dotnet, sdk, net, low, level, creating, managing, threads |
+| `azure-ai-agents-persistent-java` | Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
+Triggers: "PersistentAgen... | azure, ai, agents, persistent, java | azure, ai, agents, persistent, java, sdk, low, level, creating, managing, threads, messages |
 | `azure-ai-contentsafety-java` | Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm det... | azure, ai, contentsafety, java | azure, ai, contentsafety, java, content, moderation, applications, safety, sdk, implementing, text, image |
 | `azure-ai-contentsafety-py` | Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.
 Triggers: "azure-ai-contents... | azure, ai, contentsafety, py | azure, ai, contentsafety, py, content, safety, sdk, python, detecting, harmful, text, images |
@@ -240,6 +243,8 @@ Triggers: "data lake", "Da... | azure, storage, file, datalake, py | azure, stor
 | `google-analytics-automation` | Automate Google Analytics tasks via Rube MCP (Composio): run reports, list accounts/properties, funnels, pivots, key events. Always search tools first for cu... | google, analytics | google, analytics, automation, automate, tasks, via, rube, mcp, composio, run, reports, list |
 | `googlesheets-automation` | Automate Google Sheets operations (read, write, format, filter, manage spreadsheets) via Rube MCP (Composio). Read/write data, manage tabs, apply formatting,... | googlesheets | googlesheets, automation, automate, google, sheets, operations, read, write, format, filter, spreadsheets, via |
 | `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 al... | graphql | graphql, gives, clients, exactly, data, no, less, one, endpoint, typed, schema, introspection |
+| `hosted-agents-v2-py` | Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.
+Use when creating container-based agents that run custom code in Azure ... | hosted, agents, v2, py | hosted, agents, v2, py, azure, ai, sdk, imagebasedhostedagentdefinition, creating, container, run, custom |
 | `hybrid-search-implementation` | Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides... | hybrid, search | hybrid, search, combine, vector, keyword, improved, retrieval, implementing, rag, building, engines, neither |
 | `ios-developer` | Develop native iOS applications with Swift/SwiftUI. Masters iOS 18, SwiftUI, UIKit integration, Core Data, networking, and App Store optimization. Use PROACT... | ios | ios, developer, develop, native, applications, swift, swiftui, masters, 18, uikit, integration, core |
 | `langchain-architecture` | Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implement... | langchain, architecture | langchain, architecture, llm, applications, framework, agents, memory, integration, building, implementing, ai, creating |
@@ -255,12 +260,14 @@ Triggers: "data lake", "Da... | azure, storage, file, datalake, py | azure, stor
 | `nextjs-best-practices` | Next.js App Router principles. Server Components, data fetching, routing patterns. | nextjs, best, practices | nextjs, best, practices, next, js, app, router, principles, server, components, data, fetching |
 | `nodejs-backend-patterns` | Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration,... | nodejs, backend | nodejs, backend, node, js, express, fastify, implementing, middleware, error, handling, authentication, database |
 | `php-pro` | Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications. | php | php, pro, write, idiomatic, code, generators, iterators, spl, data, structures, oop, features |
+| `podcast-generation` | Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, aud... | podcast, generation | podcast, generation, generate, ai, powered, style, audio, narratives, azure, openai, gpt, realtime |
 | `postgres-best-practices` | Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, o... | postgres, best, practices | postgres, best, practices, supabase, performance, optimization, skill, writing, reviewing, optimizing, queries, schema |
 | `postgresql` | Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features | postgresql | postgresql, specific, schema, covers, data, types, indexing, constraints, performance, features |
 | `prisma-expert` | Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, m... | prisma | prisma, orm, schema, migrations, query, optimization, relations, modeling, database, operations, proactively, issues |
 | `programmatic-seo` | Design and evaluate programmatic SEO strategies for creating SEO-driven pages at scale using templates and structured data. Use when the user mentions progra... | programmatic, seo | programmatic, seo, evaluate, creating, driven, pages, scale, structured, data, user, mentions, directory |
 | `prompt-caching` | Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache... | prompt, caching | prompt, caching, llm, prompts, including, anthropic, response, cag, cache, augmented, generation |
 | `prompt-engineering-patterns` | Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, impro... | prompt, engineering | prompt, engineering, techniques, maximize, llm, performance, reliability, controllability, optimizing, prompts, improving, outputs |
+| `pydantic-models-py` | Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schem... | pydantic, models, py | pydantic, models, py, following, multi, model, base, update, response, indb, variants, defining |
 | `rag-engineer` | Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LL... | rag | rag, engineer, building, retrieval, augmented, generation, masters, embedding, models, vector, databases, chunking |
 | `rag-implementation` | Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded A... | rag | rag, retrieval, augmented, generation, llm, applications, vector, databases, semantic, search, implementing, knowledge |
 | `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.j... | react, best, practices | react, best, practices, vercel, next, js, performance, optimization, guidelines, engineering, skill, should |
@@ -272,6 +279,7 @@ Triggers: "data lake", "Da... | azure, storage, file, datalake, py | azure, stor
 | `senior-architect` | Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, F... | senior | senior, architect, software, architecture, skill, designing, scalable, maintainable, reactjs, nextjs, nodejs, express |
 | `seo-audit` | Diagnose and audit SEO issues affecting crawlability, indexation, rankings, and organic performance. Use when the user asks for an SEO audit, technical SEO r... | seo, audit | seo, audit, diagnose, issues, affecting, crawlability, indexation, rankings, organic, performance, user, asks |
 | `similarity-search-patterns` | Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieva... | similarity, search | similarity, search, efficient, vector, databases, building, semantic, implementing, nearest, neighbor, queries, optimizing |
+| `skill-creator-ms` | Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating exi... | skill, creator, ms | skill, creator, ms, creating, effective, skills, ai, coding, agents, working, azure, sdks |
 | `skill-seekers` | -Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes. | skill, seekers | skill, seekers, automatically, convert, documentation, websites, github, repositories, pdfs, claude, ai, skills |
 | `spark-optimization` | Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or... | spark, optimization | spark, optimization, optimize, apache, jobs, partitioning, caching, shuffle, memory, tuning, improving, performance |
 | `sql-optimization-patterns` | Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when de... | sql, optimization | sql, optimization, query, indexing, explain, analysis, dramatically, improve, database, performance, eliminate, slow |
@@ -292,7 +300,7 @@ Triggers: "data lake", "Da... | azure, storage, file, datalake, py | azure, stor
 | `xlsx-official` | Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work ... | xlsx, official | xlsx, official, spreadsheet, creation, editing, analysis, formulas, formatting, data, visualization, claude, work |
 | `youtube-automation` | Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools firs... | youtube | youtube, automation, automate, tasks, via, rube, mcp, composio, upload, videos, playlists, search |
 
-## development (124)
+## development (132)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -364,12 +372,17 @@ Triggers: "queue storage", "QueueServic... | azure, storage, queue, py | azure,
 | `cc-skill-coding-standards` | Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development. | cc, skill, coding, standards | cc, skill, coding, standards, universal, typescript, javascript, react, node, js, development |
 | `cc-skill-frontend-patterns` | Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. | cc, skill, frontend | cc, skill, frontend, development, react, next, js, state, performance, optimization, ui |
 | `context7-auto-research` | Automatically fetch latest library/framework documentation for Claude Code via Context7 API | context7, auto, research | context7, auto, research, automatically, fetch, latest, library, framework, documentation, claude, code, via |
+| `copilot-sdk` | Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Pytho... | copilot, sdk | copilot, sdk, applications, powered, github, creating, programmatic, integrations, node, js, typescript, python |
 | `csharp-pro` | Write modern C# code with advanced features like records, pattern matching, and async/await. Optimizes .NET applications, implements enterprise patterns, and... | csharp | csharp, pro, write, code, features, like, records, matching, async, await, optimizes, net |
+| `dbos-golang` | DBOS Go SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Go code with DBOS, creating workflows and ... | dbos, golang | dbos, golang, go, sdk, building, reliable, fault, tolerant, applications, durable, skill, writing |
+| `dbos-python` | DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workfl... | dbos, python | dbos, python, sdk, building, reliable, fault, tolerant, applications, durable, skill, writing, code |
+| `dbos-typescript` | DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creatin... | dbos, typescript | dbos, typescript, sdk, building, reliable, fault, tolerant, applications, durable, skill, writing, code |
 | `discord-bot-architect` | Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactiv... | discord, bot | discord, bot, architect, specialized, skill, building, bots, covers, js, javascript, pycord, python |
 | `dotnet-architect` | Expert .NET backend architect specializing in C#, ASP.NET Core, Entity Framework, Dapper, and enterprise application patterns. Masters async/await, dependenc... | dotnet | dotnet, architect, net, backend, specializing, asp, core, entity, framework, dapper, enterprise, application |
 | `dotnet-backend-patterns` | Master C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Ent... | dotnet, backend | dotnet, backend, net, development, building, robust, apis, mcp, servers, enterprise, applications, covers |
 | `exa-search` | Semantic search, similar content discovery, and structured research using Exa API | exa, search | exa, search, semantic, similar, content, discovery, structured, research, api |
 | `fastapi-pro` | Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROA... | fastapi | fastapi, pro, high, performance, async, apis, sqlalchemy, pydantic, v2, microservices, websockets, python |
+| `fastapi-router-py` | Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new rout... | fastapi, router, py | fastapi, router, py, routers, crud, operations, authentication, dependencies, proper, response, models, building |
 | `fastapi-templates` | Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applicati... | fastapi | fastapi, async, dependency, injection, error, handling, building, new, applications, setting, up, backend |
 | `firecrawl-scraper` | Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API | firecrawl, scraper | firecrawl, scraper, deep, web, scraping, screenshots, pdf, parsing, website, crawling, api |
 | `fp-ts-errors` | Handle errors as values using fp-ts Either and TaskEither for cleaner, more predictable TypeScript code. Use when implementing error handling patterns with f... | fp, ts, errors | fp, ts, errors, handle, values, either, taskeither, cleaner, predictable, typescript, code, implementing |
@@ -382,6 +395,7 @@ Triggers: "queue storage", "QueueServic... | azure, storage, queue, py | azure,
 | `gemini-api-dev` | Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function... | gemini, api, dev | gemini, api, dev, skill, building, applications, models, working, multimodal, content, text, images |
 | `go-concurrency-patterns` | Master Go concurrency with goroutines, channels, sync primitives, and context. Use when building concurrent Go applications, implementing worker pools, or de... | go, concurrency | go, concurrency, goroutines, channels, sync, primitives, context, building, concurrent, applications, implementing, worker |
 | `go-playwright` | Expert capability for robust, stealthy, and efficient browser automation using Playwright Go. | go, playwright | go, playwright, capability, robust, stealthy, efficient, browser, automation |
+| `go-rod-master` | Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns. | go, rod, master | go, rod, master, browser, automation, web, scraping, chrome, devtools, protocol, including, stealth |
 | `golang-pro` | Master Go 1.21+ with modern patterns, advanced concurrency, performance optimization, and production-ready microservices. Expert in the latest Go ecosystem i... | golang | golang, pro, go, 21, concurrency, performance, optimization, microservices, latest, ecosystem, including, generics |
 | `hubspot-integration` | Expert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations, webhooks, and custom objects. Covers... | hubspot, integration | hubspot, integration, crm, including, oauth, authentication, objects, associations, batch, operations, webhooks, custom |
 | `javascript-mastery` | Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced pa... | javascript, mastery | javascript, mastery, reference, covering, 33, essential, concepts, every, developer, should, know, fundamentals |
@@ -392,6 +406,7 @@ Triggers: "queue storage", "QueueServic... | azure, storage, queue, py | azure,
 | `m365-agents-ts` | Microsoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentApplication routing, Express hosting, stre... | m365, agents, ts | m365, agents, ts, microsoft, 365, sdk, typescript, node, js, multichannel, teams, copilot |
 | `makepad-skills` | Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting. | makepad, skills | makepad, skills, ui, development, rust, apps, setup, shaders, packaging, troubleshooting |
 | `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 whe... | mcp, builder | mcp, builder, creating, high, quality, model, context, protocol, servers, enable, llms, interact |
+| `mcp-builder-ms` | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use whe... | mcp, builder, ms | mcp, builder, ms, creating, high, quality, model, context, protocol, servers, enable, llms |
 | `memory-safety-patterns` | Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, ... | memory, safety | memory, safety, safe, programming, raii, ownership, smart, pointers, resource, rust, writing, code |
 | `microsoft-azure-webjobs-extensions-authentication-events-dotnet` | Microsoft Entra Authentication Events SDK for .NET. Azure Functions triggers for custom authentication extensions. Use for token enrichment, custom claims, a... | microsoft, azure, webjobs, extensions, authentication, events, dotnet | microsoft, azure, webjobs, extensions, authentication, events, dotnet, entra, sdk, net, functions, triggers |
 | `mobile-design` | Mobile-first design and engineering doctrine for iOS and Android apps. Covers touch interaction, performance, platform conventions, offline behavior, and mob... | mobile | mobile, first, engineering, doctrine, ios, android, apps, covers, touch, interaction, performance, platform |
@@ -408,6 +423,7 @@ Triggers: "queue storage", "QueueServic... | azure, storage, queue, py | azure,
 | `python-performance-optimization` | Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottleneck... | python, performance, optimization | python, performance, optimization, profile, optimize, code, cprofile, memory, profilers, debugging, slow, optimizing |
 | `python-pro` | Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem ... | python | python, pro, 12, features, async, programming, performance, optimization, latest, ecosystem, including, uv |
 | `python-testing-patterns` | Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites... | python | python, testing, pytest, fixtures, mocking, test, driven, development, writing, tests, setting, up |
+| `react-flow-architect` | Expert ReactFlow architect for building interactive graph applications with hierarchical node-edge systems, performance optimization, and auto-layout integra... | react, flow | react, flow, architect, reactflow, building, interactive, graph, applications, hierarchical, node, edge, performance |
 | `react-flow-node-ts` | Create React Flow node components with TypeScript types, handles, and Zustand integration. Use when building custom nodes for React Flow canvas, creating vis... | react, flow, node, ts | react, flow, node, ts, components, typescript, types, zustand, integration, building, custom, nodes |
 | `react-modernization` | Upgrade React applications to latest versions, migrate from class components to hooks, and adopt concurrent features. Use when modernizing React codebases, m... | react, modernization | react, modernization, upgrade, applications, latest, versions, migrate, class, components, hooks, adopt, concurrent |
 | `react-native-architecture` | Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns. Use when developing mobile apps, impleme... | react, native, architecture | react, native, architecture, apps, expo, navigation, modules, offline, sync, cross, platform, developing |
@@ -439,7 +455,7 @@ TRIGGER: "shopify", "shopify app", "checkout extension",... | shopify | shopify,
 | `webapp-testing` | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing... | webapp | webapp, testing, toolkit, interacting, local, web, applications, playwright, supports, verifying, frontend, functionality |
 | `zustand-store-ts` | Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creati... | zustand, store, ts | zustand, store, ts, stores, typescript, subscribewithselector, middleware, proper, state, action, separation, building |
 
-## general (134)
+## general (135)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -517,6 +533,7 @@ TRIGGER: "shopify", "shopify app", "checkout extension",... | shopify | shopify,
 | `git-advanced-workflows` | Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use... | git, advanced | git, advanced, including, rebasing, cherry, picking, bisect, worktrees, reflog, maintain, clean, history |
 | `git-pr-workflows-onboard` | You are an **expert onboarding specialist and knowledge transfer architect** with deep experience in remote-first organizations, technical team integration, ... | git, pr, onboard | git, pr, onboard, onboarding, knowledge, transfer, architect, deep, experience, remote, first, organizations |
 | `git-pr-workflows-pr-enhance` | You are a PR optimization expert specializing in creating high-quality pull requests that facilitate efficient code reviews. Generate comprehensive PR descri... | git, pr, enhance | git, pr, enhance, optimization, specializing, creating, high, quality, pull, requests, facilitate, efficient |
+| `github-issue-creator` | Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error me... | github, issue, creator | github, issue, creator, convert, raw, notes, error, logs, voice, dictation, screenshots, crisp |
 | `imagen` |  | imagen | imagen |
 | `infinite-gratitude` | Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies). | infinite, gratitude | infinite, gratitude, multi, agent, research, skill, parallel, execution, 10, agents, battle, tested |
 | `interactive-portfolio` | Expert in building portfolios that actually land jobs and clients - not just showing work, but creating memorable experiences. Covers developer portfolios, d... | interactive, portfolio | interactive, portfolio, building, portfolios, actually, land, jobs, clients, just, showing, work, creating |
@@ -558,7 +575,7 @@ TRIGGER: "shopify", "shopify app", "checkout extension",... | shopify | shopify,
 | `subagent-driven-development` | Use when executing implementation plans with independent tasks in the current session | subagent, driven | subagent, driven, development, executing, plans, independent, tasks, current, session |
 | `superpowers-lab` | Lab environment for Claude superpowers | superpowers, lab | superpowers, lab, environment, claude |
 | `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... | theme, factory | theme, factory, toolkit, styling, artifacts, these, slides, docs, reportings, html, landing, pages |
-| `threejs-skills` | Three.js skills for creating 3D elements and interactive experiences | threejs, skills | threejs, skills, three, js, creating, 3d, elements, interactive, experiences |
+| `threejs-skills` | Create 3D scenes, interactive experiences, and visual effects using Three.js. Use when user requests 3D graphics, WebGL experiences, 3D visualizations, anima... | threejs, skills | threejs, skills, 3d, scenes, interactive, experiences, visual, effects, three, js, user, requests |
 | `turborepo-caching` | Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing d... | turborepo, caching | turborepo, caching, configure, efficient, monorepo, local, remote, setting, up, optimizing, pipelines, implementing |
 | `tutorial-engineer` | Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples. U... | tutorial | tutorial, engineer, creates, step, tutorials, educational, content, code, transforms, complex, concepts, progressive |
 | `ui-skills` | Opinionated, evolving constraints to guide agents when building interfaces | ui, skills | ui, skills, opinionated, evolving, constraints, agents, building, interfaces |
@@ -578,7 +595,7 @@ TRIGGER: "shopify", "shopify app", "checkout extension",... | shopify | shopify,
 | `x-article-publisher-skill` | Publish articles to X/Twitter | x, article, publisher, skill | x, article, publisher, skill, publish, articles, twitter |
 | `youtube-summarizer` | Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks | video, summarization, transcription, youtube, content-analysis | video, summarization, transcription, youtube, content-analysis, summarizer, extract, transcripts, videos, generate, detailed, summaries |
 
-## infrastructure (101)
+## infrastructure (102)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -588,6 +605,7 @@ TRIGGER: "shopify", "shopify app", "checkout extension",... | shopify | shopify,
 | `application-performance-performance-optimization` | Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across... | application, performance, optimization | application, performance, optimization, optimize, profiling, observability, backend, frontend, tuning, coordinating, stack |
 | `aws-serverless` | Specialized skill for building production-ready serverless applications on AWS. Covers Lambda functions, API Gateway, DynamoDB, SQS/SNS event-driven patterns... | aws, serverless | aws, serverless, specialized, skill, building, applications, covers, lambda, functions, api, gateway, dynamodb |
 | `aws-skills` | AWS development with infrastructure automation and cloud architecture patterns | aws, skills | aws, skills, development, infrastructure, automation, cloud, architecture |
+| `azd-deployment` | Deploy containerized applications to Azure Container Apps using Azure Developer CLI (azd). Use when setting up azd projects, writing azure.yaml configuration... | azd, deployment | azd, deployment, deploy, containerized, applications, azure, container, apps, developer, cli, setting, up |
 | `azure-ai-anomalydetector-java` | Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate/multivariate anomaly detection, time-serie... | azure, ai, anomalydetector, java | azure, ai, anomalydetector, java, anomaly, detection, applications, detector, sdk, implementing, univariate, multivariate |
 | `azure-identity-java` | Azure Identity Java SDK for authentication with Azure services. Use when implementing DefaultAzureCredential, managed identity, service principal, or any Azu... | azure, identity, java | azure, identity, java, sdk, authentication, implementing, defaultazurecredential, managed, principal, any, applications |
 | `azure-identity-py` | Azure Identity SDK for Python authentication. Use for DefaultAzureCredential, managed identity, service principals, and token caching.
@@ -691,7 +709,7 @@ Triggers: "azure-storage-file-share", "Share... | azure, storage, file, share, p
 | `wireshark-analysis` | This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow... | wireshark | wireshark, network, traffic, analysis, skill, should, used, user, asks, analyze, capture, packets |
 | `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... |  | automation, infrastructure, makes, ai, agents, reliable, without, durable, execution, network, hiccup, during |
 
-## security (126)
+## security (129)
 
 | Skill | Description | Tags | Triggers |
 | --- | --- | --- | --- |
@@ -727,6 +745,7 @@ Triggers: "keyvault secrets rust", "SecretClient rust"... | azure, keyvault, sec
 | `code-reviewer` | Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Mas... | code | code, reviewer, elite, review, specializing, ai, powered, analysis, security, vulnerabilities, performance, optimization |
 | `codebase-cleanup-deps-audit` | You are a dependency security expert specializing in vulnerability scanning, license compliance, and supply chain security. Analyze project dependencies for ... | codebase, cleanup, deps, audit | codebase, cleanup, deps, audit, dependency, security, specializing, vulnerability, scanning, license, compliance, supply |
 | `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... | computer, use, agents | computer, use, agents, ai, interact, computers, like, humans, do, viewing, screens, moving |
+| `crypto-bd-agent` | Autonomous crypto business development patterns — multi-chain token discovery, 100-point scoring with wallet forensics, x402 micropayments, ERC-8004 on-chain... | crypto, business-development, token-scanning, x402, erc-8004, autonomous-agent, solana, ethereum, wallet-forensics | crypto, business-development, token-scanning, x402, erc-8004, autonomous-agent, solana, ethereum, wallet-forensics, bd, agent, autonomous |
 | `database-admin` | Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP database services, Infra... | database, admin | database, admin, administrator, specializing, cloud, databases, automation, reliability, engineering, masters, aws, azure |
 | `database-migration` | Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databas... | database, migration | database, migration, execute, migrations, orms, platforms, zero, downtime, data, transformation, rollback, procedures |
 | `database-migrations-sql-migrations` | SQL database migrations with zero-downtime strategies for PostgreSQL, MySQL, SQL Server | database, sql, migrations, postgresql, mysql, flyway, liquibase, alembic, zero-downtime | database, sql, migrations, postgresql, mysql, flyway, liquibase, alembic, zero-downtime, zero, downtime, server |
@@ -761,6 +780,8 @@ Triggers: "keyvault secrets rust", "SecretClient rust"... | azure, keyvault, sec
 | `k8s-manifest-generator` | Create production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets following best practices and security standards. Use when gen... | k8s, manifest, generator | k8s, manifest, generator, kubernetes, manifests, deployments, configmaps, secrets, following, security, standards, generating |
 | `k8s-security-policies` | Implement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clust... | k8s, security, policies | k8s, security, policies, kubernetes, including, networkpolicy, podsecuritypolicy, rbac, grade, securing, clusters, implementing |
 | `kubernetes-architect` | Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Mas... | kubernetes | kubernetes, architect, specializing, cloud, native, infrastructure, gitops, argocd, flux, enterprise, container, orchestration |
+| `laravel-expert` | Senior Laravel Engineer role for production-grade, maintainable, and idiomatic Laravel solutions. Focuses on clean architecture, security, performance, and m... | laravel | laravel, senior, engineer, role, grade, maintainable, idiomatic, solutions, clean, architecture, security, performance |
+| `laravel-security-audit` | Security auditor for Laravel applications. Analyzes code for vulnerabilities, misconfigurations, and insecure practices using OWASP standards and Laravel sec... | laravel, security, audit | laravel, security, audit, auditor, applications, analyzes, code, vulnerabilities, misconfigurations, insecure, owasp, standards |
 | `legal-advisor` | Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements. Use ... | legal, advisor | legal, advisor, draft, privacy, policies, terms, disclaimers, notices, creates, gdpr, compliant, texts |
 | `linkerd-patterns` | Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies... | linkerd | linkerd, mesh, lightweight, security, deployments, setting, up, configuring, traffic, policies, implementing, zero |
 | `loki-mode` | Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security... | loki, mode | loki, mode, multi, agent, autonomous, startup, claude, code, triggers, orchestrates, 100, specialized |

CHANGELOG.md

@@ -7,6 +7,148 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [5.6.0] - 2026-02-17 - "Autonomous Agents & Trusted Workflows"
+
+> **DBOS for reliable workflows, Crypto BD agents, and improved usage documentation.**
+
+This release introduces official DBOS skills for building fault-tolerant applications in TypeScript, Python, and Go, plus a sophisticated autonomous Business Development agent for crypto, and a comprehensive usage guide to help new users get started.
+
+### Added
+
+- **DBOS Skills** (Official):
+  - `dbos-typescript`: Durable workflows and steps for TypeScript.
+  - `dbos-python`: Fault-tolerant Python applications.
+  - `dbos-golang`: Reliable Go services.
+- **New Skill**: `crypto-bd-agent` - Autonomous BD patterns for token discovery, scoring, and outreach with wallet forensics.
+- **Documentation**: New `docs/USAGE.md` guide addressing post-installation confusion (how to prompt, where skills live).
+
+### Registry
+
+- **Total Skills**: 864 (from 860).
+- **Generated Files**: Synced `skills_index.json`, `data/catalog.json`, and `README.md`.
+
+### Contributors
+
+- **[@maxdml](https://github.com/maxdml)** - DBOS Skills (PR #94).
+- **[@buzzbysolcex](https://github.com/buzzbysolcex)** - Crypto BD Agent (PR #92).
+- **[@copilot-swe-agent](https://github.com/apps/copilot-swe-agent)** - Usage Guide (PR #93).
+
+---
+
+## [5.5.0] - 2026-02-16 - "Laravel Pro & ReactFlow Architect"
+
+> **Advanced Laravel engineering roles and ReactFlow architecture patterns.**
+
+This release introduces professional Laravel capabilities (Expert & Security Auditor) and a comprehensive ReactFlow Architect skill for building complex node-based applications.
+
+### Added
+
+- **New Skill**: `laravel-expert` - Senior Laravel Engineer role for production-grade, maintainable, and idiomatic solutions (clean architecture, security, performance).
+- **New Skill**: `laravel-security-audit` - Specialized security auditor for Laravel apps (OWASP, vulnerabilities, misconfigurations).
+- **New Skill**: `react-flow-architect` - Expert ReactFlow patterns for interactive graph apps (hierarchical navigation, performance, customized state management).
+
+### Changed
+
+- **OpenCode**: Updated installation path to `.agents/skills` to align with latest OpenCode standards.
+
+### Registry
+
+- **Total Skills**: 860 (from 857).
+- **Generated Files**: Synced `skills_index.json`, `data/catalog.json`, and `README.md`.
+
+### Contributors
+
+- **[@Musayrlsms](https://github.com/Musayrlsms)** - Laravel Expert & Security Audit skills (PR #85, #86).
+- **[@mertbaskurt](https://github.com/mertbaskurt)** - ReactFlow Architect skill (PR #88).
+- **[@sharmanilay](https://github.com/sharmanilay)** - OpenCode path fix (PR #87).
+
+---
+
+## [5.4.0] - 2026-02-16 - "CursorRules Pro & Go-Rod"
+
+> **Community contributions: CursorRules Pro in credits and go-rod-master skill for browser automation with Go.**
+
+This release adds CursorRules Pro to Community Contributors and a new skill for browser automation and web scraping with go-rod (Chrome DevTools Protocol) in Golang, including stealth and anti-bot-detection patterns.
+
+### New Skills
+
+#### go-rod-master ([skills/go-rod-master/](skills/go-rod-master/))
+
+**Browser automation and web scraping with Go and Chrome DevTools Protocol.**
+Comprehensive guide for the go-rod library: launch and page lifecycle, Must vs error patterns, context and timeouts, element selectors, auto-wait, and integration with go-rod/stealth for anti-bot detection.
+
+- **Key features**: CDP-native driver, thread-safe operations, stealth plugin, request hijacking, concurrent page pools.
+- **When to use**: Scraping or automating sites with Go, headless browser for SPAs, stealth/anti-bot needs, migrating from chromedp or Playwright Go.
+
+> **Try it:** "Automate logging into example.com with Go using go-rod and stealth."
+
+### Registry
+
+- **Total Skills**: 857 (from 856).
+- **Generated files**: README, skills_index.json, catalog, and bundles synced.
+
+### Credits
+
+- **[@Wittlesus](https://github.com/Wittlesus)** - CursorRules Pro in Community Contributors (PR #81).
+- **[@8hrsk](https://github.com/8hrsk)** - go-rod-master skill (PR #83).
+
+---
+
+_Upgrade now: `git pull origin main` to fetch the latest skills._
+
+---
+
+## [5.3.0] - 2026-02-13 - "Advanced Three.js & Modern Graphics"
+
+> **Enhanced Three.js patterns: performance, visual polish, and production practices.**
+
+This release significantly upgrades our 3D visualization capabilities with a comprehensive Three.js skill upgrade, focusing on CDN-compatible patterns, performance optimizations, and modern graphics techniques like shadows, fog, and GSAP integration.
+
+### Added
+
+- **Modern Three.js Patterns**: Comprehensive guide for `r128` (CDN) and production environments.
+- **Visual Polish**: Advanced sections for shadows, environment maps, and tone mapping.
+- **Interaction Models**: Custom camera controls (OrbitControls alternative) and raycasting for object selection.
+- **Production Readiness**: Integration patterns for GSAP, scroll-based animations, and build tool optimizations.
+
+### Registry
+
+- **Total Skills**: 856.
+- **Metadata**: Fixed missing source and risk fields for `threejs-skills`.
+- **Sync**: All discovery artifacts (README, Catalog, Index) updated and synced.
+
+### Contributors
+
+- **[@Krishna-hehe](https://github.com/Krishna-hehe)** - Advanced Three.js skill overhaul (PR #78).
+
+---
+
+> **New AI capabilities: Podcast Generation, Azure Identity, and Self-Evolving Agents.**
+
+### Added
+
+- **New Skill**: `podcast-generation` - Create multi-speaker podcasts from text/URLs using OpenAI Text-to-Speech (TTS) and pydub.
+- **New Skill**: `weevolve` - Self-evolving knowledge engine with recursive improvement protocol.
+- **Azure Skills Expansion**:
+  - `azure-ai-agents-persistent-dotnet`: Persistent agent patterns for .NET.
+  - `azure-ai-agents-persistent-java`: Persistent agent patterns for Java.
+  - `azd-deployment`: Azure Developer CLI deployment strategies.
+- **Python Enhancements**:
+  - `pydantic-models-py`: Robust data validation patterns.
+  - `fastapi-router-py`: Scalable API routing structures.
+
+### Registry
+
+- **Total Skills**: 856 (from 845).
+- **Generated Files**: Synced `skills_index.json`, `data/catalog.json`, and `README.md`.
+
+### Contributors
+
+- **[@sickn33](https://github.com/sickn33)** - Podcast Generation & Azure skills sync (PR #74).
+- **[@aro-brez](https://github.com/aro-brez)** - WeEvolve skill (Issue #75).
+
+---
+
 ## [5.1.0] - 2026-02-12 - "Official Microsoft & Gemini Skills"
 
 > **845+ skills: the largest single-PR expansion ever, powered by official vendor collections.**

README.md

@@ -1,6 +1,6 @@
-# 🌌 Antigravity Awesome Skills: 845+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
+# 🌌 Antigravity Awesome Skills: 864+ Agentic Skills for Claude Code, Gemini CLI, Cursor, Copilot & More
 
-> **The Ultimate Collection of 845+ Universal Agentic Skills for AI Coding Assistants — Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode, AdaL**
+> **The Ultimate Collection of 864+ Universal Agentic Skills for AI Coding Assistants — Claude Code, Gemini CLI, Codex CLI, Antigravity IDE, GitHub Copilot, Cursor, OpenCode, AdaL**
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Claude Code](https://img.shields.io/badge/Claude%20Code-Anthropic-purple)](https://claude.ai)
@@ -16,7 +16,7 @@
 
 If this project helps you, you can [support it here](https://buymeacoffee.com/sickn33) or simply ⭐ the repo.
 
-**Antigravity Awesome Skills** is a curated, battle-tested library of **845 high-performance agentic skills** designed to work seamlessly across all major AI coding assistants:
+**Antigravity Awesome Skills** is a curated, battle-tested library of **864 high-performance agentic skills** designed to work seamlessly across all major AI coding assistants:
 
 - 🟣 **Claude Code** (Anthropic CLI)
 - 🔵 **Gemini CLI** (Google DeepMind)
@@ -32,13 +32,14 @@ This repository provides essential skills to transform your AI assistant into a
 ## Table of Contents
 
 - [🚀 New Here? Start Here!](#new-here-start-here)
+- [📖 Complete Usage Guide](docs/USAGE.md) - **Start here if confused after installation!**
 - [🔌 Compatibility & Invocation](#compatibility--invocation)
 - [🛠️ Installation](#installation)
 - [🧯 Troubleshooting](#troubleshooting)
 - [🎁 Curated Collections (Bundles)](#curated-collections)
 - [🧭 Antigravity Workflows](#antigravity-workflows)
 - [📦 Features & Categories](#features--categories)
-- [📚 Browse 845+ Skills](#browse-845-skills)
+- [📚 Browse 864+ Skills](#browse-864-skills)
 - [🤝 How to Contribute](#how-to-contribute)
 - [🤝 Community](#community)
 - [☕ Support the Project](#support-the-project)
@@ -52,11 +53,11 @@ This repository provides essential skills to transform your AI assistant into a
 
 ## New Here? Start Here!
 
-**Welcome to the V5.0.0 Workflows Edition.** This isn't just a list of scripts; it's a complete operating system for your AI Agent.
+**Welcome to the V5.4.0 Workflows Edition.** This isn't just a list of scripts; it's a complete operating system for your AI Agent.
 
 ### 1. 🐣 Context: What is this?
 
-**Antigravity Awesome Skills** (Release 5.0.0) is a massive upgrade to your AI's capabilities.
+**Antigravity Awesome Skills** (Release 5.4.0) is a massive upgrade to your AI's capabilities.
 
 AI Agents (like Claude Code, Cursor, or Gemini) are smart, but they lack **specific tools**. They don't know your company's "Deployment Protocol" or the specific syntax for "AWS CloudFormation".
 **Skills** are small markdown files that teach them how to do these specific tasks perfectly, every time.
@@ -94,7 +95,9 @@ Once installed, just ask your agent naturally:
 > "Use the **@brainstorming** skill to help me plan a SaaS."
 > "Run **@lint-and-validate** on this file."
 
-👉 **[Read the Full Getting Started Guide](docs/GETTING_STARTED.md)**
+👉 **NEW:** [**Complete Usage Guide - Read This First!**](docs/USAGE.md) (answers: "What do I do after installation?", "How do I execute skills?", "What should prompts look like?")
+
+👉 **[Full Getting Started Guide](docs/GETTING_STARTED.md)**
 
 ---
 
@@ -110,11 +113,12 @@ These skills follow the universal **SKILL.md** format and work with any AI codin
 | **Antigravity** | IDE  | `(Agent Mode) Use skill...`       | `.agent/skills/`  |
 | **Cursor**      | IDE  | `@skill-name (in Chat)`           | `.cursor/skills/` |
 | **Copilot**     | Ext  | `(Paste content manually)`        | N/A               |
-| **OpenCode**    | CLI  | `opencode run @skill-name`        | `.agent/skills/`  |
+| **OpenCode**    | CLI  | `opencode run @skill-name`        | `.agents/skills/`  |
 | **AdaL CLI**    | CLI  | `(Auto) Skills load on-demand`    | `.adal/skills/`   |
 
 > [!TIP]
 > **Universal Path**: We recommend cloning to `.agent/skills/`. Most modern tools (Antigravity, recent CLIs) look here by default.
+> **OpenCode Path Update**: opencode path is changed to `.agents/skills` for global skills. See [Place Files](https://opencode.ai/docs/skills/#place-files) directive on OpenCode Docs.
 
 > [!WARNING]
 > **Windows Users**: this repository uses **symlinks** for official skills.
@@ -144,8 +148,8 @@ npx antigravity-awesome-skills --gemini
 # Codex CLI
 npx antigravity-awesome-skills --codex
 
-# OpenCode (Universal)
-npx antigravity-awesome-skills
+# OpenCode
+npx antigravity-awesome-skills --path .agents/skills
 
 # Custom path
 npx antigravity-awesome-skills --path ./my-skills
@@ -171,8 +175,8 @@ git clone https://github.com/sickn33/antigravity-awesome-skills.git .codex/skill
 # Cursor specific
 git clone https://github.com/sickn33/antigravity-awesome-skills.git .cursor/skills
 
-# OpenCode specific (Universal path)
-git clone https://github.com/sickn33/antigravity-awesome-skills.git .agent/skills
+# OpenCode
+git clone https://github.com/sickn33/antigravity-awesome-skills.git .agents/skills
 ```
 
 ---
@@ -218,26 +222,34 @@ npx antigravity-awesome-skills
 
 **Bundles** are curated groups of skills for a specific role or goal (for example: `Web Wizard`, `Security Engineer`, `OSS Maintainer`).
 
-They help you avoid picking from 700+ skills one by one.
+They help you avoid picking from 860+ skills one by one.
 
-What bundles are:
+### ⚠️ Important: Bundles Are NOT Separate Installations!
 
-- Recommended starting sets for common workflows.
-- A shortcut for onboarding and faster execution.
+**Common confusion:** "Do I need to install each bundle separately?"
 
-What bundles are not:
+**Answer: NO!** Here's what bundles actually are:
 
-- Not a separate install.
-- Not a locked preset.
+**What bundles ARE:**
+- ✅ Recommended skill lists organized by role
+- ✅ Curated starting points to help you decide what to use
+- ✅ Time-saving shortcuts for discovering relevant skills
 
-How to use bundles:
+**What bundles are NOT:**
+- ❌ Separate installations or downloads
+- ❌ Different git commands
+- ❌ Something you need to "activate"
 
-1. Install the repository once.
-2. Pick one bundle in [docs/BUNDLES.md](docs/BUNDLES.md).
-3. Start with 3-5 skills from that bundle in your prompt.
-4. Add more only when needed.
+### How to use bundles:
 
-Examples:
+1. **Install the repository once** (you already have all skills)
+2. **Browse bundles** in [docs/BUNDLES.md](docs/BUNDLES.md) to find your role
+3. **Pick 3-5 skills** from that bundle to start using in your prompts
+4. **Reference them in your conversations** with your AI (e.g., "Use @brainstorming...")
+
+For detailed examples of how to actually use skills, see the [**Usage Guide**](docs/USAGE.md).
+
+### Examples:
 
 - Building a SaaS MVP: `Essentials` + `Full-Stack Developer` + `QA & Testing`.
 - Hardening production: `Security Developer` + `DevOps & Cloud` + `Observability & Monitoring`.
@@ -280,7 +292,7 @@ The repository is organized into specialized domains to transform your AI into a
 
 Counts change as new skills are added. For the current full registry, see [CATALOG.md](CATALOG.md).
 
-## Browse 845+ Skills
+## Browse 864+ Skills
 
 We have moved the full skill registry to a dedicated catalog to keep this README clean.
 
@@ -379,6 +391,7 @@ This collection would not be possible without the incredible work of the Claude
 - **[whatiskadudoing/fp-ts-skills](https://github.com/whatiskadudoing/fp-ts-skills)**: Practical fp-ts skills for TypeScript – fp-ts-pragmatic, fp-ts-react, fp-ts-errors (v4.4.0).
 - **[webzler/agentMemory](https://github.com/webzler/agentMemory)**: Source for the agent-memory-mcp skill.
 - **[sstklen/claude-api-cost-optimization](https://github.com/sstklen/claude-api-cost-optimization)**: Save 50-90% on Claude API costs with smart optimization strategies (MIT).
+- **[Wittlesus/cursorrules-pro](https://github.com/Wittlesus/cursorrules-pro)**: Professional .cursorrules configurations for 8 frameworks - Next.js, React, Python, Go, Rust, and more. Works with Cursor, Claude Code, and Windsurf.
 
 ### Inspirations
 
@@ -437,6 +450,8 @@ We officially thank the following contributors for their help in making this rep
 - [@ericgandrade](https://github.com/ericgandrade)
 - [@sohamganatra](https://github.com/sohamganatra)
 - [@Nguyen-Van-Chan](https://github.com/Nguyen-Van-Chan)
+- [@8hrsk](https://github.com/8hrsk)
+- [@Wittlesus](https://github.com/Wittlesus)
 
 ---
 

data/aliases.json

@@ -10,9 +10,9 @@
     "templates": "app-builder/templates",
     "application-performance-optimization": "application-performance-performance-optimization",
     "aws penetration testing": "aws-penetration-testing",
-    "azure-ai-java": "azure-ai-anomalydetector-java",
+    "azure-ai-dotnet": "azure-ai-agents-persistent-dotnet",
+    "azure-ai-java": "azure-ai-agents-persistent-java",
     "azure-ai-py": "azure-ai-contentunderstanding-py",
-    "azure-ai-dotnet": "azure-ai-document-intelligence-dotnet",
     "azure-ai-ts": "azure-ai-document-intelligence-ts",
     "azure-communication-java": "azure-communication-callautomation-java",
     "azure-keyvault-rust": "azure-keyvault-certificates-rust",

data/bundles.json

@@ -20,6 +20,7 @@
         "async-python-patterns",
         "autonomous-agents",
         "aws-serverless",
+        "azure-ai-agents-persistent-java",
         "azure-ai-anomalydetector-java",
         "azure-ai-contentsafety-java",
         "azure-ai-contentsafety-py",
@@ -117,6 +118,10 @@
         "claude-d3js-skill",
         "code-documentation-doc-generate",
         "context7-auto-research",
+        "copilot-sdk",
+        "dbos-golang",
+        "dbos-python",
+        "dbos-typescript",
         "discord-bot-architect",
         "django-pro",
         "documentation-generation-doc-generate",
@@ -126,6 +131,7 @@
         "dotnet-backend-patterns",
         "exa-search",
         "fastapi-pro",
+        "fastapi-router-py",
         "fastapi-templates",
         "firebase",
         "firecrawl-scraper",
@@ -145,6 +151,7 @@
         "gemini-api-dev",
         "go-concurrency-patterns",
         "go-playwright",
+        "go-rod-master",
         "golang-pro",
         "graphql",
         "hubspot-integration",
@@ -161,6 +168,7 @@
         "m365-agents-ts",
         "makepad-skills",
         "mcp-builder",
+        "mcp-builder-ms",
         "memory-safety-patterns",
         "mobile-design",
         "mobile-developer",
@@ -179,7 +187,9 @@
         "openapi-spec-generation",
         "php-pro",
         "plaid-fintech",
+        "podcast-generation",
         "product-manager-toolkit",
+        "pydantic-models-py",
         "python-development-python-scaffold",
         "python-packaging",
         "python-patterns",
@@ -187,6 +197,7 @@
         "python-pro",
         "python-testing-patterns",
         "react-best-practices",
+        "react-flow-architect",
         "react-flow-node-ts",
         "react-modernization",
         "react-native-architecture",
@@ -283,6 +294,8 @@
         "k8s-manifest-generator",
         "k8s-security-policies",
         "kubernetes-architect",
+        "laravel-expert",
+        "laravel-security-audit",
         "legal-advisor",
         "linkerd-patterns",
         "loki-mode",
@@ -339,6 +352,7 @@
     "k8s-core": {
       "description": "Kubernetes and service mesh essentials.",
       "skills": [
+        "azd-deployment",
         "azure-cosmos-db-py",
         "azure-identity-dotnet",
         "azure-identity-java",
@@ -456,6 +470,7 @@
         "postgresql",
         "prisma-expert",
         "programmatic-seo",
+        "pydantic-models-py",
         "quant-analyst",
         "react-best-practices",
         "react-ui-patterns",
@@ -486,6 +501,7 @@
         "api-testing-observability-api-mock",
         "application-performance-performance-optimization",
         "aws-serverless",
+        "azd-deployment",
         "azure-ai-anomalydetector-java",
         "azure-mgmt-applicationinsights-dotnet",
         "azure-mgmt-arizeaiobservabilityeval-dotnet",
@@ -497,6 +513,7 @@
         "c4-container",
         "cicd-automation-workflow-automate",
         "code-review-ai-ai-review",
+        "crypto-bd-agent",
         "data-engineer",
         "data-engineering-data-pipeline",
         "database-migration",

data/catalog.json

@@ -1,6 +1,6 @@
 {
   "generatedAt": "2026-02-08T00:00:00.000Z",
-  "total": 845,
+  "total": 864,
   "skills": [
     {
       "id": "3d-web-experience",
@@ -1550,6 +1550,87 @@
       ],
       "path": "skills/aws-skills/SKILL.md"
     },
+    {
+      "id": "azd-deployment",
+      "name": "azd-deployment",
+      "description": "Deploy containerized applications to Azure Container Apps using Azure Developer CLI (azd). Use when setting up azd projects, writing azure.yaml configuration, creating Bicep infrastructure for Container Apps, configuring remote builds with ACR, implementing idempotent deployments, managing environment variables across local/.azure/Bicep, or troubleshooting azd up failures. Triggers on requests for azd configuration, Container Apps deployment, multi-service deployments, and infrastructure-as-code with Bicep.",
+      "category": "infrastructure",
+      "tags": [
+        "azd",
+        "deployment"
+      ],
+      "triggers": [
+        "azd",
+        "deployment",
+        "deploy",
+        "containerized",
+        "applications",
+        "azure",
+        "container",
+        "apps",
+        "developer",
+        "cli",
+        "setting",
+        "up"
+      ],
+      "path": "skills/azd-deployment/SKILL.md"
+    },
+    {
+      "id": "azure-ai-agents-persistent-dotnet",
+      "name": "azure-ai-agents-persistent-dotnet",
+      "description": "Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".",
+      "category": "data-ai",
+      "tags": [
+        "azure",
+        "ai",
+        "agents",
+        "persistent",
+        "dotnet"
+      ],
+      "triggers": [
+        "azure",
+        "ai",
+        "agents",
+        "persistent",
+        "dotnet",
+        "sdk",
+        "net",
+        "low",
+        "level",
+        "creating",
+        "managing",
+        "threads"
+      ],
+      "path": "skills/azure-ai-agents-persistent-dotnet/SKILL.md"
+    },
+    {
+      "id": "azure-ai-agents-persistent-java",
+      "name": "azure-ai-agents-persistent-java",
+      "description": "Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.\nTriggers: \"PersistentAgentsClient\", \"persistent agents java\", \"agent threads java\", \"agent runs java\", \"streaming agents java\".",
+      "category": "data-ai",
+      "tags": [
+        "azure",
+        "ai",
+        "agents",
+        "persistent",
+        "java"
+      ],
+      "triggers": [
+        "azure",
+        "ai",
+        "agents",
+        "persistent",
+        "java",
+        "sdk",
+        "low",
+        "level",
+        "creating",
+        "managing",
+        "threads",
+        "messages"
+      ],
+      "path": "skills/azure-ai-agents-persistent-java/SKILL.md"
+    },
     {
       "id": "azure-ai-anomalydetector-java",
       "name": "azure-ai-anomalydetector-java",
@@ -7259,6 +7340,31 @@
       ],
       "path": "skills/convertkit-automation/SKILL.md"
     },
+    {
+      "id": "copilot-sdk",
+      "name": "copilot-sdk",
+      "description": "Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management, custom tools, streaming, hooks, MCP servers, BYOK providers, session persistence, and custom agents. Requires GitHub Copilot CLI installed and a GitHub Copilot subscription (unless using BYOK).",
+      "category": "development",
+      "tags": [
+        "copilot",
+        "sdk"
+      ],
+      "triggers": [
+        "copilot",
+        "sdk",
+        "applications",
+        "powered",
+        "github",
+        "creating",
+        "programmatic",
+        "integrations",
+        "node",
+        "js",
+        "typescript",
+        "python"
+      ],
+      "path": "skills/copilot-sdk/SKILL.md"
+    },
     {
       "id": "copy-editing",
       "name": "copy-editing",
@@ -7451,6 +7557,38 @@
       ],
       "path": "skills/crewai/SKILL.md"
     },
+    {
+      "id": "crypto-bd-agent",
+      "name": "crypto-bd-agent",
+      "description": "Autonomous crypto business development patterns — multi-chain token discovery, 100-point scoring with wallet forensics, x402 micropayments, ERC-8004 on-chain identity, LLM cascade routing, and pipeline automation for CEX/DEX listing acquisition. Use when building AI agents for crypto BD, token evaluation, exchange listing outreach, or autonomous commerce with payment protocols.",
+      "category": "security",
+      "tags": [
+        "crypto",
+        "business-development",
+        "token-scanning",
+        "x402",
+        "erc-8004",
+        "autonomous-agent",
+        "solana",
+        "ethereum",
+        "wallet-forensics"
+      ],
+      "triggers": [
+        "crypto",
+        "business-development",
+        "token-scanning",
+        "x402",
+        "erc-8004",
+        "autonomous-agent",
+        "solana",
+        "ethereum",
+        "wallet-forensics",
+        "bd",
+        "agent",
+        "autonomous"
+      ],
+      "path": "skills/crypto-bd-agent/SKILL.md"
+    },
     {
       "id": "csharp-pro",
       "name": "csharp-pro",
@@ -7929,6 +8067,81 @@
       ],
       "path": "skills/datadog-automation/SKILL.md"
     },
+    {
+      "id": "dbos-golang",
+      "name": "dbos-golang",
+      "description": "DBOS Go SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Go code with DBOS, creating workflows and steps, using queues, using the DBOS Client from external applications, or building Go applications that need to be resilient to failures.",
+      "category": "development",
+      "tags": [
+        "dbos",
+        "golang"
+      ],
+      "triggers": [
+        "dbos",
+        "golang",
+        "go",
+        "sdk",
+        "building",
+        "reliable",
+        "fault",
+        "tolerant",
+        "applications",
+        "durable",
+        "skill",
+        "writing"
+      ],
+      "path": "skills/dbos-golang/SKILL.md"
+    },
+    {
+      "id": "dbos-python",
+      "name": "dbos-python",
+      "description": "DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.",
+      "category": "development",
+      "tags": [
+        "dbos",
+        "python"
+      ],
+      "triggers": [
+        "dbos",
+        "python",
+        "sdk",
+        "building",
+        "reliable",
+        "fault",
+        "tolerant",
+        "applications",
+        "durable",
+        "skill",
+        "writing",
+        "code"
+      ],
+      "path": "skills/dbos-python/SKILL.md"
+    },
+    {
+      "id": "dbos-typescript",
+      "name": "dbos-typescript",
+      "description": "DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.",
+      "category": "development",
+      "tags": [
+        "dbos",
+        "typescript"
+      ],
+      "triggers": [
+        "dbos",
+        "typescript",
+        "sdk",
+        "building",
+        "reliable",
+        "fault",
+        "tolerant",
+        "applications",
+        "durable",
+        "skill",
+        "writing",
+        "code"
+      ],
+      "path": "skills/dbos-typescript/SKILL.md"
+    },
     {
       "id": "dbt-transformation-patterns",
       "name": "dbt-transformation-patterns",
@@ -9387,6 +9600,32 @@
       ],
       "path": "skills/fastapi-pro/SKILL.md"
     },
+    {
+      "id": "fastapi-router-py",
+      "name": "fastapi-router-py",
+      "description": "Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.",
+      "category": "development",
+      "tags": [
+        "fastapi",
+        "router",
+        "py"
+      ],
+      "triggers": [
+        "fastapi",
+        "router",
+        "py",
+        "routers",
+        "crud",
+        "operations",
+        "authentication",
+        "dependencies",
+        "proper",
+        "response",
+        "models",
+        "building"
+      ],
+      "path": "skills/fastapi-router-py/SKILL.md"
+    },
     {
       "id": "fastapi-templates",
       "name": "fastapi-templates",
@@ -10716,6 +10955,32 @@
       ],
       "path": "skills/github-automation/SKILL.md"
     },
+    {
+      "id": "github-issue-creator",
+      "name": "github-issue-creator",
+      "description": "Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence.",
+      "category": "general",
+      "tags": [
+        "github",
+        "issue",
+        "creator"
+      ],
+      "triggers": [
+        "github",
+        "issue",
+        "creator",
+        "convert",
+        "raw",
+        "notes",
+        "error",
+        "logs",
+        "voice",
+        "dictation",
+        "screenshots",
+        "crisp"
+      ],
+      "path": "skills/github-issue-creator/SKILL.md"
+    },
     {
       "id": "github-workflow-automation",
       "name": "github-workflow-automation",
@@ -10883,6 +11148,32 @@
       ],
       "path": "skills/go-playwright/SKILL.md"
     },
+    {
+      "id": "go-rod-master",
+      "name": "go-rod-master",
+      "description": "Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns.",
+      "category": "development",
+      "tags": [
+        "go",
+        "rod",
+        "master"
+      ],
+      "triggers": [
+        "go",
+        "rod",
+        "master",
+        "browser",
+        "automation",
+        "web",
+        "scraping",
+        "chrome",
+        "devtools",
+        "protocol",
+        "including",
+        "stealth"
+      ],
+      "path": "skills/go-rod-master/SKILL.md"
+    },
     {
       "id": "godot-gdscript-patterns",
       "name": "godot-gdscript-patterns",
@@ -11177,6 +11468,33 @@
       ],
       "path": "skills/helpdesk-automation/SKILL.md"
     },
+    {
+      "id": "hosted-agents-v2-py",
+      "name": "hosted-agents-v2-py",
+      "description": "Build hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition.\nUse when creating container-based agents that run custom code in Azure AI Foundry.\nTriggers: \"ImageBasedHostedAgentDefinition\", \"hosted agent\", \"container agent\", \n\"create_version\", \"ProtocolVersionRecord\", \"AgentProtocol.RESPONSES\".",
+      "category": "data-ai",
+      "tags": [
+        "hosted",
+        "agents",
+        "v2",
+        "py"
+      ],
+      "triggers": [
+        "hosted",
+        "agents",
+        "v2",
+        "py",
+        "azure",
+        "ai",
+        "sdk",
+        "imagebasedhostedagentdefinition",
+        "creating",
+        "container",
+        "run",
+        "custom"
+      ],
+      "path": "skills/hosted-agents-v2-py/SKILL.md"
+    },
     {
       "id": "hr-pro",
       "name": "hr-pro",
@@ -12196,6 +12514,56 @@
       ],
       "path": "skills/langgraph/SKILL.md"
     },
+    {
+      "id": "laravel-expert",
+      "name": "laravel-expert",
+      "description": "Senior Laravel Engineer role for production-grade, maintainable, and idiomatic Laravel solutions. Focuses on clean architecture, security, performance, and modern standards (Laravel 10/11+).",
+      "category": "security",
+      "tags": [
+        "laravel"
+      ],
+      "triggers": [
+        "laravel",
+        "senior",
+        "engineer",
+        "role",
+        "grade",
+        "maintainable",
+        "idiomatic",
+        "solutions",
+        "clean",
+        "architecture",
+        "security",
+        "performance"
+      ],
+      "path": "skills/laravel-expert/SKILL.md"
+    },
+    {
+      "id": "laravel-security-audit",
+      "name": "laravel-security-audit",
+      "description": "Security auditor for Laravel applications. Analyzes code for vulnerabilities, misconfigurations, and insecure practices using OWASP standards and Laravel security best practices.",
+      "category": "security",
+      "tags": [
+        "laravel",
+        "security",
+        "audit"
+      ],
+      "triggers": [
+        "laravel",
+        "security",
+        "audit",
+        "auditor",
+        "applications",
+        "analyzes",
+        "code",
+        "vulnerabilities",
+        "misconfigurations",
+        "insecure",
+        "owasp",
+        "standards"
+      ],
+      "path": "skills/laravel-security-audit/SKILL.md"
+    },
     {
       "id": "last30days",
       "name": "last30days",
@@ -12915,6 +13283,32 @@
       ],
       "path": "skills/mcp-builder/SKILL.md"
     },
+    {
+      "id": "mcp-builder-ms",
+      "name": "mcp-builder",
+      "description": "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), Node/TypeScript (MCP SDK), or C#/.NET (Microsoft MCP SDK).",
+      "category": "development",
+      "tags": [
+        "mcp",
+        "builder",
+        "ms"
+      ],
+      "triggers": [
+        "mcp",
+        "builder",
+        "ms",
+        "creating",
+        "high",
+        "quality",
+        "model",
+        "context",
+        "protocol",
+        "servers",
+        "enable",
+        "llms"
+      ],
+      "path": "skills/mcp-builder-ms/SKILL.md"
+    },
     {
       "id": "memory-forensics",
       "name": "memory-forensics",
@@ -14916,6 +15310,31 @@
       ],
       "path": "skills/playwright-skill/SKILL.md"
     },
+    {
+      "id": "podcast-generation",
+      "name": "podcast-generation",
+      "description": "Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.",
+      "category": "data-ai",
+      "tags": [
+        "podcast",
+        "generation"
+      ],
+      "triggers": [
+        "podcast",
+        "generation",
+        "generate",
+        "ai",
+        "powered",
+        "style",
+        "audio",
+        "narratives",
+        "azure",
+        "openai",
+        "gpt",
+        "realtime"
+      ],
+      "path": "skills/podcast-generation/SKILL.md"
+    },
     {
       "id": "popup-cro",
       "name": "popup-cro",
@@ -15481,6 +15900,32 @@
       ],
       "path": "skills/protocol-reverse-engineering/SKILL.md"
     },
+    {
+      "id": "pydantic-models-py",
+      "name": "pydantic-models-py",
+      "description": "Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.",
+      "category": "data-ai",
+      "tags": [
+        "pydantic",
+        "models",
+        "py"
+      ],
+      "triggers": [
+        "pydantic",
+        "models",
+        "py",
+        "following",
+        "multi",
+        "model",
+        "base",
+        "update",
+        "response",
+        "indb",
+        "variants",
+        "defining"
+      ],
+      "path": "skills/pydantic-models-py/SKILL.md"
+    },
     {
       "id": "pypict-skill",
       "name": "pypict-skill",
@@ -15769,6 +16214,31 @@
       ],
       "path": "skills/react-best-practices/SKILL.md"
     },
+    {
+      "id": "react-flow-architect",
+      "name": "react-flow-architect",
+      "description": "Expert ReactFlow architect for building interactive graph applications with hierarchical node-edge systems, performance optimization, and auto-layout integration. Use when Claude needs to create or optimize ReactFlow applications for: (1) Interactive process graphs with expand/collapse navigation, (2) Hierarchical tree structures with drag & drop, (3) Performance-optimized large datasets with incremental rendering, (4) Auto-layout integration with Dagre, (5) Complex state management for nodes and edges, or any advanced ReactFlow visualization requirements.",
+      "category": "development",
+      "tags": [
+        "react",
+        "flow"
+      ],
+      "triggers": [
+        "react",
+        "flow",
+        "architect",
+        "reactflow",
+        "building",
+        "interactive",
+        "graph",
+        "applications",
+        "hierarchical",
+        "node",
+        "edge",
+        "performance"
+      ],
+      "path": "skills/react-flow-architect/SKILL.md"
+    },
     {
       "id": "react-flow-node-ts",
       "name": "react-flow-node-ts",
@@ -17574,6 +18044,32 @@
       ],
       "path": "skills/skill-creator/SKILL.md"
     },
+    {
+      "id": "skill-creator-ms",
+      "name": "skill-creator",
+      "description": "Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.",
+      "category": "data-ai",
+      "tags": [
+        "skill",
+        "creator",
+        "ms"
+      ],
+      "triggers": [
+        "skill",
+        "creator",
+        "ms",
+        "creating",
+        "effective",
+        "skills",
+        "ai",
+        "coding",
+        "agents",
+        "working",
+        "azure",
+        "sdks"
+      ],
+      "path": "skills/skill-creator-ms/SKILL.md"
+    },
     {
       "id": "skill-developer",
       "name": "skill-developer",
@@ -19044,7 +19540,7 @@
     {
       "id": "threejs-skills",
       "name": "threejs-skills",
-      "description": "Three.js skills for creating 3D elements and interactive experiences",
+      "description": "Create 3D scenes, interactive experiences, and visual effects using Three.js. Use when user requests 3D graphics, WebGL experiences, 3D visualizations, animations, or interactive 3D elements.",
       "category": "general",
       "tags": [
         "threejs",
@@ -19053,13 +19549,16 @@
       "triggers": [
         "threejs",
         "skills",
+        "3d",
+        "scenes",
+        "interactive",
+        "experiences",
+        "visual",
+        "effects",
         "three",
         "js",
-        "creating",
-        "3d",
-        "elements",
-        "interactive",
-        "experiences"
+        "user",
+        "requests"
       ],
       "path": "skills/threejs-skills/SKILL.md"
     },

docs/FAQ.md

@@ -114,6 +114,8 @@ git pull origin main
 
 ## 🛠️ Using Skills
 
+> **💡 For a complete guide with examples, see [USAGE.md](USAGE.md)**
+
 ### How do I invoke a skill?
 
 Use the `@` symbol followed by the skill name:

docs/GETTING_STARTED.md

@@ -2,6 +2,8 @@
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 
+> **💡 Confused about what to do after installation?** Check out the [**Complete Usage Guide**](USAGE.md) for detailed explanations and examples!
+
 ---
 
 ## 🤔 What Are "Skills"?

docs/USAGE.md

@@ -0,0 +1,362 @@
+# 📖 Usage Guide: How to Actually Use These Skills
+
+> **Confused after installation?** This guide walks you through exactly what to do next, step by step.
+
+---
+
+## 🤔 "I just installed the repository. Now what?"
+
+Great question! Here's what just happened and what to do next:
+
+### What You Just Did
+
+When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
+
+✅ **Downloaded 860+ skill files** to your computer (usually in `~/.agent/skills/`)  
+✅ **Made them available** to your AI assistant  
+❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
+
+Think of it like installing a toolbox. You have all the tools now, but you need to **pick which ones to use** for each job.
+
+---
+
+## 🎯 Step 1: Understanding "Bundles" (This is NOT Another Install!)
+
+**Common confusion:** "Do I need to download each skill separately?"
+
+**Answer: NO!** Here's what bundles actually are:
+
+### What Bundles Are
+
+Bundles are **recommended lists** of skills grouped by role. They help you decide which skills to start using.
+
+**Analogy:** 
+- You installed a toolbox with 860 tools (✅ done)
+- Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
+- You don't install bundles—you **pick skills from them**
+
+### What Bundles Are NOT
+
+❌ Separate installations  
+❌ Different download commands  
+❌ Something you need to "activate"
+
+### Example: The "Web Wizard" Bundle
+
+When you see the [Web Wizard bundle](BUNDLES.md#-the-web-wizard-pack), it lists:
+- `frontend-design`
+- `react-best-practices`
+- `tailwind-patterns`
+- etc.
+
+These are **recommendations** for which skills a web developer should try first. They're already installed—you just need to **use them in your prompts**.
+
+---
+
+## 🚀 Step 2: How to Actually Execute/Use a Skill
+
+This is the part that should have been explained better! Here's how to use skills:
+
+### The Simple Answer
+
+**Just mention the skill name in your conversation with your AI assistant.**
+
+### Different Tools, Different Syntax
+
+The exact syntax varies by tool, but it's always simple:
+
+#### Claude Code (CLI)
+```bash
+# In your terminal/chat with Claude Code:
+>> Use @brainstorming to help me design a todo app
+```
+
+#### Cursor (IDE)
+```bash
+# In the Cursor chat panel:
+@brainstorming help me design a todo app
+```
+
+#### Gemini CLI
+```bash
+# In your conversation with Gemini:
+Use the brainstorming skill to help me plan my app
+```
+
+#### Codex CLI
+```bash
+# In your conversation with Codex:
+Apply @brainstorming to design a new feature
+```
+
+#### Antigravity IDE
+```bash
+# In agent mode:
+Use @brainstorming to plan this feature
+```
+
+> **Pro Tip:** Most modern tools use the `@skill-name` syntax. When in doubt, try that first!
+
+---
+
+## 💬 Step 3: What Should My Prompts Look Like?
+
+Here are **real-world examples** of good prompts:
+
+### Example 1: Starting a New Project
+
+**Bad Prompt:**  
+> "Help me build a todo app"
+
+**Good Prompt:**  
+> "Use @brainstorming to help me design a todo app with user authentication and cloud sync"
+
+**Why it's better:** You're explicitly invoking the skill and providing context.
+
+---
+
+### Example 2: Reviewing Code
+
+**Bad Prompt:**  
+> "Check my code"
+
+**Good Prompt:**  
+> "Use @lint-and-validate to check `src/components/Button.tsx` for issues"
+
+**Why it's better:** Specific skill + specific file = precise results.
+
+---
+
+### Example 3: Security Audit
+
+**Bad Prompt:**  
+> "Make my API secure"
+
+**Good Prompt:**  
+> "Use @api-security-best-practices to review my REST endpoints in `routes/api/users.js`"
+
+**Why it's better:** The AI knows exactly which skill's standards to apply.
+
+---
+
+### Example 4: Combining Multiple Skills
+
+**Good Prompt:**  
+> "Use @brainstorming to design a payment flow, then apply @stripe-integration to implement it"
+
+**Why it's good:** You can chain skills together in a single prompt!
+
+---
+
+## 🎓 Step 4: Your First Skill (Hands-On Tutorial)
+
+Let's actually use a skill right now. Follow these steps:
+
+### Scenario: You want to plan a new feature
+
+1. **Pick a skill:** Let's use `brainstorming` (from the "Essentials" bundle)
+
+2. **Open your AI assistant** (Claude Code, Cursor, etc.)
+
+3. **Type this exact prompt:**
+   ```
+   Use @brainstorming to help me design a user profile page for my app
+   ```
+
+4. **Press Enter**
+
+5. **What happens next:**
+   - The AI loads the brainstorming skill
+   - It will start asking you structured questions (one at a time)
+   - It will guide you through understanding, requirements, and design
+   - You answer each question, and it builds a complete spec
+
+6. **Result:** You'll end up with a detailed design document—without writing a single line of code yet!
+
+---
+
+## 🗂️ Step 5: Picking Your First Skills (Practical Advice)
+
+Don't try to use all 860 skills! Here's a sensible approach:
+
+### Start with "The Essentials" (5 skills, everyone needs these)
+
+1. **`@brainstorming`** - Plan before you build
+2. **`@lint-and-validate`** - Keep code clean
+3. **`@git-pushing`** - Save work safely  
+4. **`@systematic-debugging`** - Fix bugs faster
+5. **`@concise-planning`** - Organize tasks
+
+**How to use them:**
+- Before writing new code → `@brainstorming`
+- After writing code → `@lint-and-validate`
+- Before committing → `@git-pushing`
+- When stuck → `@systematic-debugging`
+
+### Then Add Role-Specific Skills (5-10 more)
+
+Find your role in [BUNDLES.md](BUNDLES.md) and pick 5-10 skills from that bundle.
+
+**Example for Web Developer:**
+- `@frontend-design`
+- `@react-best-practices`
+- `@tailwind-patterns`
+- `@seo-audit`
+
+**Example for Security Engineer:**
+- `@api-security-best-practices`
+- `@vulnerability-scanner`
+- `@ethical-hacking-methodology`
+
+### Finally, Add On-Demand Skills (as needed)
+
+Keep the [CATALOG.md](../CATALOG.md) open as reference. When you need something specific:
+
+> "I need to integrate Stripe payments"  
+> → Search catalog → Find `@stripe-integration` → Use it!
+
+---
+
+## 🔄 Complete Example: Building a Feature End-to-End
+
+Let's walk through a realistic scenario:
+
+### Task: "Add a blog to my Next.js website"
+
+#### Step 1: Plan (use @brainstorming)
+```
+You: Use @brainstorming to design a blog system for my Next.js site
+
+AI: [Asks structured questions about requirements]
+You: [Answer questions]
+AI: [Produces detailed design spec]
+```
+
+#### Step 2: Implement (use @nextjs-best-practices)
+```
+You: Use @nextjs-best-practices to scaffold the blog with App Router
+
+AI: [Creates file structure, sets up routes, adds components]
+```
+
+#### Step 3: Style (use @tailwind-patterns)
+```
+You: Use @tailwind-patterns to make the blog posts look modern
+
+AI: [Applies Tailwind styling with responsive design]
+```
+
+#### Step 4: SEO (use @seo-audit)
+```
+You: Use @seo-audit to optimize the blog for search engines
+
+AI: [Adds meta tags, sitemaps, structured data]
+```
+
+#### Step 5: Test & Deploy
+```
+You: Use @test-driven-development to add tests, then @vercel-deployment to deploy
+
+AI: [Creates tests, sets up CI/CD, deploys to Vercel]
+```
+
+**Result:** Professional blog built with best practices, without manually researching each step!
+
+---
+
+## 🆘 Common Questions
+
+### "Which tool should I use? Claude Code, Cursor, Gemini?"
+
+**Any of them!** Skills work universally. Pick the tool you already use or prefer:
+- **Claude Code** - Best for terminal/CLI workflows
+- **Cursor** - Best for IDE integration
+- **Gemini CLI** - Best for Google ecosystem
+- **Codex CLI** - Best for OpenAI ecosystem
+
+### "Can I see all available skills?"
+
+Yes! Three ways:
+1. Browse [CATALOG.md](../CATALOG.md) (searchable list)
+2. Run `ls ~/.agent/skills/` (if installed there)
+3. Ask your AI: "What skills do you have for [topic]?"
+
+### "Do I need to restart my IDE after installing?"
+
+Usually no, but if your AI doesn't recognize a skill:
+1. Try restarting your IDE/CLI
+2. Check the installation path matches your tool
+3. Try the explicit path: `npx antigravity-awesome-skills --claude` (or `--cursor`, `--gemini`, etc.)
+
+### "Can I create my own skills?"
+
+Yes! Use the `@skill-creator` skill:
+```
+Use @skill-creator to help me build a custom skill for [your task]
+```
+
+### "What if a skill doesn't work as expected?"
+
+1. Check the skill's SKILL.md file directly: `~/.agent/skills/[skill-name]/SKILL.md`
+2. Read the description to ensure you're using it correctly
+3. [Open an issue](https://github.com/sickn33/antigravity-awesome-skills/issues) with details
+
+---
+
+## 🎯 Quick Reference Card
+
+**Save this for quick lookup:**
+
+| Task | Skill to Use | Example Prompt |
+|------|-------------|----------------|
+| Plan new feature | `@brainstorming` | `Use @brainstorming to design a login system` |
+| Review code | `@lint-and-validate` | `Use @lint-and-validate on src/app.js` |
+| Debug issue | `@systematic-debugging` | `Use @systematic-debugging to fix login error` |
+| Security audit | `@api-security-best-practices` | `Use @api-security-best-practices on my API routes` |
+| SEO check | `@seo-audit` | `Use @seo-audit on my landing page` |
+| React component | `@react-patterns` | `Use @react-patterns to build a form component` |
+| Deploy app | `@vercel-deployment` | `Use @vercel-deployment to ship this to production` |
+
+---
+
+## 🚦 Next Steps
+
+Now that you understand how to use skills:
+
+1. ✅ **Try one skill right now** - Start with `@brainstorming` on any idea you have
+2. 📚 **Pick 3-5 skills** from your role's bundle in [BUNDLES.md](BUNDLES.md)
+3. 🔖 **Bookmark** [CATALOG.md](../CATALOG.md) for when you need something specific
+4. 🎯 **Try a workflow** from [WORKFLOWS.md](WORKFLOWS.md) for a complete end-to-end process
+
+---
+
+## 💡 Pro Tips for Maximum Effectiveness
+
+### Tip 1: Start Every Feature with @brainstorming
+> Before writing code, use `@brainstorming` to plan. You'll save hours of refactoring.
+
+### Tip 2: Chain Skills in Order
+> Don't try to do everything at once. Use skills sequentially: Plan → Build → Test → Deploy
+
+### Tip 3: Be Specific in Prompts
+> Bad: "Use @react-patterns"  
+> Good: "Use @react-patterns to build a modal component with animations"
+
+### Tip 4: Reference File Paths
+> Help the AI focus: "Use @security-auditor on routes/api/auth.js"
+
+### Tip 5: Combine Skills for Complex Tasks
+> "Use @brainstorming to design, then @test-driven-development to implement with tests"
+
+---
+
+## 📞 Still Confused?
+
+If something still doesn't make sense:
+
+1. Check the [FAQ](FAQ.md)
+2. See [Real-World Examples](EXAMPLES.md)
+3. [Open a Discussion](https://github.com/sickn33/antigravity-awesome-skills/discussions)
+4. [File an Issue](https://github.com/sickn33/antigravity-awesome-skills/issues) to help us improve this guide!
+
+Remember: You're not alone! The whole point of this project is to make AI assistants easier to use. If this guide didn't help, let us know so we can fix it. 🙌

docs/microsoft-skills-attribution.json

@@ -2,7 +2,7 @@
   "source": "microsoft/skills",
   "repository": "https://github.com/microsoft/skills",
   "license": "MIT",
-  "synced_skills": 129,
+  "synced_skills": 140,
   "structure": "flat (frontmatter name as directory name)",
   "skills": [
     {
@@ -649,6 +649,61 @@
       "flat_name": "wiki-changelog",
       "original_path": "plugins/wiki-changelog",
       "source": "microsoft/skills (plugin)"
+    },
+    {
+      "flat_name": "fastapi-router-py",
+      "original_path": ".github/skills/fastapi-router-py",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "azd-deployment",
+      "original_path": ".github/skills/azd-deployment",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "copilot-sdk",
+      "original_path": ".github/skills/copilot-sdk",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "azure-ai-agents-persistent-dotnet",
+      "original_path": ".github/skills/azure-ai-agents-persistent-dotnet",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "hosted-agents-v2-py",
+      "original_path": ".github/skills/hosted-agents-v2-py",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "pydantic-models-py",
+      "original_path": ".github/skills/pydantic-models-py",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "skill-creator-ms",
+      "original_path": ".github/skills/skill-creator",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "podcast-generation",
+      "original_path": ".github/skills/podcast-generation",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "github-issue-creator",
+      "original_path": ".github/skills/github-issue-creator",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "azure-ai-agents-persistent-java",
+      "original_path": ".github/skills/azure-ai-agents-persistent-java",
+      "source": "microsoft/skills (.github/skills)"
+    },
+    {
+      "flat_name": "mcp-builder-ms",
+      "original_path": ".github/skills/mcp-builder",
+      "source": "microsoft/skills (.github/skills)"
     }
   ]
 }

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "antigravity-awesome-skills",
-  "version": "5.0.0",
+  "version": "5.5.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "antigravity-awesome-skills",
-      "version": "5.0.0",
+      "version": "5.5.0",
       "license": "MIT",
       "bin": {
         "antigravity-awesome-skills": "bin/install.js"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "antigravity-awesome-skills",
-  "version": "5.1.0",
+  "version": "5.6.0",
   "description": "845+ agentic skills for Claude Code, Gemini CLI, Cursor, Antigravity & more. Installer CLI.",
   "license": "MIT",
   "scripts": {

release_notes.md

@@ -1,36 +1,32 @@
-## [5.0.0] - 2026-02-10 - "Antigravity Workflows Foundation"
+# v5.4.0 - CursorRules Pro & Go-Rod
 
-> First-class Workflows are now available to orchestrate multiple skills through guided execution playbooks.
+> **Community contributions: CursorRules Pro in credits and go-rod-master skill for browser automation with Go.**
 
-### 🚀 New Skills
+This release adds CursorRules Pro to Community Contributors and a new skill for browser automation and web scraping with go-rod (Chrome DevTools Protocol) in Golang, including stealth and anti-bot-detection patterns.
 
-### 🧭 [antigravity-workflows](skills/antigravity-workflows/)
+## New Skills
 
-**Orchestrates multi-step outcomes using curated workflow playbooks.**
-This new skill routes users from high-level goals to concrete execution steps across related skills and bundles.
+### go-rod-master
 
-- **Key Feature 1**: Workflow routing for SaaS MVP, Security Audit, AI Agent Systems, and Browser QA.
-- **Key Feature 2**: Explicit step-by-step outputs with prerequisites, recommended skills, and validation checkpoints.
+**Browser automation and web scraping with Go and Chrome DevTools Protocol.**
 
-> **Try it:** `Use @antigravity-workflows to run ship-saas-mvp for my project.`
+Comprehensive guide for the go-rod library: launch and page lifecycle, Must vs error patterns, context and timeouts, element selectors, auto-wait, and integration with go-rod/stealth for anti-bot detection.
+
+- **Key features**: CDP-native driver, thread-safe operations, stealth plugin, request hijacking, concurrent page pools.
+- **When to use**: Scraping or automating sites with Go, headless browser for SPAs, stealth/anti-bot needs, migrating from chromedp or Playwright Go.
+
+**Try it:** "Automate logging into example.com with Go using go-rod and stealth."
+
+## Registry
+
+- **Total Skills**: 857 (from 856).
+- **Generated files**: README, skills_index.json, catalog, and bundles synced.
+
+## Credits
+
+- **@Wittlesus** - CursorRules Pro in Community Contributors (PR #81).
+- **@8hrsk** - go-rod-master skill (PR #83).
 
 ---
 
-## 📦 Improvements
-
-- **Workflow Registry**: Added `data/workflows.json` for machine-readable workflow metadata.
-- **Workflow Docs**: Added `docs/WORKFLOWS.md` to distinguish Bundles vs Workflows and provide practical execution playbooks.
-- **Trinity Sync**: Updated `README.md`, `docs/GETTING_STARTED.md`, and `docs/FAQ.md` for workflow onboarding.
-- **Go QA Path**: Added optional `@go-playwright` wiring in QA/E2E workflow steps.
-- **Registry Update**: Catalog regenerated; repository now tracks 714 skills.
-
-## 👥 Credits
-
-A huge shoutout to our community and maintainers:
-
-- **@Walapalam** for the Workflows concept request ([Issue #72](https://github.com/sickn33/antigravity-awesome-skills/issues/72))
-- **@sickn33** for workflow integration, release preparation, and maintenance updates
-
----
-
-_Upgrade now: `git pull origin main` to fetch the latest skills._
+Upgrade now: `git pull origin main` to fetch the latest skills.

scripts/sync_microsoft_skills.py

@@ -158,11 +158,46 @@ def find_plugin_skills(source_dir: Path, already_synced_names: set):
     return results
 
 
+def find_github_skills(source_dir: Path, already_synced_names: set):
+    """Find skills in .github/skills/ not reachable via the skills/ symlink tree."""
+    results = []
+    github_skills = source_dir / ".github" / "skills"
+
+    if not github_skills.exists():
+        return results
+
+    for skill_dir in github_skills.iterdir():
+        if not skill_dir.is_dir() or not (skill_dir / "SKILL.md").exists():
+            continue
+
+        if skill_dir.name not in already_synced_names:
+            results.append({
+                "relative_path": Path(".github/skills") / skill_dir.name,
+                "skill_md": skill_dir / "SKILL.md",
+                "source_dir": skill_dir,
+            })
+
+    return results
+
+
 def sync_skills_flat(source_dir: Path, target_dir: Path):
     """
     Sync all Microsoft skills into a flat structure under skills/.
     Uses frontmatter 'name' as directory name, with collision detection.
+    Protects existing non-Microsoft skills from being overwritten.
     """
+    # Load previous attribution to know which dirs are Microsoft-owned
+    previously_synced_names = set()
+    if ATTRIBUTION_FILE.exists():
+        try:
+            with open(ATTRIBUTION_FILE) as f:
+                prev = json.load(f)
+            previously_synced_names = {
+                s["flat_name"] for s in prev.get("skills", []) if s.get("flat_name")
+            }
+        except (json.JSONDecodeError, OSError):
+            pass
+
     all_skill_entries = find_skills_in_directory(source_dir)
     print(f"  📂 Found {len(all_skill_entries)} skills in skills/ directory")
 
@@ -179,16 +214,23 @@ def sync_skills_flat(source_dir: Path, target_dir: Path):
             print(
                 f"  ⚠️  No frontmatter name for {entry['relative_path']}, using fallback: {skill_name}")
 
-        # Collision detection
+        # Internal collision detection (two Microsoft skills with same name)
         if skill_name in used_names:
             original = used_names[skill_name]
             print(
                 f"  ⚠️  Name collision '{skill_name}': {entry['relative_path']} vs {original}")
-            # Append language prefix from path to disambiguate
             lang = entry["relative_path"].parts[0] if entry["relative_path"].parts else "unknown"
             skill_name = f"{skill_name}-{lang}"
             print(f"       Resolved to: {skill_name}")
 
+        # Protect existing non-Microsoft skills from being overwritten
+        target_skill_dir = target_dir / skill_name
+        if target_skill_dir.exists() and skill_name not in previously_synced_names:
+            original_name = skill_name
+            skill_name = f"{skill_name}-ms"
+            print(
+                f"  ⚠️  '{original_name}' exists as a non-Microsoft skill, using: {skill_name}")
+
         used_names[skill_name] = str(entry["relative_path"])
 
         # Create flat target directory
@@ -212,10 +254,13 @@ def sync_skills_flat(source_dir: Path, target_dir: Path):
         synced_count += 1
         print(f"  ✅ {entry['relative_path']} → skills/{skill_name}/")
 
-    # Sync plugin skills
+    # Collect all source directory names already synced (for dedup)
     synced_names = set(used_names.keys())
-    plugin_entries = find_plugin_skills(
-        source_dir, {e["source_dir"].name for e in all_skill_entries})
+    already_synced_dir_names = {
+        e["source_dir"].name for e in all_skill_entries}
+
+    # Sync plugin skills from .github/plugins/
+    plugin_entries = find_plugin_skills(source_dir, already_synced_dir_names)
 
     if plugin_entries:
         print(f"\n  📦 Found {len(plugin_entries)} additional plugin skills")
@@ -227,9 +272,18 @@ def sync_skills_flat(source_dir: Path, target_dir: Path):
             if skill_name in synced_names:
                 skill_name = f"{skill_name}-plugin"
 
-            synced_names.add(skill_name)
-
+            # Protect existing non-Microsoft skills
             target_skill_dir = target_dir / skill_name
+            if target_skill_dir.exists() and skill_name not in previously_synced_names:
+                original_name = skill_name
+                skill_name = f"{skill_name}-ms"
+                target_skill_dir = target_dir / skill_name
+                print(
+                    f"  ⚠️  '{original_name}' exists as a non-Microsoft skill, using: {skill_name}")
+
+            synced_names.add(skill_name)
+            already_synced_dir_names.add(entry["source_dir"].name)
+
             target_skill_dir.mkdir(parents=True, exist_ok=True)
 
             shutil.copy2(entry["skill_md"], target_skill_dir / "SKILL.md")
@@ -247,6 +301,49 @@ def sync_skills_flat(source_dir: Path, target_dir: Path):
             synced_count += 1
             print(f"  ✅ {entry['relative_path']} → skills/{skill_name}/")
 
+    # Sync skills in .github/skills/ not reachable via the skills/ symlink tree
+    github_skill_entries = find_github_skills(
+        source_dir, already_synced_dir_names)
+
+    if github_skill_entries:
+        print(
+            f"\n  <20> Found {len(github_skill_entries)} skills in .github/skills/ not linked from skills/")
+        for entry in github_skill_entries:
+            skill_name = extract_skill_name(entry["skill_md"])
+            if not skill_name:
+                skill_name = entry["source_dir"].name
+
+            if skill_name in synced_names:
+                skill_name = f"{skill_name}-github"
+
+            # Protect existing non-Microsoft skills
+            target_skill_dir = target_dir / skill_name
+            if target_skill_dir.exists() and skill_name not in previously_synced_names:
+                original_name = skill_name
+                skill_name = f"{skill_name}-ms"
+                target_skill_dir = target_dir / skill_name
+                print(
+                    f"  ⚠️  '{original_name}' exists as a non-Microsoft skill, using: {skill_name}")
+
+            synced_names.add(skill_name)
+
+            target_skill_dir.mkdir(parents=True, exist_ok=True)
+
+            shutil.copy2(entry["skill_md"], target_skill_dir / "SKILL.md")
+
+            for file_item in entry["source_dir"].iterdir():
+                if file_item.name != "SKILL.md" and file_item.is_file():
+                    shutil.copy2(file_item, target_skill_dir / file_item.name)
+
+            skill_metadata.append({
+                "flat_name": skill_name,
+                "original_path": str(entry["relative_path"]),
+                "source": "microsoft/skills (.github/skills)",
+            })
+
+            synced_count += 1
+            print(f"  ✅ {entry['relative_path']} → skills/{skill_name}/")
+
     return synced_count, skill_metadata
 
 

scripts/tests/validate_skills_headings.test.js

@@ -1,11 +1,11 @@
-const assert = require('assert');
-const { hasUseSection } = require('../validate-skills');
+const assert = require("assert");
+const { hasUseSection } = require("../validate-skills");
 
 const samples = [
-  ['## When to Use', true],
-  ['## Use this skill when', true],
-  ['## When to Use This Skill', true],
-  ['## Overview', false],
+  ["## When to Use", true],
+  ["## Use this skill when", true],
+  ["## When to Use This Skill", true],
+  ["## Overview", false],
 ];
 
 for (const [heading, expected] of samples) {
@@ -13,4 +13,31 @@ for (const [heading, expected] of samples) {
   assert.strictEqual(hasUseSection(content), expected, heading);
 }
 
-console.log('ok');
+// Regression test for YAML validity in frontmatter (Issue #79)
+const fs = require("fs");
+const path = require("path");
+const { listSkillIds, parseFrontmatter } = require("../../lib/skill-utils");
+
+const SKILLS_DIR = path.join(__dirname, "../../skills");
+const skillIds = listSkillIds(SKILLS_DIR);
+
+console.log(`Checking YAML validity for ${skillIds.length} skills...`);
+
+for (const skillId of skillIds) {
+  const skillPath = path.join(SKILLS_DIR, skillId, "SKILL.md");
+  const content = fs.readFileSync(skillPath, "utf8");
+  const { errors, hasFrontmatter } = parseFrontmatter(content);
+
+  if (!hasFrontmatter) {
+    console.warn(`[WARN] No frontmatter in ${skillId}`);
+    continue;
+  }
+
+  assert.strictEqual(
+    errors.length,
+    0,
+    `YAML parse errors in ${skillId}: ${errors.join(", ")}`,
+  );
+}
+
+console.log("ok");

scripts/validate-skills.js

@@ -2,13 +2,13 @@
  * Legacy / alternative validator. For CI and PR checks, use scripts/validate_skills.py.
  * Run: npm run validate (or npm run validate:strict)
  */
-const fs = require('fs');
-const path = require('path');
-const { listSkillIds, parseFrontmatter } = require('../lib/skill-utils');
+const fs = require("fs");
+const path = require("path");
+const { listSkillIds, parseFrontmatter } = require("../lib/skill-utils");
 
-const ROOT = path.resolve(__dirname, '..');
-const SKILLS_DIR = path.join(ROOT, 'skills');
-const BASELINE_PATH = path.join(ROOT, 'validation-baseline.json');
+const ROOT = path.resolve(__dirname, "..");
+const SKILLS_DIR = path.join(ROOT, "skills");
+const BASELINE_PATH = path.join(ROOT, "validation-baseline.json");
 
 const errors = [];
 const warnings = [];
@@ -17,12 +17,14 @@ const missingDoNotUseSection = [];
 const missingInstructionsSection = [];
 const longFiles = [];
 const unknownFieldSkills = [];
-const isStrict = process.argv.includes('--strict')
-  || process.env.STRICT === '1'
-  || process.env.STRICT === 'true';
-const writeBaseline = process.argv.includes('--write-baseline')
-  || process.env.WRITE_BASELINE === '1'
-  || process.env.WRITE_BASELINE === 'true';
+const isStrict =
+  process.argv.includes("--strict") ||
+  process.env.STRICT === "1" ||
+  process.env.STRICT === "true";
+const writeBaseline =
+  process.argv.includes("--write-baseline") ||
+  process.env.WRITE_BASELINE === "1" ||
+  process.env.WRITE_BASELINE === "true";
 
 const NAME_PATTERN = /^[a-z0-9]+(?:-[a-z0-9]+)*$/;
 const MAX_NAME_LENGTH = 64;
@@ -30,14 +32,15 @@ const MAX_DESCRIPTION_LENGTH = 1024;
 const MAX_COMPATIBILITY_LENGTH = 500;
 const MAX_SKILL_LINES = 500;
 const ALLOWED_FIELDS = new Set([
-  'name',
-  'description',
-  'risk',
-  'source',
-  'license',
-  'compatibility',
-  'metadata',
-  'allowed-tools',
+  "name",
+  "description",
+  "risk",
+  "source",
+  "license",
+  "compatibility",
+  "metadata",
+  "allowed-tools",
+  "package",
 ]);
 
 const USE_SECTION_PATTERNS = [
@@ -47,15 +50,19 @@ const USE_SECTION_PATTERNS = [
 ];
 
 function hasUseSection(content) {
-  return USE_SECTION_PATTERNS.some(pattern => pattern.test(content));
+  return USE_SECTION_PATTERNS.some((pattern) => pattern.test(content));
 }
 
 function isPlainObject(value) {
-  return value && typeof value === 'object' && !Array.isArray(value);
+  return value && typeof value === "object" && !Array.isArray(value);
 }
 
-function validateStringField(fieldName, value, { min = 1, max = Infinity } = {}) {
-  if (typeof value !== 'string') {
+function validateStringField(
+  fieldName,
+  value,
+  { min = 1, max = Infinity } = {},
+) {
+  if (typeof value !== "string") {
     return `${fieldName} must be a string.`;
   }
   const trimmed = value.trim();
@@ -90,24 +97,37 @@ function loadBaseline() {
   }
 
   try {
-    const parsed = JSON.parse(fs.readFileSync(BASELINE_PATH, 'utf8'));
+    const parsed = JSON.parse(fs.readFileSync(BASELINE_PATH, "utf8"));
     return {
       useSection: Array.isArray(parsed.useSection) ? parsed.useSection : [],
-      doNotUseSection: Array.isArray(parsed.doNotUseSection) ? parsed.doNotUseSection : [],
-      instructionsSection: Array.isArray(parsed.instructionsSection) ? parsed.instructionsSection : [],
+      doNotUseSection: Array.isArray(parsed.doNotUseSection)
+        ? parsed.doNotUseSection
+        : [],
+      instructionsSection: Array.isArray(parsed.instructionsSection)
+        ? parsed.instructionsSection
+        : [],
       longFile: Array.isArray(parsed.longFile) ? parsed.longFile : [],
     };
   } catch (err) {
-    addWarning('Failed to parse validation-baseline.json; strict mode may fail.');
-    return { useSection: [], doNotUseSection: [], instructionsSection: [], longFile: [] };
+    addWarning(
+      "Failed to parse validation-baseline.json; strict mode may fail.",
+    );
+    return {
+      useSection: [],
+      doNotUseSection: [],
+      instructionsSection: [],
+      longFile: [],
+    };
   }
 }
 
 function addStrictSectionErrors(label, missing, baselineSet) {
   if (!isStrict) return;
-  const strictMissing = missing.filter(skillId => !baselineSet.has(skillId));
+  const strictMissing = missing.filter((skillId) => !baselineSet.has(skillId));
   if (strictMissing.length) {
-    addError(`Missing "${label}" section (strict): ${strictMissing.length} skills (examples: ${strictMissing.slice(0, 5).join(', ')})`);
+    addError(
+      `Missing "${label}" section (strict): ${strictMissing.length} skills (examples: ${strictMissing.slice(0, 5).join(", ")})`,
+    );
   }
 }
 
@@ -120,15 +140,19 @@ function run() {
   const baselineLongFile = new Set(baseline.longFile || []);
 
   for (const skillId of skillIds) {
-    const skillPath = path.join(SKILLS_DIR, skillId, 'SKILL.md');
+    const skillPath = path.join(SKILLS_DIR, skillId, "SKILL.md");
 
     if (!fs.existsSync(skillPath)) {
       addError(`Missing SKILL.md: ${skillId}`);
       continue;
     }
 
-    const content = fs.readFileSync(skillPath, 'utf8');
-    const { data, errors: fmErrors, hasFrontmatter } = parseFrontmatter(content);
+    const content = fs.readFileSync(skillPath, "utf8");
+    const {
+      data,
+      errors: fmErrors,
+      hasFrontmatter,
+    } = parseFrontmatter(content);
     const lineCount = content.split(/\r?\n/).length;
 
     if (!hasFrontmatter) {
@@ -136,7 +160,9 @@ function run() {
     }
 
     if (fmErrors && fmErrors.length) {
-      fmErrors.forEach(error => addError(`Frontmatter parse error (${skillId}): ${error}`));
+      fmErrors.forEach((error) =>
+        addError(`Frontmatter parse error (${skillId}): ${error}`),
+      );
     }
 
     if (!NAME_PATTERN.test(skillId)) {
@@ -144,7 +170,10 @@ function run() {
     }
 
     if (data.name !== undefined) {
-      const nameError = validateStringField('name', data.name, { min: 1, max: MAX_NAME_LENGTH });
+      const nameError = validateStringField("name", data.name, {
+        min: 1,
+        max: MAX_NAME_LENGTH,
+      });
       if (nameError) {
         addError(`${nameError} (${skillId})`);
       } else {
@@ -158,15 +187,22 @@ function run() {
       }
     }
 
-    const descError = data.description === undefined
-      ? 'description is required.'
-      : validateStringField('description', data.description, { min: 1, max: MAX_DESCRIPTION_LENGTH });
+    const descError =
+      data.description === undefined
+        ? "description is required."
+        : validateStringField("description", data.description, {
+            min: 1,
+            max: MAX_DESCRIPTION_LENGTH,
+          });
     if (descError) {
       addError(`${descError} (${skillId})`);
     }
 
     if (data.license !== undefined) {
-      const licenseError = validateStringField('license', data.license, { min: 1, max: 128 });
+      const licenseError = validateStringField("license", data.license, {
+        min: 1,
+        max: 128,
+      });
       if (licenseError) {
         addError(`${licenseError} (${skillId})`);
       }
@@ -174,7 +210,7 @@ function run() {
 
     if (data.compatibility !== undefined) {
       const compatibilityError = validateStringField(
-        'compatibility',
+        "compatibility",
         data.compatibility,
         { min: 1, max: MAX_COMPATIBILITY_LENGTH },
       );
@@ -183,10 +219,12 @@ function run() {
       }
     }
 
-    if (data['allowed-tools'] !== undefined) {
-      if (typeof data['allowed-tools'] !== 'string') {
-        addError(`allowed-tools must be a space-delimited string. (${skillId})`);
-      } else if (!data['allowed-tools'].trim()) {
+    if (data["allowed-tools"] !== undefined) {
+      if (typeof data["allowed-tools"] !== "string") {
+        addError(
+          `allowed-tools must be a space-delimited string. (${skillId})`,
+        );
+      } else if (!data["allowed-tools"].trim()) {
         addError(`allowed-tools cannot be empty. (${skillId})`);
       }
     }
@@ -196,7 +234,7 @@ function run() {
         addError(`metadata must be a string map/object. (${skillId})`);
       } else {
         for (const [key, value] of Object.entries(data.metadata)) {
-          if (typeof value !== 'string') {
+          if (typeof value !== "string") {
             addError(`metadata.${key} must be a string. (${skillId})`);
           }
         }
@@ -204,10 +242,14 @@ function run() {
     }
 
     if (data && Object.keys(data).length) {
-      const unknownFields = Object.keys(data).filter(key => !ALLOWED_FIELDS.has(key));
+      const unknownFields = Object.keys(data).filter(
+        (key) => !ALLOWED_FIELDS.has(key),
+      );
       if (unknownFields.length) {
         unknownFieldSkills.push(skillId);
-        addError(`Unknown frontmatter fields (${skillId}): ${unknownFields.join(', ')}`);
+        addError(
+          `Unknown frontmatter fields (${skillId}): ${unknownFields.join(", ")}`,
+        );
       }
     }
 
@@ -219,39 +261,61 @@ function run() {
       missingUseSection.push(skillId);
     }
 
-    if (!content.includes('## Do not use')) {
+    if (!content.includes("## Do not use")) {
       missingDoNotUseSection.push(skillId);
     }
 
-    if (!content.includes('## Instructions')) {
+    if (!content.includes("## Instructions")) {
       missingInstructionsSection.push(skillId);
     }
   }
 
   if (missingUseSection.length) {
-    addWarning(`Missing "Use this skill when" section: ${missingUseSection.length} skills (examples: ${missingUseSection.slice(0, 5).join(', ')})`);
+    addWarning(
+      `Missing "Use this skill when" section: ${missingUseSection.length} skills (examples: ${missingUseSection.slice(0, 5).join(", ")})`,
+    );
   }
 
   if (missingDoNotUseSection.length) {
-    addWarning(`Missing "Do not use" section: ${missingDoNotUseSection.length} skills (examples: ${missingDoNotUseSection.slice(0, 5).join(', ')})`);
+    addWarning(
+      `Missing "Do not use" section: ${missingDoNotUseSection.length} skills (examples: ${missingDoNotUseSection.slice(0, 5).join(", ")})`,
+    );
   }
 
   if (missingInstructionsSection.length) {
-    addWarning(`Missing "Instructions" section: ${missingInstructionsSection.length} skills (examples: ${missingInstructionsSection.slice(0, 5).join(', ')})`);
+    addWarning(
+      `Missing "Instructions" section: ${missingInstructionsSection.length} skills (examples: ${missingInstructionsSection.slice(0, 5).join(", ")})`,
+    );
   }
 
   if (longFiles.length) {
-    addWarning(`SKILL.md over ${MAX_SKILL_LINES} lines: ${longFiles.length} skills (examples: ${longFiles.slice(0, 5).join(', ')})`);
+    addWarning(
+      `SKILL.md over ${MAX_SKILL_LINES} lines: ${longFiles.length} skills (examples: ${longFiles.slice(0, 5).join(", ")})`,
+    );
   }
 
   if (unknownFieldSkills.length) {
-    addWarning(`Unknown frontmatter fields detected: ${unknownFieldSkills.length} skills (examples: ${unknownFieldSkills.slice(0, 5).join(', ')})`);
+    addWarning(
+      `Unknown frontmatter fields detected: ${unknownFieldSkills.length} skills (examples: ${unknownFieldSkills.slice(0, 5).join(", ")})`,
+    );
   }
 
-  addStrictSectionErrors('Use this skill when', missingUseSection, baselineUse);
-  addStrictSectionErrors('Do not use', missingDoNotUseSection, baselineDoNotUse);
-  addStrictSectionErrors('Instructions', missingInstructionsSection, baselineInstructions);
-  addStrictSectionErrors(`SKILL.md line count <= ${MAX_SKILL_LINES}`, longFiles, baselineLongFile);
+  addStrictSectionErrors("Use this skill when", missingUseSection, baselineUse);
+  addStrictSectionErrors(
+    "Do not use",
+    missingDoNotUseSection,
+    baselineDoNotUse,
+  );
+  addStrictSectionErrors(
+    "Instructions",
+    missingInstructionsSection,
+    baselineInstructions,
+  );
+  addStrictSectionErrors(
+    `SKILL.md line count <= ${MAX_SKILL_LINES}`,
+    longFiles,
+    baselineLongFile,
+  );
 
   if (writeBaseline) {
     const baselineData = {
@@ -266,14 +330,14 @@ function run() {
   }
 
   if (warnings.length) {
-    console.warn('Warnings:');
+    console.warn("Warnings:");
     for (const warning of warnings) {
       console.warn(`- ${warning}`);
     }
   }
 
   if (errors.length) {
-    console.error('\nErrors:');
+    console.error("\nErrors:");
     for (const error of errors) {
       console.error(`- ${error}`);
     }

skills/azd-deployment/SKILL.md

@@ -0,0 +1,296 @@
+---
+name: azd-deployment
+description: Deploy containerized applications to Azure Container Apps using Azure Developer CLI (azd). Use when setting up azd projects, writing azure.yaml configuration, creating Bicep infrastructure for Container Apps, configuring remote builds with ACR, implementing idempotent deployments, managing environment variables across local/.azure/Bicep, or troubleshooting azd up failures. Triggers on requests for azd configuration, Container Apps deployment, multi-service deployments, and infrastructure-as-code with Bicep.
+---
+
+# Azure Developer CLI (azd) Container Apps Deployment
+
+Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
+
+## Quick Start
+
+```bash
+# Initialize and deploy
+azd auth login
+azd init                    # Creates azure.yaml and .azure/ folder
+azd env new <env-name>      # Create environment (dev, staging, prod)
+azd up                      # Provision infra + build + deploy
+```
+
+## Core File Structure
+
+```
+project/
+├── azure.yaml              # azd service definitions + hooks
+├── infra/
+│   ├── main.bicep          # Root infrastructure module
+│   ├── main.parameters.json # Parameter injection from env vars
+│   └── modules/
+│       ├── container-apps-environment.bicep
+│       └── container-app.bicep
+├── .azure/
+│   ├── config.json         # Default environment pointer
+│   └── <env-name>/
+│       ├── .env            # Environment-specific values (azd-managed)
+│       └── config.json     # Environment metadata
+└── src/
+    ├── frontend/Dockerfile
+    └── backend/Dockerfile
+```
+
+## azure.yaml Configuration
+
+### Minimal Configuration
+
+```yaml
+name: azd-deployment
+services:
+  backend:
+    project: ./src/backend
+    language: python
+    host: containerapp
+    docker:
+      path: ./Dockerfile
+      remoteBuild: true
+```
+
+### Full Configuration with Hooks
+
+```yaml
+name: azd-deployment
+metadata:
+  template: my-project@1.0.0
+
+infra:
+  provider: bicep
+  path: ./infra
+
+azure:
+  location: eastus2
+
+services:
+  frontend:
+    project: ./src/frontend
+    language: ts
+    host: containerapp
+    docker:
+      path: ./Dockerfile
+      context: .
+      remoteBuild: true
+
+  backend:
+    project: ./src/backend
+    language: python
+    host: containerapp
+    docker:
+      path: ./Dockerfile
+      context: .
+      remoteBuild: true
+
+hooks:
+  preprovision:
+    shell: sh
+    run: |
+      echo "Before provisioning..."
+      
+  postprovision:
+    shell: sh
+    run: |
+      echo "After provisioning - set up RBAC, etc."
+      
+  postdeploy:
+    shell: sh
+    run: |
+      echo "Frontend: ${SERVICE_FRONTEND_URI}"
+      echo "Backend: ${SERVICE_BACKEND_URI}"
+```
+
+### Key azure.yaml Options
+
+| Option | Description |
+|--------|-------------|
+| `remoteBuild: true` | Build images in Azure Container Registry (recommended) |
+| `context: .` | Docker build context relative to project path |
+| `host: containerapp` | Deploy to Azure Container Apps |
+| `infra.provider: bicep` | Use Bicep for infrastructure |
+
+## Environment Variables Flow
+
+### Three-Level Configuration
+
+1. **Local `.env`** - For local development only
+2. **`.azure/<env>/.env`** - azd-managed, auto-populated from Bicep outputs
+3. **`main.parameters.json`** - Maps env vars to Bicep parameters
+
+### Parameter Injection Pattern
+
+```json
+// infra/main.parameters.json
+{
+  "parameters": {
+    "environmentName": { "value": "${AZURE_ENV_NAME}" },
+    "location": { "value": "${AZURE_LOCATION=eastus2}" },
+    "azureOpenAiEndpoint": { "value": "${AZURE_OPENAI_ENDPOINT}" }
+  }
+}
+```
+
+Syntax: `${VAR_NAME}` or `${VAR_NAME=default_value}`
+
+### Setting Environment Variables
+
+```bash
+# Set for current environment
+azd env set AZURE_OPENAI_ENDPOINT "https://my-openai.openai.azure.com"
+azd env set AZURE_SEARCH_ENDPOINT "https://my-search.search.windows.net"
+
+# Set during init
+azd env new prod
+azd env set AZURE_OPENAI_ENDPOINT "..." 
+```
+
+### Bicep Output → Environment Variable
+
+```bicep
+// In main.bicep - outputs auto-populate .azure/<env>/.env
+output SERVICE_FRONTEND_URI string = frontend.outputs.uri
+output SERVICE_BACKEND_URI string = backend.outputs.uri
+output BACKEND_PRINCIPAL_ID string = backend.outputs.principalId
+```
+
+## Idempotent Deployments
+
+### Why azd up is Idempotent
+
+1. **Bicep is declarative** - Resources reconcile to desired state
+2. **Remote builds tag uniquely** - Image tags include deployment timestamp
+3. **ACR reuses layers** - Only changed layers upload
+
+### Preserving Manual Changes
+
+Custom domains added via Portal can be lost on redeploy. Preserve with hooks:
+
+```yaml
+hooks:
+  preprovision:
+    shell: sh
+    run: |
+      # Save custom domains before provision
+      if az containerapp show --name "$FRONTEND_NAME" -g "$RG" &>/dev/null; then
+        az containerapp show --name "$FRONTEND_NAME" -g "$RG" \
+          --query "properties.configuration.ingress.customDomains" \
+          -o json > /tmp/domains.json
+      fi
+
+  postprovision:
+    shell: sh
+    run: |
+      # Verify/restore custom domains
+      if [ -f /tmp/domains.json ]; then
+        echo "Saved domains: $(cat /tmp/domains.json)"
+      fi
+```
+
+### Handling Existing Resources
+
+```bicep
+// Reference existing ACR (don't recreate)
+resource containerRegistry 'Microsoft.ContainerRegistry/registries@2023-07-01' existing = {
+  name: containerRegistryName
+}
+
+// Set customDomains to null to preserve Portal-added domains
+customDomains: empty(customDomainsParam) ? null : customDomainsParam
+```
+
+## Container App Service Discovery
+
+Internal HTTP routing between Container Apps in same environment:
+
+```bicep
+// Backend reference in frontend env vars
+env: [
+  {
+    name: 'BACKEND_URL'
+    value: 'http://ca-backend-${resourceToken}'  // Internal DNS
+  }
+]
+```
+
+Frontend nginx proxies to internal URL:
+```nginx
+location /api {
+    proxy_pass $BACKEND_URL;
+}
+```
+
+## Managed Identity & RBAC
+
+### Enable System-Assigned Identity
+
+```bicep
+resource containerApp 'Microsoft.App/containerApps@2024-03-01' = {
+  identity: {
+    type: 'SystemAssigned'
+  }
+}
+
+output principalId string = containerApp.identity.principalId
+```
+
+### Post-Provision RBAC Assignment
+
+```yaml
+hooks:
+  postprovision:
+    shell: sh
+    run: |
+      PRINCIPAL_ID="${BACKEND_PRINCIPAL_ID}"
+      
+      # Azure OpenAI access
+      az role assignment create \
+        --assignee-object-id "$PRINCIPAL_ID" \
+        --assignee-principal-type ServicePrincipal \
+        --role "Cognitive Services OpenAI User" \
+        --scope "$OPENAI_RESOURCE_ID" 2>/dev/null || true
+      
+      # Azure AI Search access
+      az role assignment create \
+        --assignee-object-id "$PRINCIPAL_ID" \
+        --role "Search Index Data Reader" \
+        --scope "$SEARCH_RESOURCE_ID" 2>/dev/null || true
+```
+
+## Common Commands
+
+```bash
+# Environment management
+azd env list                        # List environments
+azd env select <name>               # Switch environment
+azd env get-values                  # Show all env vars
+azd env set KEY value               # Set variable
+
+# Deployment
+azd up                              # Full provision + deploy
+azd provision                       # Infrastructure only
+azd deploy                          # Code deployment only
+azd deploy --service backend        # Deploy single service
+
+# Debugging
+azd show                            # Show project status
+az containerapp logs show -n <app> -g <rg> --follow  # Stream logs
+```
+
+## Reference Files
+
+- **Bicep patterns**: See [references/bicep-patterns.md](references/bicep-patterns.md) for Container Apps modules
+- **Troubleshooting**: See [references/troubleshooting.md](references/troubleshooting.md) for common issues
+- **azure.yaml schema**: See [references/azure-yaml-schema.md](references/azure-yaml-schema.md) for full options
+
+## Critical Reminders
+
+1. **Always use `remoteBuild: true`** - Local builds fail on M1/ARM Macs deploying to AMD64
+2. **Bicep outputs auto-populate .azure/<env>/.env** - Don't manually edit
+3. **Use `azd env set` for secrets** - Not main.parameters.json defaults
+4. **Service tags (`azd-service-name`)** - Required for azd to find Container Apps
+5. **`|| true` in hooks** - Prevent RBAC "already exists" errors from failing deploy

skills/azure-ai-agents-persistent-dotnet/SKILL.md

@@ -0,0 +1,349 @@
+---
+name: azure-ai-agents-persistent-dotnet
+description: |
+  Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: "PersistentAgentsClient", "persistent agents", "agent threads", "agent runs", "streaming agents", "function calling agents .NET".
+package: Azure.AI.Agents.Persistent
+---
+
+# Azure.AI.Agents.Persistent (.NET)
+
+Low-level SDK for creating and managing persistent AI agents with threads, messages, runs, and tools.
+
+## Installation
+
+```bash
+dotnet add package Azure.AI.Agents.Persistent --prerelease
+dotnet add package Azure.Identity
+```
+
+**Current Versions**: Stable v1.1.0, Preview v1.2.0-beta.8
+
+## Environment Variables
+
+```bash
+PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project>
+MODEL_DEPLOYMENT_NAME=gpt-4o-mini
+AZURE_BING_CONNECTION_ID=<bing-connection-resource-id>
+AZURE_AI_SEARCH_CONNECTION_ID=<search-connection-resource-id>
+```
+
+## Authentication
+
+```csharp
+using Azure.AI.Agents.Persistent;
+using Azure.Identity;
+
+var projectEndpoint = Environment.GetEnvironmentVariable("PROJECT_ENDPOINT");
+PersistentAgentsClient client = new(projectEndpoint, new DefaultAzureCredential());
+```
+
+## Client Hierarchy
+
+```
+PersistentAgentsClient
+├── Administration  → Agent CRUD operations
+├── Threads         → Thread management
+├── Messages        → Message operations
+├── Runs            → Run execution and streaming
+├── Files           → File upload/download
+└── VectorStores    → Vector store management
+```
+
+## Core Workflow
+
+### 1. Create Agent
+
+```csharp
+var modelDeploymentName = Environment.GetEnvironmentVariable("MODEL_DEPLOYMENT_NAME");
+
+PersistentAgent agent = await client.Administration.CreateAgentAsync(
+    model: modelDeploymentName,
+    name: "Math Tutor",
+    instructions: "You are a personal math tutor. Write and run code to answer math questions.",
+    tools: [new CodeInterpreterToolDefinition()]
+);
+```
+
+### 2. Create Thread and Message
+
+```csharp
+// Create thread
+PersistentAgentThread thread = await client.Threads.CreateThreadAsync();
+
+// Create message
+await client.Messages.CreateMessageAsync(
+    thread.Id,
+    MessageRole.User,
+    "I need to solve the equation `3x + 11 = 14`. Can you help me?"
+);
+```
+
+### 3. Run Agent (Polling)
+
+```csharp
+// Create run
+ThreadRun run = await client.Runs.CreateRunAsync(
+    thread.Id,
+    agent.Id,
+    additionalInstructions: "Please address the user as Jane Doe."
+);
+
+// Poll for completion
+do
+{
+    await Task.Delay(TimeSpan.FromMilliseconds(500));
+    run = await client.Runs.GetRunAsync(thread.Id, run.Id);
+}
+while (run.Status == RunStatus.Queued || run.Status == RunStatus.InProgress);
+
+// Retrieve messages
+await foreach (PersistentThreadMessage message in client.Messages.GetMessagesAsync(
+    threadId: thread.Id, 
+    order: ListSortOrder.Ascending))
+{
+    Console.Write($"{message.Role}: ");
+    foreach (MessageContent content in message.ContentItems)
+    {
+        if (content is MessageTextContent textContent)
+            Console.WriteLine(textContent.Text);
+    }
+}
+```
+
+### 4. Streaming Response
+
+```csharp
+AsyncCollectionResult<StreamingUpdate> stream = client.Runs.CreateRunStreamingAsync(
+    thread.Id, 
+    agent.Id
+);
+
+await foreach (StreamingUpdate update in stream)
+{
+    if (update.UpdateKind == StreamingUpdateReason.RunCreated)
+    {
+        Console.WriteLine("--- Run started! ---");
+    }
+    else if (update is MessageContentUpdate contentUpdate)
+    {
+        Console.Write(contentUpdate.Text);
+    }
+    else if (update.UpdateKind == StreamingUpdateReason.RunCompleted)
+    {
+        Console.WriteLine("\n--- Run completed! ---");
+    }
+}
+```
+
+### 5. Function Calling
+
+```csharp
+// Define function tool
+FunctionToolDefinition weatherTool = new(
+    name: "getCurrentWeather",
+    description: "Gets the current weather at a location.",
+    parameters: BinaryData.FromObjectAsJson(new
+    {
+        Type = "object",
+        Properties = new
+        {
+            Location = new { Type = "string", Description = "City and state, e.g. San Francisco, CA" },
+            Unit = new { Type = "string", Enum = new[] { "c", "f" } }
+        },
+        Required = new[] { "location" }
+    }, new JsonSerializerOptions { PropertyNamingPolicy = JsonNamingPolicy.CamelCase })
+);
+
+// Create agent with function
+PersistentAgent agent = await client.Administration.CreateAgentAsync(
+    model: modelDeploymentName,
+    name: "Weather Bot",
+    instructions: "You are a weather bot.",
+    tools: [weatherTool]
+);
+
+// Handle function calls during polling
+do
+{
+    await Task.Delay(500);
+    run = await client.Runs.GetRunAsync(thread.Id, run.Id);
+
+    if (run.Status == RunStatus.RequiresAction 
+        && run.RequiredAction is SubmitToolOutputsAction submitAction)
+    {
+        List<ToolOutput> outputs = [];
+        foreach (RequiredToolCall toolCall in submitAction.ToolCalls)
+        {
+            if (toolCall is RequiredFunctionToolCall funcCall)
+            {
+                // Execute function and get result
+                string result = ExecuteFunction(funcCall.Name, funcCall.Arguments);
+                outputs.Add(new ToolOutput(toolCall, result));
+            }
+        }
+        run = await client.Runs.SubmitToolOutputsToRunAsync(run, outputs, toolApprovals: null);
+    }
+}
+while (run.Status == RunStatus.Queued || run.Status == RunStatus.InProgress);
+```
+
+### 6. File Search with Vector Store
+
+```csharp
+// Upload file
+PersistentAgentFileInfo file = await client.Files.UploadFileAsync(
+    filePath: "document.txt",
+    purpose: PersistentAgentFilePurpose.Agents
+);
+
+// Create vector store
+PersistentAgentsVectorStore vectorStore = await client.VectorStores.CreateVectorStoreAsync(
+    fileIds: [file.Id],
+    name: "my_vector_store"
+);
+
+// Create file search resource
+FileSearchToolResource fileSearchResource = new();
+fileSearchResource.VectorStoreIds.Add(vectorStore.Id);
+
+// Create agent with file search
+PersistentAgent agent = await client.Administration.CreateAgentAsync(
+    model: modelDeploymentName,
+    name: "Document Assistant",
+    instructions: "You help users find information in documents.",
+    tools: [new FileSearchToolDefinition()],
+    toolResources: new ToolResources { FileSearch = fileSearchResource }
+);
+```
+
+### 7. Bing Grounding
+
+```csharp
+var bingConnectionId = Environment.GetEnvironmentVariable("AZURE_BING_CONNECTION_ID");
+
+BingGroundingToolDefinition bingTool = new(
+    new BingGroundingSearchToolParameters(
+        [new BingGroundingSearchConfiguration(bingConnectionId)]
+    )
+);
+
+PersistentAgent agent = await client.Administration.CreateAgentAsync(
+    model: modelDeploymentName,
+    name: "Search Agent",
+    instructions: "Use Bing to answer questions about current events.",
+    tools: [bingTool]
+);
+```
+
+### 8. Azure AI Search
+
+```csharp
+AzureAISearchToolResource searchResource = new(
+    connectionId: searchConnectionId,
+    indexName: "my_index",
+    topK: 5,
+    filter: "category eq 'documentation'",
+    queryType: AzureAISearchQueryType.Simple
+);
+
+PersistentAgent agent = await client.Administration.CreateAgentAsync(
+    model: modelDeploymentName,
+    name: "Search Agent",
+    instructions: "Search the documentation index to answer questions.",
+    tools: [new AzureAISearchToolDefinition()],
+    toolResources: new ToolResources { AzureAISearch = searchResource }
+);
+```
+
+### 9. Cleanup
+
+```csharp
+await client.Threads.DeleteThreadAsync(thread.Id);
+await client.Administration.DeleteAgentAsync(agent.Id);
+await client.VectorStores.DeleteVectorStoreAsync(vectorStore.Id);
+await client.Files.DeleteFileAsync(file.Id);
+```
+
+## Available Tools
+
+| Tool | Class | Purpose |
+|------|-------|---------|
+| Code Interpreter | `CodeInterpreterToolDefinition` | Execute Python code, generate visualizations |
+| File Search | `FileSearchToolDefinition` | Search uploaded files via vector stores |
+| Function Calling | `FunctionToolDefinition` | Call custom functions |
+| Bing Grounding | `BingGroundingToolDefinition` | Web search via Bing |
+| Azure AI Search | `AzureAISearchToolDefinition` | Search Azure AI Search indexes |
+| OpenAPI | `OpenApiToolDefinition` | Call external APIs via OpenAPI spec |
+| Azure Functions | `AzureFunctionToolDefinition` | Invoke Azure Functions |
+| MCP | `MCPToolDefinition` | Model Context Protocol tools |
+| SharePoint | `SharepointToolDefinition` | Access SharePoint content |
+| Microsoft Fabric | `MicrosoftFabricToolDefinition` | Access Fabric data |
+
+## Streaming Update Types
+
+| Update Type | Description |
+|-------------|-------------|
+| `StreamingUpdateReason.RunCreated` | Run started |
+| `StreamingUpdateReason.RunInProgress` | Run processing |
+| `StreamingUpdateReason.RunCompleted` | Run finished |
+| `StreamingUpdateReason.RunFailed` | Run errored |
+| `MessageContentUpdate` | Text content chunk |
+| `RunStepUpdate` | Step status change |
+
+## Key Types Reference
+
+| Type | Purpose |
+|------|---------|
+| `PersistentAgentsClient` | Main entry point |
+| `PersistentAgent` | Agent with model, instructions, tools |
+| `PersistentAgentThread` | Conversation thread |
+| `PersistentThreadMessage` | Message in thread |
+| `ThreadRun` | Execution of agent against thread |
+| `RunStatus` | Queued, InProgress, RequiresAction, Completed, Failed |
+| `ToolResources` | Combined tool resources |
+| `ToolOutput` | Function call response |
+
+## Best Practices
+
+1. **Always dispose clients** — Use `using` statements or explicit disposal
+2. **Poll with appropriate delays** — 500ms recommended between status checks
+3. **Clean up resources** — Delete threads and agents when done
+4. **Handle all run statuses** — Check for `RequiresAction`, `Failed`, `Cancelled`
+5. **Use streaming for real-time UX** — Better user experience than polling
+6. **Store IDs not objects** — Reference agents/threads by ID
+7. **Use async methods** — All operations should be async
+
+## Error Handling
+
+```csharp
+using Azure;
+
+try
+{
+    var agent = await client.Administration.CreateAgentAsync(...);
+}
+catch (RequestFailedException ex) when (ex.Status == 404)
+{
+    Console.WriteLine("Resource not found");
+}
+catch (RequestFailedException ex)
+{
+    Console.WriteLine($"Error: {ex.Status} - {ex.ErrorCode}: {ex.Message}");
+}
+```
+
+## Related SDKs
+
+| SDK | Purpose | Install |
+|-----|---------|---------|
+| `Azure.AI.Agents.Persistent` | Low-level agents (this SDK) | `dotnet add package Azure.AI.Agents.Persistent` |
+| `Azure.AI.Projects` | High-level project client | `dotnet add package Azure.AI.Projects` |
+
+## Reference Links
+
+| Resource | URL |
+|----------|-----|
+| NuGet Package | https://www.nuget.org/packages/Azure.AI.Agents.Persistent |
+| API Reference | https://learn.microsoft.com/dotnet/api/azure.ai.agents.persistent |
+| GitHub Source | https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Agents.Persistent |
+| Samples | https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Agents.Persistent/samples |

skills/azure-ai-agents-persistent-java/SKILL.md

@@ -0,0 +1,137 @@
+---
+name: azure-ai-agents-persistent-java
+description: |
+  Azure AI Agents Persistent SDK for Java. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools.
+  Triggers: "PersistentAgentsClient", "persistent agents java", "agent threads java", "agent runs java", "streaming agents java".
+package: com.azure:azure-ai-agents-persistent
+---
+
+# Azure AI Agents Persistent SDK for Java
+
+Low-level SDK for creating and managing persistent AI agents with threads, messages, runs, and tools.
+
+## Installation
+
+```xml
+<dependency>
+    <groupId>com.azure</groupId>
+    <artifactId>azure-ai-agents-persistent</artifactId>
+    <version>1.0.0-beta.1</version>
+</dependency>
+```
+
+## Environment Variables
+
+```bash
+PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project>
+MODEL_DEPLOYMENT_NAME=gpt-4o-mini
+```
+
+## Authentication
+
+```java
+import com.azure.ai.agents.persistent.PersistentAgentsClient;
+import com.azure.ai.agents.persistent.PersistentAgentsClientBuilder;
+import com.azure.identity.DefaultAzureCredentialBuilder;
+
+String endpoint = System.getenv("PROJECT_ENDPOINT");
+PersistentAgentsClient client = new PersistentAgentsClientBuilder()
+    .endpoint(endpoint)
+    .credential(new DefaultAzureCredentialBuilder().build())
+    .buildClient();
+```
+
+## Key Concepts
+
+The Azure AI Agents Persistent SDK provides a low-level API for managing persistent agents that can be reused across sessions.
+
+### Client Hierarchy
+
+| Client | Purpose |
+|--------|---------|
+| `PersistentAgentsClient` | Sync client for agent operations |
+| `PersistentAgentsAsyncClient` | Async client for agent operations |
+
+## Core Workflow
+
+### 1. Create Agent
+
+```java
+// Create agent with tools
+PersistentAgent agent = client.createAgent(
+    modelDeploymentName,
+    "Math Tutor",
+    "You are a personal math tutor."
+);
+```
+
+### 2. Create Thread
+
+```java
+PersistentAgentThread thread = client.createThread();
+```
+
+### 3. Add Message
+
+```java
+client.createMessage(
+    thread.getId(),
+    MessageRole.USER,
+    "I need help with equations."
+);
+```
+
+### 4. Run Agent
+
+```java
+ThreadRun run = client.createRun(thread.getId(), agent.getId());
+
+// Poll for completion
+while (run.getStatus() == RunStatus.QUEUED || run.getStatus() == RunStatus.IN_PROGRESS) {
+    Thread.sleep(500);
+    run = client.getRun(thread.getId(), run.getId());
+}
+```
+
+### 5. Get Response
+
+```java
+PagedIterable<PersistentThreadMessage> messages = client.listMessages(thread.getId());
+for (PersistentThreadMessage message : messages) {
+    System.out.println(message.getRole() + ": " + message.getContent());
+}
+```
+
+### 6. Cleanup
+
+```java
+client.deleteThread(thread.getId());
+client.deleteAgent(agent.getId());
+```
+
+## Best Practices
+
+1. **Use DefaultAzureCredential** for production authentication
+2. **Poll with appropriate delays** — 500ms recommended between status checks
+3. **Clean up resources** — Delete threads and agents when done
+4. **Handle all run statuses** — Check for RequiresAction, Failed, Cancelled
+5. **Use async client** for better throughput in high-concurrency scenarios
+
+## Error Handling
+
+```java
+import com.azure.core.exception.HttpResponseException;
+
+try {
+    PersistentAgent agent = client.createAgent(modelName, name, instructions);
+} catch (HttpResponseException e) {
+    System.err.println("Error: " + e.getResponse().getStatusCode() + " - " + e.getMessage());
+}
+```
+
+## Reference Links
+
+| Resource | URL |
+|----------|-----|
+| Maven Package | https://central.sonatype.com/artifact/com.azure/azure-ai-agents-persistent |
+| GitHub Source | https://github.com/Azure/azure-sdk-for-java/tree/main/sdk/ai/azure-ai-agents-persistent |

skills/azure-ai-contentsafety-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-ai-contentsafety-ts
 description: Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.
-package: @azure-rest/ai-content-safety
+package: "@azure-rest/ai-content-safety"
 ---
 
 # Azure AI Content Safety REST SDK for TypeScript

skills/azure-ai-document-intelligence-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-ai-document-intelligence-ts
 description: Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.
-package: @azure-rest/ai-document-intelligence
+package: "@azure-rest/ai-document-intelligence"
 ---
 
 # Azure Document Intelligence REST SDK for TypeScript

skills/azure-ai-projects-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-ai-projects-ts
 description: Build AI applications using Azure AI Projects SDK for JavaScript (@azure/ai-projects). Use when working with Foundry project clients, agents, connections, deployments, datasets, indexes, evaluations, or getting OpenAI clients.
-package: @azure/ai-projects
+package: "@azure/ai-projects"
 ---
 
 # Azure AI Projects SDK for TypeScript

skills/azure-ai-translation-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-ai-translation-ts
 description: Build translation applications using Azure Translation SDKs for JavaScript (@azure-rest/ai-translation-text, @azure-rest/ai-translation-document). Use when implementing text translation, transliteration, language detection, or batch document translation.
-package: @azure-rest/ai-translation-text, @azure-rest/ai-translation-document
+package: "@azure-rest/ai-translation-text, @azure-rest/ai-translation-document"
 ---
 
 # Azure Translation SDKs for TypeScript

skills/azure-ai-voicelive-ts/SKILL.md

@@ -2,7 +2,7 @@
 name: azure-ai-voicelive-ts
 description: |
   Azure AI Voice Live SDK for JavaScript/TypeScript. Build real-time voice AI applications with bidirectional WebSocket communication. Use for voice assistants, conversational AI, real-time speech-to-speech, and voice-enabled chatbots in Node.js or browser environments. Triggers: "voice live", "real-time voice", "VoiceLiveClient", "VoiceLiveSession", "voice assistant TypeScript", "bidirectional audio", "speech-to-speech JavaScript".
-package: @azure/ai-voicelive
+package: "@azure/ai-voicelive"
 ---
 
 # @azure/ai-voicelive (JavaScript/TypeScript)

skills/azure-appconfiguration-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-appconfiguration-ts
 description: Build applications using Azure App Configuration SDK for JavaScript (@azure/app-configuration). Use when working with configuration settings, feature flags, Key Vault references, dynamic refresh, or centralized configuration management.
-package: @azure/app-configuration
+package: "@azure/app-configuration"
 ---
 
 # Azure App Configuration SDK for TypeScript

skills/azure-cosmos-ts/SKILL.md

@@ -2,7 +2,7 @@
 name: azure-cosmos-ts
 description: |
   Azure Cosmos DB JavaScript/TypeScript SDK (@azure/cosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: "Cosmos DB", "@azure/cosmos", "CosmosClient", "document CRUD", "NoSQL queries", "bulk operations", "partition key", "container.items".
-package: @azure/cosmos
+package: "@azure/cosmos"
 ---
 
 # @azure/cosmos (TypeScript/JavaScript)

skills/azure-eventhub-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-eventhub-ts
 description: Build event streaming applications using Azure Event Hubs SDK for JavaScript (@azure/event-hubs). Use when implementing high-throughput event ingestion, real-time analytics, IoT telemetry, or event-driven architectures with partitioned consumers.
-package: @azure/event-hubs
+package: "@azure/event-hubs"
 ---
 
 # Azure Event Hubs SDK for TypeScript

skills/azure-identity-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-identity-ts
 description: Authenticate to Azure services using Azure Identity SDK for JavaScript (@azure/identity). Use when configuring authentication with DefaultAzureCredential, managed identity, service principals, or interactive browser login.
-package: @azure/identity
+package: "@azure/identity"
 ---
 
 # Azure Identity SDK for TypeScript

skills/azure-keyvault-keys-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-keyvault-keys-ts
 description: Manage cryptographic keys using Azure Key Vault Keys SDK for JavaScript (@azure/keyvault-keys). Use when creating, encrypting/decrypting, signing, or rotating keys.
-package: @azure/keyvault-keys
+package: "@azure/keyvault-keys"
 ---
 
 # Azure Key Vault Keys SDK for TypeScript

skills/azure-keyvault-secrets-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-keyvault-secrets-ts
 description: Manage secrets using Azure Key Vault Secrets SDK for JavaScript (@azure/keyvault-secrets). Use when storing and retrieving application secrets or configuration values.
-package: @azure/keyvault-secrets
+package: "@azure/keyvault-secrets"
 ---
 
 # Azure Key Vault Secrets SDK for TypeScript

skills/azure-monitor-opentelemetry-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-monitor-opentelemetry-ts
 description: Instrument applications with Azure Monitor and OpenTelemetry for JavaScript (@azure/monitor-opentelemetry). Use when adding distributed tracing, metrics, and logs to Node.js applications with Application Insights.
-package: @azure/monitor-opentelemetry
+package: "@azure/monitor-opentelemetry"
 ---
 
 # Azure Monitor OpenTelemetry SDK for TypeScript

skills/azure-search-documents-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-search-documents-ts
 description: Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.
-package: @azure/search-documents
+package: "@azure/search-documents"
 ---
 
 # Azure AI Search SDK for TypeScript

skills/azure-servicebus-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-servicebus-ts
 description: Build messaging applications using Azure Service Bus SDK for JavaScript (@azure/service-bus). Use when implementing queues, topics/subscriptions, message sessions, dead-letter handling, or enterprise messaging patterns.
-package: @azure/service-bus
+package: "@azure/service-bus"
 ---
 
 # Azure Service Bus SDK for TypeScript

skills/azure-storage-blob-ts/SKILL.md

@@ -2,7 +2,7 @@
 name: azure-storage-blob-ts
 description: |
   Azure Blob Storage JavaScript/TypeScript SDK (@azure/storage-blob) for blob operations. Use for uploading, downloading, listing, and managing blobs and containers. Supports block blobs, append blobs, page blobs, SAS tokens, and streaming. Triggers: "blob storage", "@azure/storage-blob", "BlobServiceClient", "ContainerClient", "upload blob", "download blob", "SAS token", "block blob".
-package: @azure/storage-blob
+package: "@azure/storage-blob"
 ---
 
 # @azure/storage-blob (TypeScript/JavaScript)

skills/azure-storage-file-share-ts/SKILL.md

@@ -2,7 +2,7 @@
 name: azure-storage-file-share-ts
 description: |
   Azure File Share JavaScript/TypeScript SDK (@azure/storage-file-share) for SMB file share operations. Use for creating shares, managing directories, uploading/downloading files, and handling file metadata. Supports Azure Files SMB protocol scenarios. Triggers: "file share", "@azure/storage-file-share", "ShareServiceClient", "ShareClient", "SMB", "Azure Files".
-package: @azure/storage-file-share
+package: "@azure/storage-file-share"
 ---
 
 # @azure/storage-file-share (TypeScript/JavaScript)

skills/azure-storage-queue-ts/SKILL.md

@@ -2,7 +2,7 @@
 name: azure-storage-queue-ts
 description: |
   Azure Queue Storage JavaScript/TypeScript SDK (@azure/storage-queue) for message queue operations. Use for sending, receiving, peeking, and deleting messages in queues. Supports visibility timeout, message encoding, and batch operations. Triggers: "queue storage", "@azure/storage-queue", "QueueServiceClient", "QueueClient", "send message", "receive message", "dequeue", "visibility timeout".
-package: @azure/storage-queue
+package: "@azure/storage-queue"
 ---
 
 # @azure/storage-queue (TypeScript/JavaScript)

skills/azure-web-pubsub-ts/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: azure-web-pubsub-ts
 description: Build real-time messaging applications using Azure Web PubSub SDKs for JavaScript (@azure/web-pubsub, @azure/web-pubsub-client). Use when implementing WebSocket-based real-time features, pub/sub messaging, group chat, or live notifications.
-package: @azure/web-pubsub, @azure/web-pubsub-client
+package: "@azure/web-pubsub, @azure/web-pubsub-client"
 ---
 
 # Azure Web PubSub SDKs for TypeScript

skills/copilot-sdk/SKILL.md

@@ -0,0 +1,510 @@
+---
+name: copilot-sdk
+description: Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session management, custom tools, streaming, hooks, MCP servers, BYOK providers, session persistence, and custom agents. Requires GitHub Copilot CLI installed and a GitHub Copilot subscription (unless using BYOK).
+---
+
+# GitHub Copilot SDK
+
+Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.
+
+## Prerequisites
+
+- **GitHub Copilot CLI** installed and authenticated (`copilot --version` to verify)
+- **GitHub Copilot subscription** (Individual, Business, or Enterprise) — not required for BYOK
+- **Runtime:** Node.js 18+ / Python 3.8+ / Go 1.21+ / .NET 8.0+
+
+## Installation
+
+| Language | Package | Install |
+|----------|---------|---------|
+| Node.js | `@github/copilot-sdk` | `npm install @github/copilot-sdk` |
+| Python | `github-copilot-sdk` | `pip install github-copilot-sdk` |
+| Go | `github.com/github/copilot-sdk/go` | `go get github.com/github/copilot-sdk/go` |
+| .NET | `GitHub.Copilot.SDK` | `dotnet add package GitHub.Copilot.SDK` |
+
+---
+
+## Core Pattern: Client → Session → Message
+
+All SDK usage follows this pattern: create a client, create a session, send messages.
+
+### Node.js / TypeScript
+
+```typescript
+import { CopilotClient } from "@github/copilot-sdk";
+
+const client = new CopilotClient();
+const session = await client.createSession({ model: "gpt-4.1" });
+
+const response = await session.sendAndWait({ prompt: "What is 2 + 2?" });
+console.log(response?.data.content);
+
+await client.stop();
+```
+
+### Python
+
+```python
+import asyncio
+from copilot import CopilotClient
+
+async def main():
+    client = CopilotClient()
+    await client.start()
+    session = await client.create_session({"model": "gpt-4.1"})
+    response = await session.send_and_wait({"prompt": "What is 2 + 2?"})
+    print(response.data.content)
+    await client.stop()
+
+asyncio.run(main())
+```
+
+### Go
+
+```go
+client := copilot.NewClient(nil)
+if err := client.Start(ctx); err != nil { log.Fatal(err) }
+defer client.Stop()
+
+session, _ := client.CreateSession(ctx, &copilot.SessionConfig{Model: "gpt-4.1"})
+response, _ := session.SendAndWait(ctx, copilot.MessageOptions{Prompt: "What is 2 + 2?"})
+fmt.Println(*response.Data.Content)
+```
+
+### .NET
+
+```csharp
+await using var client = new CopilotClient();
+await using var session = await client.CreateSessionAsync(new SessionConfig { Model = "gpt-4.1" });
+var response = await session.SendAndWaitAsync(new MessageOptions { Prompt = "What is 2 + 2?" });
+Console.WriteLine(response?.Data.Content);
+```
+
+---
+
+## Streaming Responses
+
+Enable real-time output by setting `streaming: true` and subscribing to delta events.
+
+```typescript
+const session = await client.createSession({ model: "gpt-4.1", streaming: true });
+
+session.on("assistant.message_delta", (event) => {
+    process.stdout.write(event.data.deltaContent);
+});
+session.on("session.idle", () => console.log());
+
+await session.sendAndWait({ prompt: "Tell me a joke" });
+```
+
+**Python equivalent:**
+
+```python
+from copilot.generated.session_events import SessionEventType
+
+session = await client.create_session({"model": "gpt-4.1", "streaming": True})
+
+def handle_event(event):
+    if event.type == SessionEventType.ASSISTANT_MESSAGE_DELTA:
+        sys.stdout.write(event.data.delta_content)
+        sys.stdout.flush()
+
+session.on(handle_event)
+await session.send_and_wait({"prompt": "Tell me a joke"})
+```
+
+### Event Subscription
+
+| Method | Description |
+|--------|-------------|
+| `on(handler)` | Subscribe to all events; returns unsubscribe function |
+| `on(eventType, handler)` | Subscribe to specific event type (Node.js only) |
+
+---
+
+## Custom Tools
+
+Define tools that Copilot can call to extend its capabilities.
+
+### Node.js
+
+```typescript
+import { CopilotClient, defineTool } from "@github/copilot-sdk";
+
+const getWeather = defineTool("get_weather", {
+    description: "Get the current weather for a city",
+    parameters: {
+        type: "object",
+        properties: { city: { type: "string", description: "The city name" } },
+        required: ["city"],
+    },
+    handler: async ({ city }) => ({ city, temperature: "72°F", condition: "sunny" }),
+});
+
+const session = await client.createSession({
+    model: "gpt-4.1",
+    tools: [getWeather],
+});
+```
+
+### Python
+
+```python
+from copilot.tools import define_tool
+from pydantic import BaseModel, Field
+
+class GetWeatherParams(BaseModel):
+    city: str = Field(description="The city name")
+
+@define_tool(description="Get the current weather for a city")
+async def get_weather(params: GetWeatherParams) -> dict:
+    return {"city": params.city, "temperature": "72°F", "condition": "sunny"}
+
+session = await client.create_session({"model": "gpt-4.1", "tools": [get_weather]})
+```
+
+### Go
+
+```go
+type WeatherParams struct {
+    City string `json:"city" jsonschema:"The city name"`
+}
+
+getWeather := copilot.DefineTool("get_weather", "Get weather for a city",
+    func(params WeatherParams, inv copilot.ToolInvocation) (WeatherResult, error) {
+        return WeatherResult{City: params.City, Temperature: "72°F"}, nil
+    },
+)
+
+session, _ := client.CreateSession(ctx, &copilot.SessionConfig{
+    Model: "gpt-4.1",
+    Tools: []copilot.Tool{getWeather},
+})
+```
+
+### .NET
+
+```csharp
+var getWeather = AIFunctionFactory.Create(
+    ([Description("The city name")] string city) => new { city, temperature = "72°F" },
+    "get_weather", "Get the current weather for a city");
+
+await using var session = await client.CreateSessionAsync(new SessionConfig {
+    Model = "gpt-4.1", Tools = [getWeather],
+});
+```
+
+---
+
+## Hooks
+
+Intercept and customize session behavior at key lifecycle points.
+
+| Hook | Trigger | Use Case |
+|------|---------|----------|
+| `onPreToolUse` | Before tool executes | Permission control, argument modification |
+| `onPostToolUse` | After tool executes | Result transformation, logging |
+| `onUserPromptSubmitted` | User sends message | Prompt modification, filtering |
+| `onSessionStart` | Session begins | Add context, configure session |
+| `onSessionEnd` | Session ends | Cleanup, analytics |
+| `onErrorOccurred` | Error happens | Custom error handling, retry logic |
+
+### Example: Tool Permission Control
+
+```typescript
+const session = await client.createSession({
+    hooks: {
+        onPreToolUse: async (input) => {
+            if (["shell", "bash"].includes(input.toolName)) {
+                return { permissionDecision: "deny", permissionDecisionReason: "Shell access not permitted" };
+            }
+            return { permissionDecision: "allow" };
+        },
+    },
+});
+```
+
+### Pre-Tool Use Output
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `permissionDecision` | `"allow"` \| `"deny"` \| `"ask"` | Whether to allow the tool call |
+| `permissionDecisionReason` | string | Explanation for deny/ask |
+| `modifiedArgs` | object | Modified arguments to pass |
+| `additionalContext` | string | Extra context for conversation |
+| `suppressOutput` | boolean | Hide tool output from conversation |
+
+---
+
+## MCP Server Integration
+
+Connect to MCP servers for pre-built tool capabilities.
+
+### Remote HTTP Server
+
+```typescript
+const session = await client.createSession({
+    mcpServers: {
+        github: { type: "http", url: "https://api.githubcopilot.com/mcp/" },
+    },
+});
+```
+
+### Local Stdio Server
+
+```typescript
+const session = await client.createSession({
+    mcpServers: {
+        filesystem: {
+            type: "local",
+            command: "npx",
+            args: ["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"],
+            tools: ["*"],
+        },
+    },
+});
+```
+
+### MCP Config Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `type` | `"local"` \| `"http"` | Server transport type |
+| `command` | string | Executable path (local) |
+| `args` | string[] | Command arguments (local) |
+| `url` | string | Server URL (http) |
+| `tools` | string[] | `["*"]` or specific tool names |
+| `env` | object | Environment variables |
+| `cwd` | string | Working directory (local) |
+| `timeout` | number | Timeout in milliseconds |
+
+---
+
+## Authentication
+
+### Methods (Priority Order)
+
+1. **Explicit token** — `githubToken` in constructor
+2. **Environment variables** — `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN`
+3. **Stored OAuth** — From `copilot auth login`
+4. **GitHub CLI** — `gh auth` credentials
+
+### Programmatic Token
+
+```typescript
+const client = new CopilotClient({ githubToken: process.env.GITHUB_TOKEN });
+```
+
+### BYOK (Bring Your Own Key)
+
+Use your own API keys — no Copilot subscription required.
+
+```typescript
+const session = await client.createSession({
+    model: "gpt-5.2-codex",
+    provider: {
+        type: "openai",
+        baseUrl: "https://your-resource.openai.azure.com/openai/v1/",
+        wireApi: "responses",
+        apiKey: process.env.FOUNDRY_API_KEY,
+    },
+});
+```
+
+| Provider | Type | Notes |
+|----------|------|-------|
+| OpenAI | `"openai"` | OpenAI API and compatible endpoints |
+| Azure OpenAI | `"azure"` | Native Azure endpoints (don't include `/openai/v1`) |
+| Azure AI Foundry | `"openai"` | OpenAI-compatible Foundry endpoints |
+| Anthropic | `"anthropic"` | Claude models |
+| Ollama | `"openai"` | Local models, no API key needed |
+
+**Wire API:** Use `"responses"` for GPT-5 series, `"completions"` (default) for others.
+
+---
+
+## Session Persistence
+
+Resume sessions across restarts by providing your own session ID.
+
+```typescript
+// Create with explicit ID
+const session = await client.createSession({
+    sessionId: "user-123-task-456",
+    model: "gpt-4.1",
+});
+
+// Resume later
+const resumed = await client.resumeSession("user-123-task-456");
+await resumed.sendAndWait({ prompt: "What did we discuss?" });
+```
+
+**Session management:**
+
+```typescript
+const sessions = await client.listSessions();          // List all
+await client.deleteSession("user-123-task-456");       // Delete
+await session.destroy();                                // Destroy active
+```
+
+**BYOK sessions:** Must re-provide `provider` config on resume (keys are not persisted).
+
+### Infinite Sessions
+
+For long-running workflows that may exceed context limits:
+
+```typescript
+const session = await client.createSession({
+    infiniteSessions: {
+        enabled: true,
+        backgroundCompactionThreshold: 0.80,
+        bufferExhaustionThreshold: 0.95,
+    },
+});
+```
+
+---
+
+## Custom Agents
+
+Define specialized AI personas:
+
+```typescript
+const session = await client.createSession({
+    customAgents: [{
+        name: "pr-reviewer",
+        displayName: "PR Reviewer",
+        description: "Reviews pull requests for best practices",
+        prompt: "You are an expert code reviewer. Focus on security, performance, and maintainability.",
+    }],
+});
+```
+
+---
+
+## System Message
+
+Control AI behavior and personality:
+
+```typescript
+const session = await client.createSession({
+    systemMessage: { content: "You are a helpful assistant. Always be concise." },
+});
+```
+
+---
+
+## Skills Integration
+
+Load skill directories to extend Copilot's capabilities:
+
+```typescript
+const session = await client.createSession({
+    skillDirectories: ["./skills/code-review", "./skills/documentation"],
+    disabledSkills: ["experimental-feature"],
+});
+```
+
+---
+
+## Permission & Input Handlers
+
+Handle tool permissions and user input requests programmatically:
+
+```typescript
+const session = await client.createSession({
+    onPermissionRequest: async (request) => {
+        // Auto-approve git commands only
+        if (request.kind === "shell") {
+            return { approved: request.command.startsWith("git") };
+        }
+        return { approved: true };
+    },
+    onUserInputRequest: async (request) => {
+        // Handle ask_user tool calls
+        return { response: "yes" };
+    },
+});
+```
+
+---
+
+## External CLI Server
+
+Connect to a separately running CLI instead of auto-managing the process:
+
+```bash
+copilot --headless --port 4321
+```
+
+```typescript
+const client = new CopilotClient({ cliUrl: "localhost:4321" });
+```
+
+---
+
+## Client Configuration
+
+| Option | Type | Description |
+|--------|------|-------------|
+| `cliPath` | string | Path to Copilot CLI executable |
+| `cliUrl` | string | URL of external CLI server |
+| `githubToken` | string | GitHub token for auth |
+| `useLoggedInUser` | boolean | Use stored CLI credentials (default: true) |
+| `logLevel` | string | `"none"` \| `"error"` \| `"warning"` \| `"info"` \| `"debug"` |
+| `autoRestart` | boolean | Auto-restart CLI on crash (default: true) |
+| `useStdio` | boolean | Use stdio transport (default: true) |
+
+## Session Configuration
+
+| Option | Type | Description |
+|--------|------|-------------|
+| `model` | string | Model to use (e.g., `"gpt-4.1"`) |
+| `sessionId` | string | Custom ID for resumable sessions |
+| `streaming` | boolean | Enable streaming responses |
+| `tools` | Tool[] | Custom tools |
+| `mcpServers` | object | MCP server configurations |
+| `hooks` | object | Session hooks |
+| `provider` | object | BYOK provider config |
+| `customAgents` | object[] | Custom agent definitions |
+| `systemMessage` | object | System message override |
+| `skillDirectories` | string[] | Directories to load skills from |
+| `disabledSkills` | string[] | Skills to disable |
+| `reasoningEffort` | string | Reasoning effort level |
+| `availableTools` | string[] | Restrict available tools |
+| `excludedTools` | string[] | Exclude specific tools |
+| `infiniteSessions` | object | Auto-compaction config |
+| `workingDirectory` | string | Working directory |
+
+---
+
+## Debugging
+
+Enable debug logging to troubleshoot issues:
+
+```typescript
+const client = new CopilotClient({ logLevel: "debug" });
+```
+
+**Common issues:**
+- `CLI not found` → Install CLI or set `cliPath`
+- `Not authenticated` → Run `copilot auth login` or provide `githubToken`
+- `Session not found` → Don't use session after `destroy()`
+- `Connection refused` → Check CLI process, enable `autoRestart`
+
+---
+
+## Key API Summary
+
+| Language | Client | Session Create | Send | Stop |
+|----------|--------|---------------|------|------|
+| Node.js | `new CopilotClient()` | `client.createSession()` | `session.sendAndWait()` | `client.stop()` |
+| Python | `CopilotClient()` | `client.create_session()` | `session.send_and_wait()` | `client.stop()` |
+| Go | `copilot.NewClient(nil)` | `client.CreateSession()` | `session.SendAndWait()` | `client.Stop()` |
+| .NET | `new CopilotClient()` | `client.CreateSessionAsync()` | `session.SendAndWaitAsync()` | `client.DisposeAsync()` |
+
+## References
+
+- [GitHub Copilot SDK](https://github.com/github/copilot-sdk)
+- [Copilot CLI Installation](https://docs.github.com/en/copilot/how-tos/set-up/install-copilot-cli)
+- [MCP Protocol Specification](https://modelcontextprotocol.io)

skills/crypto-bd-agent/SKILL.md

@@ -0,0 +1,248 @@
+---
+name: crypto-bd-agent
+description: >
+  Autonomous crypto business development patterns — multi-chain token discovery,
+  100-point scoring with wallet forensics, x402 micropayments, ERC-8004 on-chain
+  identity, LLM cascade routing, and pipeline automation for CEX/DEX listing
+  acquisition. Use when building AI agents for crypto BD, token evaluation,
+  exchange listing outreach, or autonomous commerce with payment protocols.
+risk: safe
+source: community
+tags:
+  - crypto
+  - business-development
+  - token-scanning
+  - x402
+  - erc-8004
+  - autonomous-agent
+  - solana
+  - ethereum
+  - wallet-forensics
+---
+
+# Crypto BD Agent — Autonomous Business Development for Exchanges
+
+> Production-tested patterns for building AI agents that autonomously discover,
+> evaluate, and acquire token listings for cryptocurrency exchanges.
+
+## Overview
+
+This skill teaches AI agents systematic crypto business development: discover
+promising tokens across chains, score them with a 100-point weighted system,
+verify safety through wallet forensics, and manage outreach pipelines with
+human-in-the-loop oversight.
+
+Built from production experience running Buzz BD Agent by SolCex Exchange —
+an autonomous agent on decentralized infrastructure with 13 intelligence
+sources, x402 micropayments, and dual-chain ERC-8004 registration.
+
+Reference implementation: https://github.com/buzzbysolcex/buzz-bd-agent
+
+## When to Use This Skill
+
+- Building an AI agent for crypto/DeFi business development
+- Creating token evaluation and scoring systems
+- Implementing multi-chain scanning pipelines
+- Setting up autonomous payment workflows (x402)
+- Designing wallet forensics for deployer analysis
+- Managing BD pipelines with human-in-the-loop
+- Registering agents on-chain via ERC-8004
+- Implementing cost-efficient LLM cascades
+
+## Do Not Use When
+
+- Building trading bots (this is BD, not trading)
+- Creating DeFi protocols or smart contracts
+- Non-crypto business development
+
+---
+
+## Architecture
+```text
+Intelligence Sources (Free + Paid via x402)
+        |
+        v
+  Scoring Engine (100-point weighted)
+        |
+        v
+  Wallet Forensics (deployer verification)
+        |
+        v
+  Pipeline Manager (10-stage tracked)
+        |
+        v
+  Outreach Drafts → Human Approval → Send
+```
+
+### LLM Cascade Pattern
+
+Route tasks to the cheapest model that handles them correctly:
+```text
+Fast/cheap model (routine: tweets, forum posts, pipeline updates)
+    ↓ fallback on quality issues
+Free API models (scanning, initial scoring, system tasks)
+    ↓ fallback
+Mid-tier model (outreach drafts, deeper analysis)
+    ↓ fallback
+Premium model (strategy, wallet forensics, final outreach)
+```
+
+Run a quality gate (10+ test cases) before promoting any new model.
+
+---
+
+## 1. Intelligence Gathering
+
+### Free-First Principle
+Always exhaust free data before paying. Target: $0/day for 90% of intelligence.
+
+### Recommended Source Categories
+
+| Category | What to Track | Example Sources |
+|----------|--------------|-----------------|
+| DEX Data | Prices, liquidity, pairs, chain coverage | DexScreener, GeckoTerminal |
+| AI Momentum | Trending tokens, catalysts | AIXBT or similar trackers |
+| Smart Money | VC follows, KOL accumulation | leak.me, Nansen free, Arkham |
+| Contract Safety | Rug scores, LP lock, authorities | RugCheck |
+| Wallet Forensics | Deployer analysis, fund flow | Helius (Solana), Allium (multi-chain) |
+| Web Scraping | Project verification, team info | Firecrawl or similar |
+| On-Chain Identity | Agent registration, trust signals | ATV Web3 Identity, ERC-8004 |
+| Community | Forum signals, ecosystem intel | Protocol forums |
+
+### Paid Sources (via x402 micropayments)
+- Whale alert services (~$0.10/call, 1-2x daily)
+- Breaking news aggregators (~$0.10/call, 2x daily)
+- Budget: ~$0.30/day = ~$9/month
+
+### Rules
+1. Cross-reference: every prospect needs 2+ independent source confirmations
+2. Multi-source cross-match gets +5 score bonus
+3. Track ROI per paid source — did this call produce a qualified prospect?
+4. Store insights in experience memory for continuous calibration
+
+---
+
+## 2. Token Scoring (100 Points)
+
+### Base Criteria
+
+| Factor | Weight | Scoring |
+|--------|--------|---------|
+| Liquidity | 25% | >$500K excellent, $200-500K good, $100K minimum |
+| Market Cap | 20% | >$10M excellent, $1-10M good, $500K-1M acceptable |
+| 24h Volume | 20% | >$1M excellent, $500K-1M good, $100-500K acceptable |
+| Social Metrics | 15% | Multi-platform active, 2+ platforms, 1 platform |
+| Token Age | 10% | Established >6mo, moderate 1-6mo, new <1mo |
+| Team Transparency | 10% | Doxxed + active, partial, anonymous |
+
+### Catalyst Adjustments
+
+Positive: Hackathon win +10, mainnet launch +10, major partnership +10,
+CEX listing +8, audit +8, multi-source match +5, whale signal +5,
+wallet verified +3-5, cross-chain deployer +3, net positive wallet +2.
+
+Negative: Rugpull association -15, exploit history -15, mixer funded AUTO REJECT,
+contract vulnerability -10, serial creator -5, already on major CEXs -5,
+team controversy -10, deployer dump >50% in 7 days -10 to -15.
+
+### Score Actions
+
+| Range | Action |
+|-------|--------|
+| 85-100 HOT | Immediate outreach + wallet forensics |
+| 70-84 Qualified | Priority queue + wallet forensics |
+| 50-69 Watch | Monitor 48 hours |
+| 0-49 Skip | Log only, no action |
+
+---
+
+## 3. Wallet Forensics
+
+Run on every token scoring 70+. This differentiates serious BD agents from
+simple scanners.
+
+### 5-Step Deployer Analysis
+
+1. **Funded-By** — Where did deployer get funds? (exchange, mixer, other wallet)
+2. **Balances** — Current holdings across chains
+3. **Transfer History** — Dump patterns, accumulation, LP activity
+4. **Identity** — ENS, social links, KYC indicators
+5. **Score Adjustment** — Apply flags based on findings
+
+### Wallet Flags
+
+| Flag | Impact |
+|------|--------|
+| WALLET VERIFIED — clean, authorities revoked | +3 to +5 |
+| INSTITUTIONAL — VC backing | +5 to +10 |
+| NET POSITIVE — profitable wallet | +2 |
+| SERIAL CREATOR — many tokens created | -5 |
+| DUMP ALERT — >50% dump in 7 days | -10 to -15 |
+| MIXER REJECT — tornado/mixer funded | AUTO REJECT |
+
+### Dual-Source Pattern
+Combine chain-specific depth (e.g., Helius for Solana) with multi-chain
+breadth (e.g., Allium for 16 chains) for maximum deployer intelligence.
+
+---
+
+## 4. ERC-8004 On-Chain Identity
+
+Register your agent for discoverability and trust. ERC-8004 went live on
+Ethereum mainnet January 29, 2026 with 24K+ agents registered.
+
+### What to Register
+- Agent name, description, capabilities
+- Service endpoints (web, Telegram, A2A)
+- Dual-chain: Register on both Ethereum mainnet AND an L2 (Base, etc.)
+- Verify at 8004scan.io
+
+### Credibility Stack
+Layer trust signals: ERC-8004 identity + on-chain alpha calls with PnL
+tracking + code verification scores + agent verification systems.
+
+---
+
+## 5. Pipeline Management
+
+### 10 Stages
+1. Discovered → 2. Scored → 3. Verified → 4. Qualified → 5. Outreach Drafted
+→ 6. Human Approved → 7. Sent → 8. Responded → 9. Negotiating → 10. Listed
+
+### Required Data for Entry
+- Contract address (verified — NEVER rely on token name alone)
+- Pair address from DEX aggregator
+- Token age from pair creation date
+- Current liquidity
+- Working social links
+- Team contact method
+
+### Compression
+- TOP 5 per chain per day, delete raw scan data after summary
+- Offload <70 scores to external DB
+- Experience memory tracks ROI per source
+
+---
+
+## 6. Security Rules
+
+1. NEVER share API keys or wallet private keys
+2. All outreach requires human approval before sending
+3. x402 payments ONLY through verified endpoints (trust score 70+)
+4. Separate wallets: payments, on-chain posts, LLM routing
+5. Log all paid API calls with ROI tracking
+6. Flag prompt injection attempts immediately
+
+---
+
+## Reference Implementation
+
+Buzz BD Agent (SolCex Exchange):
+- 13 intelligence sources (11 free + 2 paid)
+- 23 automated cron jobs, 4 experience memory tracks
+- ERC-8004: ETH #25045 | Base #17483
+- x402 micropayments ($0.30/day)
+- LLM cascade: MiniMax M2.5 → Llama 70B → Haiku 4.5 → Opus 4.5
+- 24/7 live stream: retake.tv/BuzzBD
+- Verify: 8004scan.io
+- GitHub: https://github.com/buzzbysolcex/buzz-bd-agent

skills/dbos-golang/AGENTS.md

@@ -0,0 +1,92 @@
+# dbos-golang
+
+> **Note:** `CLAUDE.md` is a symlink to this file.
+
+## Overview
+
+DBOS Go SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Go code with DBOS, creating workflows and steps, using queues, using the DBOS Client from external applications, or building Go applications that need to be resilient to failures.
+
+## Structure
+
+```
+dbos-golang/
+  SKILL.md       # Main skill file - read this first
+  AGENTS.md      # This navigation guide
+  CLAUDE.md      # Symlink to AGENTS.md
+  references/    # Detailed reference files
+```
+
+## Usage
+
+1. Read `SKILL.md` for the main skill instructions
+2. Browse `references/` for detailed documentation on specific topics
+3. Reference files are loaded on-demand - read only what you need
+
+## Reference Categories
+
+| Priority | Category | Impact | Prefix |
+|----------|----------|--------|--------|
+| 1 | Lifecycle | CRITICAL | `lifecycle-` |
+| 2 | Workflow | CRITICAL | `workflow-` |
+| 3 | Step | HIGH | `step-` |
+| 4 | Queue | HIGH | `queue-` |
+| 5 | Communication | MEDIUM | `comm-` |
+| 6 | Pattern | MEDIUM | `pattern-` |
+| 7 | Testing | LOW-MEDIUM | `test-` |
+| 8 | Client | MEDIUM | `client-` |
+| 9 | Advanced | LOW | `advanced-` |
+
+Reference files are named `{prefix}-{topic}.md` (e.g., `query-missing-indexes.md`).
+
+## Available References
+
+**Advanced** (`advanced-`):
+- `references/advanced-patching.md`
+- `references/advanced-versioning.md`
+
+**Client** (`client-`):
+- `references/client-enqueue.md`
+- `references/client-setup.md`
+
+**Communication** (`comm-`):
+- `references/comm-events.md`
+- `references/comm-messages.md`
+- `references/comm-streaming.md`
+
+**Lifecycle** (`lifecycle-`):
+- `references/lifecycle-config.md`
+
+**Pattern** (`pattern-`):
+- `references/pattern-debouncing.md`
+- `references/pattern-idempotency.md`
+- `references/pattern-scheduled.md`
+- `references/pattern-sleep.md`
+
+**Queue** (`queue-`):
+- `references/queue-basics.md`
+- `references/queue-concurrency.md`
+- `references/queue-deduplication.md`
+- `references/queue-listening.md`
+- `references/queue-partitioning.md`
+- `references/queue-priority.md`
+- `references/queue-rate-limiting.md`
+
+**Step** (`step-`):
+- `references/step-basics.md`
+- `references/step-concurrency.md`
+- `references/step-retries.md`
+
+**Testing** (`test-`):
+- `references/test-setup.md`
+
+**Workflow** (`workflow-`):
+- `references/workflow-background.md`
+- `references/workflow-constraints.md`
+- `references/workflow-control.md`
+- `references/workflow-determinism.md`
+- `references/workflow-introspection.md`
+- `references/workflow-timeout.md`
+
+---
+
+*29 reference files across 9 categories*

skills/dbos-golang/CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

skills/dbos-golang/SKILL.md

@@ -0,0 +1,133 @@
+---
+name: dbos-golang
+description: DBOS Go SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Go code with DBOS, creating workflows and steps, using queues, using the DBOS Client from external applications, or building Go applications that need to be resilient to failures.
+risk: safe
+source: https://docs.dbos.dev/
+license: MIT
+metadata:
+  author: dbos
+  version: "1.0.0"
+  organization: DBOS
+  date: February 2026
+  abstract: Comprehensive guide for building fault-tolerant Go applications with DBOS. Covers workflows, steps, queues, communication patterns, and best practices for durable execution.
+---
+
+# DBOS Go Best Practices
+
+Guide for building reliable, fault-tolerant Go applications with DBOS durable workflows.
+
+## When to Use
+
+Reference these guidelines when:
+- Adding DBOS to existing Go code
+- Creating workflows and steps
+- Using queues for concurrency control
+- Implementing workflow communication (events, messages, streams)
+- Configuring and launching DBOS applications
+- Using the DBOS Client from external applications
+- Testing DBOS applications
+
+## Rule Categories by Priority
+
+| Priority | Category | Impact | Prefix |
+|----------|----------|--------|--------|
+| 1 | Lifecycle | CRITICAL | `lifecycle-` |
+| 2 | Workflow | CRITICAL | `workflow-` |
+| 3 | Step | HIGH | `step-` |
+| 4 | Queue | HIGH | `queue-` |
+| 5 | Communication | MEDIUM | `comm-` |
+| 6 | Pattern | MEDIUM | `pattern-` |
+| 7 | Testing | LOW-MEDIUM | `test-` |
+| 8 | Client | MEDIUM | `client-` |
+| 9 | Advanced | LOW | `advanced-` |
+
+## Critical Rules
+
+### Installation
+
+Install the DBOS Go module:
+
+```bash
+go get github.com/dbos-inc/dbos-transact-golang/dbos@latest
+```
+
+### DBOS Configuration and Launch
+
+A DBOS application MUST create a context, register workflows, and launch before running any workflows:
+
+```go
+package main
+
+import (
+	"context"
+	"log"
+	"os"
+	"time"
+
+	"github.com/dbos-inc/dbos-transact-golang/dbos"
+)
+
+func main() {
+	ctx, err := dbos.NewDBOSContext(context.Background(), dbos.Config{
+		AppName:     "my-app",
+		DatabaseURL: os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+	})
+	if err != nil {
+		log.Fatal(err)
+	}
+	defer dbos.Shutdown(ctx, 30*time.Second)
+
+	dbos.RegisterWorkflow(ctx, myWorkflow)
+
+	if err := dbos.Launch(ctx); err != nil {
+		log.Fatal(err)
+	}
+}
+```
+
+### Workflow and Step Structure
+
+Workflows are comprised of steps. Any function performing complex operations or accessing external services must be run as a step using `dbos.RunAsStep`:
+
+```go
+func fetchData(ctx context.Context) (string, error) {
+	resp, err := http.Get("https://api.example.com/data")
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	body, _ := io.ReadAll(resp.Body)
+	return string(body), nil
+}
+
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	result, err := dbos.RunAsStep(ctx, fetchData, dbos.WithStepName("fetchData"))
+	if err != nil {
+		return "", err
+	}
+	return result, nil
+}
+```
+
+### Key Constraints
+
+- Do NOT start or enqueue workflows from within steps
+- Do NOT use uncontrolled goroutines to start workflows - use `dbos.RunWorkflow` with queues or `dbos.Go`/`dbos.Select` for concurrent steps
+- Workflows MUST be deterministic - non-deterministic operations go in steps
+- Do NOT modify global variables from workflows or steps
+- All workflows and queues MUST be registered before calling `Launch()`
+
+## How to Use
+
+Read individual rule files for detailed explanations and examples:
+
+```
+references/lifecycle-config.md
+references/workflow-determinism.md
+references/queue-concurrency.md
+```
+
+## References
+
+- https://docs.dbos.dev/
+- https://github.com/dbos-inc/dbos-transact-golang

skills/dbos-golang/references/_sections.md

@@ -0,0 +1,41 @@
+# Section Definitions
+
+This file defines the rule categories for DBOS Go best practices. Rules are automatically assigned to sections based on their filename prefix.
+
+---
+
+## 1. Lifecycle (lifecycle)
+**Impact:** CRITICAL
+**Description:** DBOS configuration, initialization, and launch patterns. Foundation for all DBOS applications.
+
+## 2. Workflow (workflow)
+**Impact:** CRITICAL
+**Description:** Workflow creation, determinism requirements, background execution, and workflow IDs.
+
+## 3. Step (step)
+**Impact:** HIGH
+**Description:** Step creation, retries, concurrent steps with Go/Select, and when to use steps vs workflows.
+
+## 4. Queue (queue)
+**Impact:** HIGH
+**Description:** Queue creation, concurrency limits, rate limiting, partitioning, and priority.
+
+## 5. Communication (comm)
+**Impact:** MEDIUM
+**Description:** Workflow events, messages, and streaming for inter-workflow communication.
+
+## 6. Pattern (pattern)
+**Impact:** MEDIUM
+**Description:** Common patterns including idempotency, scheduled workflows, debouncing, and durable sleep.
+
+## 7. Testing (test)
+**Impact:** LOW-MEDIUM
+**Description:** Testing DBOS applications with Go's testing package, mocks, and integration test setup.
+
+## 8. Client (client)
+**Impact:** MEDIUM
+**Description:** DBOS Client for interacting with DBOS from external applications.
+
+## 9. Advanced (advanced)
+**Impact:** LOW
+**Description:** Workflow versioning, patching, and safe code upgrades.

skills/dbos-golang/references/advanced-patching.md

@@ -0,0 +1,86 @@
+---
+title: Use Patching for Safe Workflow Upgrades
+impact: LOW
+impactDescription: Safely deploy breaking workflow changes without disrupting in-progress workflows
+tags: advanced, patching, upgrade, breaking-change
+---
+
+## Use Patching for Safe Workflow Upgrades
+
+Use `dbos.Patch` to safely deploy breaking changes to workflow code. Breaking changes alter which steps run or their order, which can cause recovery failures.
+
+**Incorrect (breaking change without patching):**
+
+```go
+// BEFORE: original workflow
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	result, _ := dbos.RunAsStep(ctx, foo, dbos.WithStepName("foo"))
+	_, _ = dbos.RunAsStep(ctx, bar, dbos.WithStepName("bar"))
+	return result, nil
+}
+
+// AFTER: breaking change - recovery will fail for in-progress workflows!
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	result, _ := dbos.RunAsStep(ctx, baz, dbos.WithStepName("baz")) // Changed step
+	_, _ = dbos.RunAsStep(ctx, bar, dbos.WithStepName("bar"))
+	return result, nil
+}
+```
+
+**Correct (using patch):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	useBaz, err := dbos.Patch(ctx, "use-baz")
+	if err != nil {
+		return "", err
+	}
+	var result string
+	if useBaz {
+		result, _ = dbos.RunAsStep(ctx, baz, dbos.WithStepName("baz")) // New workflows
+	} else {
+		result, _ = dbos.RunAsStep(ctx, foo, dbos.WithStepName("foo")) // Old workflows
+	}
+	_, _ = dbos.RunAsStep(ctx, bar, dbos.WithStepName("bar"))
+	return result, nil
+}
+```
+
+`dbos.Patch` returns `true` for new workflows and `false` for workflows that started before the patch.
+
+**Deprecating patches (after all old workflows complete):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	dbos.DeprecatePatch(ctx, "use-baz") // Always takes the new path
+	result, _ := dbos.RunAsStep(ctx, baz, dbos.WithStepName("baz"))
+	_, _ = dbos.RunAsStep(ctx, bar, dbos.WithStepName("bar"))
+	return result, nil
+}
+```
+
+**Removing patches (after all workflows using DeprecatePatch complete):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	result, _ := dbos.RunAsStep(ctx, baz, dbos.WithStepName("baz"))
+	_, _ = dbos.RunAsStep(ctx, bar, dbos.WithStepName("bar"))
+	return result, nil
+}
+```
+
+Lifecycle: `Patch()` → deploy → wait for old workflows → `DeprecatePatch()` → deploy → wait → remove patch entirely.
+
+**Required configuration** — patching must be explicitly enabled:
+
+```go
+ctx, _ := dbos.NewDBOSContext(context.Background(), dbos.Config{
+	AppName:        "my-app",
+	DatabaseURL:    os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+	EnablePatching: true, // Required for dbos.Patch and dbos.DeprecatePatch
+})
+```
+
+Without `EnablePatching: true`, calls to `dbos.Patch` and `dbos.DeprecatePatch` will fail.
+
+Reference: [Patching](https://docs.dbos.dev/golang/tutorials/upgrading-workflows#patching)

skills/dbos-golang/references/advanced-versioning.md

@@ -0,0 +1,62 @@
+---
+title: Use Versioning for Blue-Green Deployments
+impact: LOW
+impactDescription: Enables safe deployment of new code versions alongside old ones
+tags: advanced, versioning, blue-green, deployment
+---
+
+## Use Versioning for Blue-Green Deployments
+
+Set `ApplicationVersion` in configuration to tag workflows with a version. DBOS only recovers workflows matching the current application version, preventing code mismatches during recovery.
+
+**Incorrect (deploying new code that breaks in-progress workflows):**
+
+```go
+ctx, _ := dbos.NewDBOSContext(context.Background(), dbos.Config{
+	AppName:     "my-app",
+	DatabaseURL: os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+	// No version set - version auto-computed from binary hash
+	// Old workflows will be recovered with new code, which may break
+})
+```
+
+**Correct (versioned deployment):**
+
+```go
+ctx, _ := dbos.NewDBOSContext(context.Background(), dbos.Config{
+	AppName:            "my-app",
+	DatabaseURL:        os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+	ApplicationVersion: "2.0.0",
+})
+```
+
+By default, the application version is automatically computed from a SHA-256 hash of the executable binary. Set it explicitly for more control.
+
+**Blue-green deployment strategy:**
+
+1. Deploy new version (v2) alongside old version (v1)
+2. Direct new traffic to v2 processes
+3. Let v1 processes "drain" (complete in-progress workflows)
+4. Check for remaining v1 workflows:
+
+```go
+oldWorkflows, _ := dbos.ListWorkflows(ctx,
+	dbos.WithAppVersion("1.0.0"),
+	dbos.WithStatus([]dbos.WorkflowStatusType{dbos.WorkflowStatusPending}),
+)
+```
+
+5. Once all v1 workflows are complete, retire v1 processes
+
+**Fork to new version (for stuck workflows):**
+
+```go
+// Fork a workflow from a failed step to run on the new version
+handle, _ := dbos.ForkWorkflow[string](ctx, dbos.ForkWorkflowInput{
+	OriginalWorkflowID: workflowID,
+	StartStep:          failedStepID,
+	ApplicationVersion: "2.0.0",
+})
+```
+
+Reference: [Versioning](https://docs.dbos.dev/golang/tutorials/upgrading-workflows#versioning)

skills/dbos-golang/references/client-enqueue.md

@@ -0,0 +1,65 @@
+---
+title: Enqueue Workflows from External Applications
+impact: HIGH
+impactDescription: Enables external services to submit work to DBOS queues
+tags: client, enqueue, external, queue
+---
+
+## Enqueue Workflows from External Applications
+
+Use `client.Enqueue()` to submit workflows from outside your DBOS application. Since the Client runs externally, workflow and queue metadata must be specified explicitly by name.
+
+**Incorrect (trying to use RunWorkflow from external code):**
+
+```go
+// RunWorkflow requires a full DBOS context with registered workflows
+dbos.RunWorkflow(ctx, processTask, "data", dbos.WithQueue("myQueue"))
+```
+
+**Correct (using Client.Enqueue):**
+
+```go
+client, err := dbos.NewClient(context.Background(), dbos.ClientConfig{
+	DatabaseURL: os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+})
+if err != nil {
+	log.Fatal(err)
+}
+defer client.Shutdown(10 * time.Second)
+
+// Basic enqueue - specify workflow and queue by name
+handle, err := client.Enqueue("task_queue", "processTask", "task-data")
+if err != nil {
+	log.Fatal(err)
+}
+
+// Wait for the result
+result, err := handle.GetResult()
+```
+
+**Enqueue with options:**
+
+```go
+handle, err := client.Enqueue("task_queue", "processTask", "task-data",
+	dbos.WithEnqueueWorkflowID("custom-id"),
+	dbos.WithEnqueueDeduplicationID("unique-id"),
+	dbos.WithEnqueuePriority(10),
+	dbos.WithEnqueueTimeout(5*time.Minute),
+	dbos.WithEnqueueQueuePartitionKey("user-123"),
+	dbos.WithEnqueueApplicationVersion("2.0.0"),
+)
+```
+
+Enqueue options:
+- `WithEnqueueWorkflowID`: Custom workflow ID
+- `WithEnqueueDeduplicationID`: Prevent duplicate enqueues
+- `WithEnqueuePriority`: Queue priority (lower = higher priority)
+- `WithEnqueueTimeout`: Workflow timeout
+- `WithEnqueueQueuePartitionKey`: Partition key for partitioned queues
+- `WithEnqueueApplicationVersion`: Override application version
+
+The workflow name must match the registered name or custom name set with `WithWorkflowName` during registration.
+
+Always call `client.Shutdown()` when done.
+
+Reference: [DBOS Client Enqueue](https://docs.dbos.dev/golang/reference/client#enqueue)

skills/dbos-golang/references/client-setup.md

@@ -0,0 +1,65 @@
+---
+title: Initialize Client for External Access
+impact: HIGH
+impactDescription: Enables external applications to interact with DBOS workflows
+tags: client, external, setup, initialization
+---
+
+## Initialize Client for External Access
+
+Use `dbos.NewClient` to interact with DBOS from external applications like API servers, CLI tools, or separate services. The Client connects directly to the DBOS system database.
+
+**Incorrect (using full DBOS context from an external app):**
+
+```go
+// Full DBOS context requires Launch() - too heavy for external clients
+ctx, _ := dbos.NewDBOSContext(context.Background(), config)
+dbos.Launch(ctx)
+```
+
+**Correct (using Client):**
+
+```go
+client, err := dbos.NewClient(context.Background(), dbos.ClientConfig{
+	DatabaseURL: os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+})
+if err != nil {
+	log.Fatal(err)
+}
+defer client.Shutdown(10 * time.Second)
+
+// Send a message to a workflow
+err = client.Send(workflowID, "notification", "topic")
+
+// Get an event from a workflow
+event, err := client.GetEvent(workflowID, "status", 60*time.Second)
+
+// Retrieve a workflow handle
+handle, err := client.RetrieveWorkflow(workflowID)
+result, err := handle.GetResult()
+
+// List workflows
+workflows, err := client.ListWorkflows(
+	dbos.WithStatus([]dbos.WorkflowStatusType{dbos.WorkflowStatusError}),
+)
+
+// Workflow management
+err = client.CancelWorkflow(workflowID)
+handle, err = client.ResumeWorkflow(workflowID)
+
+// Read a stream
+values, closed, err := client.ClientReadStream(workflowID, "results")
+
+// Read a stream asynchronously
+ch, err := client.ClientReadStreamAsync(workflowID, "results")
+```
+
+ClientConfig options:
+- `DatabaseURL` (required unless `SystemDBPool` is set): PostgreSQL connection string
+- `SystemDBPool`: Custom `*pgxpool.Pool`
+- `DatabaseSchema`: Schema name (default: `"dbos"`)
+- `Logger`: Custom `*slog.Logger`
+
+Always call `client.Shutdown()` when done.
+
+Reference: [DBOS Client](https://docs.dbos.dev/golang/reference/client)

skills/dbos-golang/references/comm-events.md

@@ -0,0 +1,69 @@
+---
+title: Use Events for Workflow Status Publishing
+impact: MEDIUM
+impactDescription: Enables real-time progress monitoring and interactive workflows
+tags: communication, events, status, key-value
+---
+
+## Use Events for Workflow Status Publishing
+
+Workflows can publish events (key-value pairs) with `dbos.SetEvent`. Other code can read events with `dbos.GetEvent`. Events are persisted and useful for real-time progress monitoring.
+
+**Incorrect (using external state for progress):**
+
+```go
+var progress int // Global variable - not durable!
+
+func processData(ctx dbos.DBOSContext, input string) (string, error) {
+	progress = 50 // Not persisted, lost on restart
+	return input, nil
+}
+```
+
+**Correct (using events):**
+
+```go
+func processData(ctx dbos.DBOSContext, input string) (string, error) {
+	dbos.SetEvent(ctx, "status", "processing")
+	_, err := dbos.RunAsStep(ctx, stepOne, dbos.WithStepName("stepOne"))
+	if err != nil {
+		return "", err
+	}
+	dbos.SetEvent(ctx, "progress", 50)
+	_, err = dbos.RunAsStep(ctx, stepTwo, dbos.WithStepName("stepTwo"))
+	if err != nil {
+		return "", err
+	}
+	dbos.SetEvent(ctx, "progress", 100)
+	dbos.SetEvent(ctx, "status", "complete")
+	return "done", nil
+}
+
+// Read events from outside the workflow
+status, err := dbos.GetEvent[string](ctx, workflowID, "status", 60*time.Second)
+progress, err := dbos.GetEvent[int](ctx, workflowID, "progress", 60*time.Second)
+```
+
+Events are useful for interactive workflows. For example, a checkout workflow can publish a payment URL for the caller to redirect to:
+
+```go
+func checkoutWorkflow(ctx dbos.DBOSContext, order Order) (string, error) {
+	paymentURL, err := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		return createPayment(order)
+	}, dbos.WithStepName("createPayment"))
+	if err != nil {
+		return "", err
+	}
+	dbos.SetEvent(ctx, "paymentURL", paymentURL)
+	// Continue processing...
+	return "success", nil
+}
+
+// HTTP handler starts workflow and reads the payment URL
+handle, _ := dbos.RunWorkflow(ctx, checkoutWorkflow, order)
+url, _ := dbos.GetEvent[string](ctx, handle.GetWorkflowID(), "paymentURL", 300*time.Second)
+```
+
+`GetEvent` blocks until the event is set or the timeout expires. It returns the zero value of the type if the timeout is reached.
+
+Reference: [Workflow Events](https://docs.dbos.dev/golang/tutorials/workflow-communication#workflow-events)

skills/dbos-golang/references/comm-messages.md

@@ -0,0 +1,57 @@
+---
+title: Use Messages for Workflow Notifications
+impact: MEDIUM
+impactDescription: Enables reliable inter-workflow and external-to-workflow communication
+tags: communication, messages, send, recv, notification
+---
+
+## Use Messages for Workflow Notifications
+
+Use `dbos.Send` to send messages to a workflow and `dbos.Recv` to receive them. Messages are queued per topic and persisted for reliable delivery.
+
+**Incorrect (using external messaging for workflow communication):**
+
+```go
+// External message queue is not integrated with workflow recovery
+ch := make(chan string) // Not durable!
+```
+
+**Correct (using DBOS messages):**
+
+```go
+func checkoutWorkflow(ctx dbos.DBOSContext, orderID string) (string, error) {
+	// Wait for payment notification (timeout 120 seconds)
+	notification, err := dbos.Recv[string](ctx, "payment_status", 120*time.Second)
+	if err != nil {
+		return "", err
+	}
+
+	if notification == "paid" {
+		_, err = dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+			return fulfillOrder(orderID)
+		}, dbos.WithStepName("fulfillOrder"))
+		return "fulfilled", err
+	}
+	_, err = dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		return cancelOrder(orderID)
+	}, dbos.WithStepName("cancelOrder"))
+	return "cancelled", err
+}
+
+// Send a message from a webhook handler
+func paymentWebhook(ctx dbos.DBOSContext, workflowID, status string) error {
+	return dbos.Send(ctx, workflowID, status, "payment_status")
+}
+```
+
+Key behaviors:
+- `Recv` waits for and consumes the next message for the specified topic
+- Returns the zero value if the wait times out, with a `DBOSError` with code `TimeoutError`
+- Messages without a topic can only be received by `Recv` without a topic
+- Messages are queued per-topic (FIFO)
+
+**Reliability guarantees:**
+- All messages are persisted to the database
+- Messages sent from workflows are delivered exactly-once
+
+Reference: [Workflow Messaging and Notifications](https://docs.dbos.dev/golang/tutorials/workflow-communication#workflow-messaging-and-notifications)

skills/dbos-golang/references/comm-streaming.md

@@ -0,0 +1,75 @@
+---
+title: Use Streams for Real-Time Data
+impact: MEDIUM
+impactDescription: Enables streaming results from long-running workflows
+tags: communication, stream, real-time, channel
+---
+
+## Use Streams for Real-Time Data
+
+Workflows can stream data to clients in real-time using `dbos.WriteStream`, `dbos.CloseStream`, and `dbos.ReadStream`/`dbos.ReadStreamAsync`. Useful for LLM output streaming or progress reporting.
+
+**Incorrect (accumulating results then returning at end):**
+
+```go
+func processWorkflow(ctx dbos.DBOSContext, items []string) ([]string, error) {
+	var results []string
+	for _, item := range items {
+		result, _ := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+			return processItem(item)
+		}, dbos.WithStepName("process"))
+		results = append(results, result)
+	}
+	return results, nil // Client must wait for entire workflow to complete
+}
+```
+
+**Correct (streaming results as they become available):**
+
+```go
+func processWorkflow(ctx dbos.DBOSContext, items []string) (string, error) {
+	for _, item := range items {
+		result, err := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+			return processItem(item)
+		}, dbos.WithStepName("process"))
+		if err != nil {
+			return "", err
+		}
+		dbos.WriteStream(ctx, "results", result)
+	}
+	dbos.CloseStream(ctx, "results") // Signal completion
+	return "done", nil
+}
+
+// Read the stream synchronously (blocks until closed)
+handle, _ := dbos.RunWorkflow(ctx, processWorkflow, items)
+values, closed, err := dbos.ReadStream[string](ctx, handle.GetWorkflowID(), "results")
+```
+
+**Async stream reading with channels:**
+
+```go
+ch, err := dbos.ReadStreamAsync[string](ctx, handle.GetWorkflowID(), "results")
+if err != nil {
+	log.Fatal(err)
+}
+for sv := range ch {
+	if sv.Err != nil {
+		log.Fatal(sv.Err)
+	}
+	if sv.Closed {
+		break
+	}
+	fmt.Println("Received:", sv.Value)
+}
+```
+
+Key behaviors:
+- A workflow may have any number of streams, each identified by a unique key
+- Streams are immutable and append-only
+- Writes from workflows happen exactly-once
+- Streams are automatically closed when the workflow terminates
+- `ReadStream` blocks until the workflow is inactive or the stream is closed
+- `ReadStreamAsync` returns a channel of `StreamValue[R]` for non-blocking reads
+
+Reference: [Workflow Streaming](https://docs.dbos.dev/golang/tutorials/workflow-communication#workflow-streaming)

skills/dbos-golang/references/lifecycle-config.md

@@ -0,0 +1,70 @@
+---
+title: Configure and Launch DBOS Properly
+impact: CRITICAL
+impactDescription: Application won't function without proper setup
+tags: configuration, launch, setup, initialization
+---
+
+## Configure and Launch DBOS Properly
+
+Every DBOS application must create a context, register workflows and queues, then launch before running any workflows.
+
+**Incorrect (missing configuration or launch):**
+
+```go
+// No context or launch!
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	return input, nil
+}
+
+func main() {
+	// This will fail - DBOS is not initialized or launched
+	dbos.RegisterWorkflow(nil, myWorkflow) // panic: ctx cannot be nil
+}
+```
+
+**Correct (create context, register, launch):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	return input, nil
+}
+
+func main() {
+	ctx, err := dbos.NewDBOSContext(context.Background(), dbos.Config{
+		AppName:     "my-app",
+		DatabaseURL: os.Getenv("DBOS_SYSTEM_DATABASE_URL"),
+	})
+	if err != nil {
+		log.Fatal(err)
+	}
+	defer dbos.Shutdown(ctx, 30*time.Second)
+
+	dbos.RegisterWorkflow(ctx, myWorkflow)
+
+	if err := dbos.Launch(ctx); err != nil {
+		log.Fatal(err)
+	}
+
+	handle, err := dbos.RunWorkflow(ctx, myWorkflow, "hello")
+	if err != nil {
+		log.Fatal(err)
+	}
+	result, err := handle.GetResult()
+	fmt.Println(result) // "hello"
+}
+```
+
+Config fields:
+- `AppName` (required): Application identifier
+- `DatabaseURL` (required unless `SystemDBPool` is set): PostgreSQL connection string
+- `SystemDBPool`: Custom `*pgxpool.Pool` (takes precedence over `DatabaseURL`)
+- `DatabaseSchema`: Schema name (default: `"dbos"`)
+- `Logger`: Custom `*slog.Logger` (defaults to stdout)
+- `AdminServer`: Enable HTTP admin server (default: `false`)
+- `AdminServerPort`: Admin server port (default: `3001`)
+- `ApplicationVersion`: App version (auto-computed from binary hash if not set)
+- `ExecutorID`: Executor identifier (default: `"local"`)
+- `EnablePatching`: Enable code patching system (default: `false`)
+
+Reference: [Integrating DBOS](https://docs.dbos.dev/golang/integrating-dbos)

skills/dbos-golang/references/pattern-debouncing.md

@@ -0,0 +1,47 @@
+---
+title: Debounce Workflows to Prevent Wasted Work
+impact: MEDIUM
+impactDescription: Prevents redundant workflow executions during rapid triggers
+tags: pattern, debounce, delay, efficiency
+---
+
+## Debounce Workflows to Prevent Wasted Work
+
+Use `dbos.NewDebouncer` to delay workflow execution until some time has passed since the last trigger. This prevents wasted work when a workflow is triggered multiple times in quick succession.
+
+**Incorrect (executing on every trigger):**
+
+```go
+// Every keystroke triggers a new workflow - wasteful!
+func onInputChange(ctx dbos.DBOSContext, userInput string) {
+	dbos.RunWorkflow(ctx, processInput, userInput)
+}
+```
+
+**Correct (using Debouncer):**
+
+```go
+// Create debouncer before Launch()
+debouncer := dbos.NewDebouncer(ctx, processInput,
+	dbos.WithDebouncerTimeout(120*time.Second), // Max wait: 2 minutes
+)
+
+func onInputChange(ctx dbos.DBOSContext, userID, userInput string) error {
+	// Delays execution by 60 seconds from the last call
+	// Uses the LAST set of inputs when finally executing
+	_, err := debouncer.Debounce(ctx, userID, 60*time.Second, userInput)
+	return err
+}
+```
+
+Key behaviors:
+- First argument to `Debounce` is the debounce key, grouping executions together (e.g., per user)
+- Second argument is the delay duration from the last call
+- `WithDebouncerTimeout` sets a max wait time since the first trigger
+- When the workflow finally executes, it uses the **last** set of inputs
+- After execution begins, the next `Debounce` call starts a new cycle
+- Debouncers must be created **before** `Launch()`
+
+Type signature: `Debouncer[P any, R any]` — the type parameters match the target workflow.
+
+Reference: [Debouncing Workflows](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#debouncing)

skills/dbos-golang/references/pattern-idempotency.md

@@ -0,0 +1,63 @@
+---
+title: Use Workflow IDs for Idempotency
+impact: MEDIUM
+impactDescription: Prevents duplicate side effects like double payments
+tags: pattern, idempotency, workflow-id, deduplication
+---
+
+## Use Workflow IDs for Idempotency
+
+Assign a workflow ID to ensure a workflow executes only once, even if called multiple times. This prevents duplicate side effects like double payments.
+
+**Incorrect (no idempotency):**
+
+```go
+func processPayment(ctx dbos.DBOSContext, orderID string) (string, error) {
+	_, err := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		return chargeCard(orderID)
+	}, dbos.WithStepName("chargeCard"))
+	return "charged", err
+}
+
+// Multiple calls could charge the card multiple times!
+dbos.RunWorkflow(ctx, processPayment, "order-123")
+dbos.RunWorkflow(ctx, processPayment, "order-123") // Double charge!
+```
+
+**Correct (with workflow ID):**
+
+```go
+func processPayment(ctx dbos.DBOSContext, orderID string) (string, error) {
+	_, err := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		return chargeCard(orderID)
+	}, dbos.WithStepName("chargeCard"))
+	return "charged", err
+}
+
+// Same workflow ID = only one execution
+workflowID := fmt.Sprintf("payment-%s", orderID)
+dbos.RunWorkflow(ctx, processPayment, "order-123",
+	dbos.WithWorkflowID(workflowID),
+)
+dbos.RunWorkflow(ctx, processPayment, "order-123",
+	dbos.WithWorkflowID(workflowID),
+)
+// Second call returns the result of the first execution
+```
+
+Access the current workflow ID inside a workflow:
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	currentID, err := dbos.GetWorkflowID(ctx)
+	if err != nil {
+		return "", err
+	}
+	fmt.Printf("Running workflow: %s\n", currentID)
+	return input, nil
+}
+```
+
+Workflow IDs must be **globally unique** for your application. If not set, a random UUID is generated.
+
+Reference: [Workflow IDs and Idempotency](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#workflow-ids-and-idempotency)

skills/dbos-golang/references/pattern-scheduled.md

@@ -0,0 +1,69 @@
+---
+title: Create Scheduled Workflows
+impact: MEDIUM
+impactDescription: Enables recurring tasks with exactly-once-per-interval guarantees
+tags: pattern, scheduled, cron, recurring
+---
+
+## Create Scheduled Workflows
+
+Use `dbos.WithSchedule` when registering a workflow to run it on a cron schedule. Each scheduled invocation runs exactly once per interval.
+
+**Incorrect (manual scheduling with goroutine):**
+
+```go
+// Manual scheduling is not durable and misses intervals during downtime
+go func() {
+	for {
+		generateReport()
+		time.Sleep(60 * time.Second)
+	}
+}()
+```
+
+**Correct (using WithSchedule):**
+
+```go
+// Scheduled workflow must accept time.Time as input
+func everyThirtySeconds(ctx dbos.DBOSContext, scheduledTime time.Time) (string, error) {
+	fmt.Println("Running scheduled task at:", scheduledTime)
+	return "done", nil
+}
+
+func dailyReport(ctx dbos.DBOSContext, scheduledTime time.Time) (string, error) {
+	_, err := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		return generateReport()
+	}, dbos.WithStepName("generateReport"))
+	return "report generated", err
+}
+
+func main() {
+	ctx, _ := dbos.NewDBOSContext(context.Background(), config)
+	defer dbos.Shutdown(ctx, 30*time.Second)
+
+	dbos.RegisterWorkflow(ctx, everyThirtySeconds,
+		dbos.WithSchedule("*/30 * * * * *"),
+	)
+	dbos.RegisterWorkflow(ctx, dailyReport,
+		dbos.WithSchedule("0 0 9 * * *"), // 9 AM daily
+	)
+
+	dbos.Launch(ctx)
+	select {} // Block forever
+}
+```
+
+Scheduled workflows must accept exactly one parameter of type `time.Time` representing the scheduled execution time.
+
+DBOS crontab uses 6 fields with second precision:
+```text
+┌────────────── second
+│ ┌──────────── minute
+│ │ ┌────────── hour
+│ │ │ ┌──────── day of month
+│ │ │ │ ┌────── month
+│ │ │ │ │ ┌──── day of week
+* * * * * *
+```
+
+Reference: [Scheduled Workflows](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#scheduled-workflows)

skills/dbos-golang/references/pattern-sleep.md

@@ -0,0 +1,52 @@
+---
+title: Use Durable Sleep for Delayed Execution
+impact: MEDIUM
+impactDescription: Enables reliable scheduling across restarts
+tags: pattern, sleep, delay, durable, schedule
+---
+
+## Use Durable Sleep for Delayed Execution
+
+Use `dbos.Sleep` for durable delays within workflows. The wakeup time is stored in the database, so the sleep survives restarts.
+
+**Incorrect (non-durable sleep):**
+
+```go
+func delayedTask(ctx dbos.DBOSContext, input string) (string, error) {
+	// time.Sleep is not durable - lost on restart!
+	time.Sleep(60 * time.Second)
+	result, err := dbos.RunAsStep(ctx, doWork, dbos.WithStepName("doWork"))
+	return result, err
+}
+```
+
+**Correct (durable sleep):**
+
+```go
+func delayedTask(ctx dbos.DBOSContext, input string) (string, error) {
+	// Durable sleep - survives restarts
+	_, err := dbos.Sleep(ctx, 60*time.Second)
+	if err != nil {
+		return "", err
+	}
+	result, err := dbos.RunAsStep(ctx, doWork, dbos.WithStepName("doWork"))
+	return result, err
+}
+```
+
+`dbos.Sleep` takes a `time.Duration`. It returns the remaining sleep duration (zero if completed normally).
+
+Use cases:
+- Scheduling tasks to run in the future
+- Implementing retry delays
+- Delays spanning hours, days, or weeks
+
+```go
+func scheduledTask(ctx dbos.DBOSContext, task string) (string, error) {
+	// Sleep for one week
+	dbos.Sleep(ctx, 7*24*time.Hour)
+	return processTask(task)
+}
+```
+
+Reference: [Durable Sleep](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#durable-sleep)

skills/dbos-golang/references/queue-basics.md

@@ -0,0 +1,53 @@
+---
+title: Use Queues for Concurrent Workflows
+impact: HIGH
+impactDescription: Queues provide managed concurrency and flow control
+tags: queue, concurrency, enqueue, workflow
+---
+
+## Use Queues for Concurrent Workflows
+
+Queues run many workflows concurrently with managed flow control. Use them when you need to control how many workflows run at once.
+
+**Incorrect (uncontrolled concurrency):**
+
+```go
+// Starting many workflows without control - could overwhelm resources
+for _, task := range tasks {
+	dbos.RunWorkflow(ctx, processTask, task)
+}
+```
+
+**Correct (using a queue):**
+
+```go
+// Create queue before Launch()
+queue := dbos.NewWorkflowQueue(ctx, "task_queue")
+
+func processAllTasks(ctx dbos.DBOSContext, tasks []string) ([]string, error) {
+	var handles []dbos.WorkflowHandle[string]
+	for _, task := range tasks {
+		handle, err := dbos.RunWorkflow(ctx, processTask, task,
+			dbos.WithQueue(queue.Name),
+		)
+		if err != nil {
+			return nil, err
+		}
+		handles = append(handles, handle)
+	}
+	// Wait for all tasks
+	var results []string
+	for _, h := range handles {
+		result, err := h.GetResult()
+		if err != nil {
+			return nil, err
+		}
+		results = append(results, result)
+	}
+	return results, nil
+}
+```
+
+Queues process workflows in FIFO order. All queues must be created with `dbos.NewWorkflowQueue` before `Launch()`.
+
+Reference: [DBOS Queues](https://docs.dbos.dev/golang/tutorials/queue-tutorial)

skills/dbos-golang/references/queue-concurrency.md

@@ -0,0 +1,49 @@
+---
+title: Control Queue Concurrency
+impact: HIGH
+impactDescription: Prevents resource exhaustion with concurrent limits
+tags: queue, concurrency, workerConcurrency, limits
+---
+
+## Control Queue Concurrency
+
+Queues support worker-level and global concurrency limits to prevent resource exhaustion.
+
+**Incorrect (no concurrency control):**
+
+```go
+queue := dbos.NewWorkflowQueue(ctx, "heavy_tasks") // No limits - could exhaust memory
+```
+
+**Correct (worker concurrency):**
+
+```go
+// Each process runs at most 5 tasks from this queue
+queue := dbos.NewWorkflowQueue(ctx, "heavy_tasks",
+	dbos.WithWorkerConcurrency(5),
+)
+```
+
+**Correct (global concurrency):**
+
+```go
+// At most 10 tasks run across ALL processes
+queue := dbos.NewWorkflowQueue(ctx, "limited_tasks",
+	dbos.WithGlobalConcurrency(10),
+)
+```
+
+**In-order processing (sequential):**
+
+```go
+// Only one task at a time - guarantees order
+serialQueue := dbos.NewWorkflowQueue(ctx, "sequential_queue",
+	dbos.WithGlobalConcurrency(1),
+)
+```
+
+Worker concurrency is recommended for most use cases. Take care with global concurrency as any `PENDING` workflow on the queue counts toward the limit, including workflows from previous application versions.
+
+When using worker concurrency, each process must have a unique `ExecutorID` set in configuration (this is automatic with DBOS Conductor or Cloud).
+
+Reference: [Managing Concurrency](https://docs.dbos.dev/golang/tutorials/queue-tutorial#managing-concurrency)

skills/dbos-golang/references/queue-deduplication.md

@@ -0,0 +1,52 @@
+---
+title: Deduplicate Queued Workflows
+impact: HIGH
+impactDescription: Prevents duplicate workflow executions
+tags: queue, deduplication, idempotent, duplicate
+---
+
+## Deduplicate Queued Workflows
+
+Set a deduplication ID when enqueuing to prevent duplicate workflow executions. If a workflow with the same deduplication ID is already enqueued or executing, a `DBOSError` with code `QueueDeduplicated` is returned.
+
+**Incorrect (no deduplication):**
+
+```go
+// Multiple calls could enqueue duplicates
+func handleClick(ctx dbos.DBOSContext, userID, task string) error {
+	_, err := dbos.RunWorkflow(ctx, processTask, task,
+		dbos.WithQueue(queue.Name),
+	)
+	return err
+}
+```
+
+**Correct (with deduplication):**
+
+```go
+func handleClick(ctx dbos.DBOSContext, userID, task string) error {
+	_, err := dbos.RunWorkflow(ctx, processTask, task,
+		dbos.WithQueue(queue.Name),
+		dbos.WithDeduplicationID(userID),
+	)
+	if err != nil {
+		// Check if it was deduplicated
+		var dbosErr *dbos.DBOSError
+		if errors.As(err, &dbosErr) && dbosErr.Code == dbos.QueueDeduplicated {
+			fmt.Println("Task already in progress for user:", userID)
+			return nil
+		}
+		return err
+	}
+	return nil
+}
+```
+
+Deduplication is per-queue. The deduplication ID is active while the workflow has status `ENQUEUED` or `PENDING`. Once the workflow completes, a new workflow with the same deduplication ID can be enqueued.
+
+This is useful for:
+- Ensuring one active task per user
+- Preventing duplicate form submissions
+- Idempotent event processing
+
+Reference: [Deduplication](https://docs.dbos.dev/golang/tutorials/queue-tutorial#deduplication)

skills/dbos-golang/references/queue-listening.md

@@ -0,0 +1,49 @@
+---
+title: Control Which Queues a Worker Listens To
+impact: HIGH
+impactDescription: Enables heterogeneous worker pools
+tags: queue, listen, worker, process, configuration
+---
+
+## Control Which Queues a Worker Listens To
+
+Use `ListenQueues` to make a process only dequeue from specific queues. This enables heterogeneous worker pools.
+
+**Incorrect (all workers process all queues):**
+
+```go
+cpuQueue := dbos.NewWorkflowQueue(ctx, "cpu_queue")
+gpuQueue := dbos.NewWorkflowQueue(ctx, "gpu_queue")
+
+// Every worker processes both CPU and GPU tasks
+// GPU tasks on CPU workers will fail or be slow!
+dbos.Launch(ctx)
+```
+
+**Correct (selective queue listening):**
+
+```go
+cpuQueue := dbos.NewWorkflowQueue(ctx, "cpu_queue")
+gpuQueue := dbos.NewWorkflowQueue(ctx, "gpu_queue")
+
+workerType := os.Getenv("WORKER_TYPE") // "cpu" or "gpu"
+
+if workerType == "gpu" {
+	ctx.ListenQueues(ctx, gpuQueue)
+} else if workerType == "cpu" {
+	ctx.ListenQueues(ctx, cpuQueue)
+}
+
+dbos.Launch(ctx)
+```
+
+`ListenQueues` only controls dequeuing. A CPU worker can still enqueue tasks onto the GPU queue:
+
+```go
+// From a CPU worker, enqueue onto the GPU queue
+dbos.RunWorkflow(ctx, gpuTask, "data",
+	dbos.WithQueue(gpuQueue.Name),
+)
+```
+
+Reference: [Listening to Specific Queues](https://docs.dbos.dev/golang/tutorials/queue-tutorial#listening-to-specific-queues)

skills/dbos-golang/references/queue-partitioning.md

@@ -0,0 +1,42 @@
+---
+title: Partition Queues for Per-Entity Limits
+impact: HIGH
+impactDescription: Enables per-entity concurrency control
+tags: queue, partition, per-user, dynamic
+---
+
+## Partition Queues for Per-Entity Limits
+
+Partitioned queues apply flow control limits per partition key instead of the entire queue. Each partition acts as a dynamic "subqueue".
+
+**Incorrect (global concurrency for per-user limits):**
+
+```go
+// Global concurrency=1 blocks ALL users, not per-user
+queue := dbos.NewWorkflowQueue(ctx, "tasks",
+	dbos.WithGlobalConcurrency(1),
+)
+```
+
+**Correct (partitioned queue):**
+
+```go
+queue := dbos.NewWorkflowQueue(ctx, "tasks",
+	dbos.WithPartitionQueue(),
+	dbos.WithGlobalConcurrency(1),
+)
+
+func onUserTask(ctx dbos.DBOSContext, userID, task string) error {
+	// Each user gets their own partition - at most 1 task per user
+	// but tasks from different users can run concurrently
+	_, err := dbos.RunWorkflow(ctx, processTask, task,
+		dbos.WithQueue(queue.Name),
+		dbos.WithQueuePartitionKey(userID),
+	)
+	return err
+}
+```
+
+When a queue has `WithPartitionQueue()` enabled, you **must** provide a `WithQueuePartitionKey()` when enqueuing. Partition keys and deduplication IDs cannot be used together.
+
+Reference: [Partitioning Queues](https://docs.dbos.dev/golang/tutorials/queue-tutorial#partitioning-queues)

skills/dbos-golang/references/queue-priority.md

@@ -0,0 +1,45 @@
+---
+title: Set Queue Priority for Workflows
+impact: HIGH
+impactDescription: Prioritizes important workflows over lower-priority ones
+tags: queue, priority, ordering, importance
+---
+
+## Set Queue Priority for Workflows
+
+Enable priority on a queue to process higher-priority workflows first. Lower numbers indicate higher priority.
+
+**Incorrect (no priority - FIFO only):**
+
+```go
+queue := dbos.NewWorkflowQueue(ctx, "tasks")
+// All tasks processed in FIFO order regardless of importance
+```
+
+**Correct (priority-enabled queue):**
+
+```go
+queue := dbos.NewWorkflowQueue(ctx, "tasks",
+	dbos.WithPriorityEnabled(),
+)
+
+// High priority task (lower number = higher priority)
+dbos.RunWorkflow(ctx, processTask, "urgent-task",
+	dbos.WithQueue(queue.Name),
+	dbos.WithPriority(1),
+)
+
+// Low priority task
+dbos.RunWorkflow(ctx, processTask, "background-task",
+	dbos.WithQueue(queue.Name),
+	dbos.WithPriority(100),
+)
+```
+
+Priority rules:
+- Range: `1` to `2,147,483,647`
+- Lower number = higher priority
+- Workflows **without** assigned priorities have the highest priority (run first)
+- Workflows with the same priority are dequeued in FIFO order
+
+Reference: [Priority](https://docs.dbos.dev/golang/tutorials/queue-tutorial#priority)

skills/dbos-golang/references/queue-rate-limiting.md

@@ -0,0 +1,50 @@
+---
+title: Rate Limit Queue Execution
+impact: HIGH
+impactDescription: Prevents overwhelming external APIs with too many requests
+tags: queue, rate-limit, throttle, api
+---
+
+## Rate Limit Queue Execution
+
+Set rate limits on a queue to control how many workflows start in a given period. Rate limits are global across all DBOS processes.
+
+**Incorrect (no rate limiting):**
+
+```go
+queue := dbos.NewWorkflowQueue(ctx, "llm_tasks")
+// Could send hundreds of requests per second to a rate-limited API
+```
+
+**Correct (rate-limited queue):**
+
+```go
+queue := dbos.NewWorkflowQueue(ctx, "llm_tasks",
+	dbos.WithRateLimiter(&dbos.RateLimiter{
+		Limit:  50,
+		Period: 30 * time.Second,
+	}),
+)
+```
+
+This queue starts at most 50 workflows per 30 seconds.
+
+**Combining rate limiting with concurrency:**
+
+```go
+// At most 5 concurrent and 50 per 30 seconds
+queue := dbos.NewWorkflowQueue(ctx, "api_tasks",
+	dbos.WithWorkerConcurrency(5),
+	dbos.WithRateLimiter(&dbos.RateLimiter{
+		Limit:  50,
+		Period: 30 * time.Second,
+	}),
+)
+```
+
+Common use cases:
+- LLM API rate limiting (OpenAI, Anthropic, etc.)
+- Third-party API throttling
+- Preventing database overload
+
+Reference: [Rate Limiting](https://docs.dbos.dev/golang/tutorials/queue-tutorial#rate-limiting)

skills/dbos-golang/references/step-basics.md

@@ -0,0 +1,81 @@
+---
+title: Use Steps for External Operations
+impact: HIGH
+impactDescription: Steps enable recovery by checkpointing results
+tags: step, external, api, checkpoint
+---
+
+## Use Steps for External Operations
+
+Any function that performs complex operations, accesses external APIs, or has side effects should be a step. Step results are checkpointed, enabling workflow recovery.
+
+**Incorrect (external call in workflow):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	// External API call directly in workflow - not checkpointed!
+	resp, err := http.Get("https://api.example.com/data")
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	body, _ := io.ReadAll(resp.Body)
+	return string(body), nil
+}
+```
+
+**Correct (external call in step using `dbos.RunAsStep`):**
+
+```go
+func fetchData(ctx context.Context) (string, error) {
+	resp, err := http.Get("https://api.example.com/data")
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	body, _ := io.ReadAll(resp.Body)
+	return string(body), nil
+}
+
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	data, err := dbos.RunAsStep(ctx, fetchData, dbos.WithStepName("fetchData"))
+	if err != nil {
+		return "", err
+	}
+	return data, nil
+}
+```
+
+`dbos.RunAsStep` can also accept an inline closure:
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	data, err := dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		resp, err := http.Get("https://api.example.com/data")
+		if err != nil {
+			return "", err
+		}
+		defer resp.Body.Close()
+		body, _ := io.ReadAll(resp.Body)
+		return string(body), nil
+	}, dbos.WithStepName("fetchData"))
+	return data, err
+}
+```
+
+Step type signature: `type Step[R any] func(ctx context.Context) (R, error)`
+
+Step requirements:
+- The function must accept a `context.Context` parameter — use the one provided, not the workflow's context
+- Inputs and outputs must be serializable to JSON
+- Cannot start or enqueue workflows from within steps
+- Calling a step from within another step makes the inner call part of the outer step's execution
+
+When to use steps:
+- API calls to external services
+- File system operations
+- Random number generation
+- Getting current time
+- Any non-deterministic operation
+
+Reference: [DBOS Steps](https://docs.dbos.dev/golang/tutorials/step-tutorial)

skills/dbos-golang/references/step-concurrency.md

@@ -0,0 +1,79 @@
+---
+title: Run Concurrent Steps with Go and Select
+impact: HIGH
+impactDescription: Enables parallel execution of steps with durable checkpointing
+tags: step, concurrency, goroutine, select, parallel
+---
+
+## Run Concurrent Steps with Go and Select
+
+Use `dbos.Go` to run steps concurrently in goroutines and `dbos.Select` to durably select the first completed result. Both operations are checkpointed for recovery.
+
+**Incorrect (raw goroutines without checkpointing):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	// Raw goroutines are not checkpointed - recovery breaks!
+	ch := make(chan string, 2)
+	go func() { ch <- callAPI1() }()
+	go func() { ch <- callAPI2() }()
+	return <-ch, nil
+}
+```
+
+**Correct (using dbos.Go for concurrent steps):**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	// Start steps concurrently
+	ch1, err := dbos.Go(ctx, func(ctx context.Context) (string, error) {
+		return callAPI1(ctx)
+	}, dbos.WithStepName("api1"))
+	if err != nil {
+		return "", err
+	}
+
+	ch2, err := dbos.Go(ctx, func(ctx context.Context) (string, error) {
+		return callAPI2(ctx)
+	}, dbos.WithStepName("api2"))
+	if err != nil {
+		return "", err
+	}
+
+	// Wait for the first result (durable select)
+	result, err := dbos.Select(ctx, []<-chan dbos.StepOutcome[string]{ch1, ch2})
+	if err != nil {
+		return "", err
+	}
+	return result, nil
+}
+```
+
+**Waiting for all concurrent steps:**
+
+```go
+func myWorkflow(ctx dbos.DBOSContext, input string) ([]string, error) {
+	ch1, _ := dbos.Go(ctx, step1, dbos.WithStepName("step1"))
+	ch2, _ := dbos.Go(ctx, step2, dbos.WithStepName("step2"))
+	ch3, _ := dbos.Go(ctx, step3, dbos.WithStepName("step3"))
+
+	// Collect all results
+	results := make([]string, 3)
+	for i, ch := range []<-chan dbos.StepOutcome[string]{ch1, ch2, ch3} {
+		outcome := <-ch
+		if outcome.Err != nil {
+			return nil, outcome.Err
+		}
+		results[i] = outcome.Result
+	}
+	return results, nil
+}
+```
+
+Key behaviors:
+- `dbos.Go` starts a step in a goroutine and returns a channel of `StepOutcome[R]`
+- `dbos.Select` durably selects the first completed result and checkpoints which channel was selected
+- On recovery, `Select` replays the same selection, maintaining determinism
+- Steps started with `Go` follow the same retry and checkpointing rules as `RunAsStep`
+
+Reference: [Concurrent Steps](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#concurrent-steps)

skills/dbos-golang/references/step-retries.md

@@ -0,0 +1,66 @@
+---
+title: Configure Step Retries for Transient Failures
+impact: HIGH
+impactDescription: Automatic retries handle transient failures without manual code
+tags: step, retry, exponential-backoff, resilience
+---
+
+## Configure Step Retries for Transient Failures
+
+Steps can automatically retry on failure with exponential backoff. This handles transient failures like network issues.
+
+**Incorrect (manual retry logic):**
+
+```go
+func fetchData(ctx context.Context) (string, error) {
+	var lastErr error
+	for attempt := 0; attempt < 3; attempt++ {
+		resp, err := http.Get("https://api.example.com")
+		if err == nil {
+			defer resp.Body.Close()
+			body, _ := io.ReadAll(resp.Body)
+			return string(body), nil
+		}
+		lastErr = err
+		time.Sleep(time.Duration(math.Pow(2, float64(attempt))) * time.Second)
+	}
+	return "", lastErr
+}
+```
+
+**Correct (built-in retries with `dbos.RunAsStep`):**
+
+```go
+func fetchData(ctx context.Context) (string, error) {
+	resp, err := http.Get("https://api.example.com")
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	body, _ := io.ReadAll(resp.Body)
+	return string(body), nil
+}
+
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	data, err := dbos.RunAsStep(ctx, fetchData,
+		dbos.WithStepName("fetchData"),
+		dbos.WithStepMaxRetries(10),
+		dbos.WithBaseInterval(500*time.Millisecond),
+		dbos.WithBackoffFactor(2.0),
+		dbos.WithMaxInterval(5*time.Second),
+	)
+	return data, err
+}
+```
+
+Retry parameters:
+- `WithStepMaxRetries(n)`: Maximum retry attempts (default: `0` — no retries)
+- `WithBaseInterval(d)`: Initial delay between retries (default: `100ms`)
+- `WithBackoffFactor(f)`: Multiplier for exponential backoff (default: `2.0`)
+- `WithMaxInterval(d)`: Maximum delay between retries (default: `5s`)
+
+With defaults, retry delays are: 100ms, 200ms, 400ms, 800ms, 1.6s, 3.2s, 5s, 5s...
+
+If all retries are exhausted, a `DBOSError` with code `MaxStepRetriesExceeded` is returned to the calling workflow.
+
+Reference: [Configurable Retries](https://docs.dbos.dev/golang/tutorials/step-tutorial#configurable-retries)

skills/dbos-golang/references/test-setup.md

@@ -0,0 +1,90 @@
+---
+title: Use Proper Test Setup for DBOS
+impact: LOW-MEDIUM
+impactDescription: Ensures consistent test results with proper DBOS lifecycle management
+tags: testing, go-test, setup, integration, mock
+---
+
+## Use Proper Test Setup for DBOS
+
+DBOS applications can be tested with unit tests (mocking DBOSContext) or integration tests (real Postgres database).
+
+**Incorrect (no lifecycle management between tests):**
+
+```go
+// Tests share state - results are inconsistent!
+func TestOne(t *testing.T) {
+	myWorkflow(ctx, "input")
+}
+func TestTwo(t *testing.T) {
+	// Previous test's state leaks into this test
+	myWorkflow(ctx, "input")
+}
+```
+
+**Correct (unit testing with mocks):**
+
+The `DBOSContext` interface is fully mockable. Use a mocking library like `testify/mock` or `mockery`:
+
+```go
+func TestWorkflow(t *testing.T) {
+	mockCtx := mocks.NewMockDBOSContext(t)
+
+	// Mock RunAsStep to return a canned value
+	mockCtx.On("RunAsStep", mockCtx, mock.Anything, mock.Anything).
+		Return("mock-result", nil)
+
+	result, err := myWorkflow(mockCtx, "input")
+	assert.NoError(t, err)
+	assert.Equal(t, "expected", result)
+
+	mockCtx.AssertExpectations(t)
+}
+```
+
+**Correct (integration testing with Postgres):**
+
+```go
+func setupDBOS(t *testing.T) dbos.DBOSContext {
+	t.Helper()
+	databaseURL := os.Getenv("DBOS_TEST_DATABASE_URL")
+	if databaseURL == "" {
+		t.Skip("DBOS_TEST_DATABASE_URL not set")
+	}
+
+	ctx, err := dbos.NewDBOSContext(context.Background(), dbos.Config{
+		AppName:     "test-" + t.Name(),
+		DatabaseURL: databaseURL,
+	})
+	require.NoError(t, err)
+
+	dbos.RegisterWorkflow(ctx, myWorkflow)
+
+	err = dbos.Launch(ctx)
+	require.NoError(t, err)
+
+	t.Cleanup(func() {
+		dbos.Shutdown(ctx, 10*time.Second)
+	})
+	return ctx
+}
+
+func TestWorkflowIntegration(t *testing.T) {
+	ctx := setupDBOS(t)
+
+	handle, err := dbos.RunWorkflow(ctx, myWorkflow, "test-input")
+	require.NoError(t, err)
+
+	result, err := handle.GetResult()
+	require.NoError(t, err)
+	assert.Equal(t, "expected-output", result)
+}
+```
+
+Key points:
+- Use `t.Cleanup` to ensure `Shutdown` is called after each test
+- Use unique `AppName` per test to avoid collisions
+- Mock `DBOSContext` for fast unit tests without Postgres
+- Use real Postgres for integration tests that verify durable behavior
+
+Reference: [Testing DBOS](https://docs.dbos.dev/golang/tutorials/testing)

skills/dbos-golang/references/workflow-background.md

@@ -0,0 +1,64 @@
+---
+title: Start Workflows in Background
+impact: CRITICAL
+impactDescription: Background workflows enable reliable async processing
+tags: workflow, background, handle, async
+---
+
+## Start Workflows in Background
+
+Use `dbos.RunWorkflow` to start a workflow and get a handle to track it. The workflow is guaranteed to run to completion even if the app is interrupted.
+
+**Incorrect (no way to track background work):**
+
+```go
+func processData(ctx dbos.DBOSContext, data string) (string, error) {
+	// ...
+	return "processed: " + data, nil
+}
+
+// Fire and forget in a goroutine - no durability, no tracking
+go func() {
+	processData(ctx, data)
+}()
+```
+
+**Correct (using RunWorkflow):**
+
+```go
+func processData(ctx dbos.DBOSContext, data string) (string, error) {
+	return "processed: " + data, nil
+}
+
+func main() {
+	// ... setup and launch ...
+
+	// Start workflow, get handle
+	handle, err := dbos.RunWorkflow(ctx, processData, "input")
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// Get the workflow ID
+	fmt.Println(handle.GetWorkflowID())
+
+	// Wait for result
+	result, err := handle.GetResult()
+
+	// Check status
+	status, err := handle.GetStatus()
+}
+```
+
+Retrieve a handle later by workflow ID:
+
+```go
+handle, err := dbos.RetrieveWorkflow[string](ctx, workflowID)
+result, err := handle.GetResult()
+```
+
+`GetResult` supports options:
+- `dbos.WithHandleTimeout(timeout)`: Return a timeout error if the workflow doesn't complete within the duration
+- `dbos.WithHandlePollingInterval(interval)`: Control how often the database is polled for completion
+
+Reference: [Workflows](https://docs.dbos.dev/golang/tutorials/workflow-tutorial)

skills/dbos-golang/references/workflow-constraints.md

@@ -0,0 +1,68 @@
+---
+title: Follow Workflow Constraints
+impact: CRITICAL
+impactDescription: Violating constraints breaks recovery and durability guarantees
+tags: workflow, constraints, rules, best-practices
+---
+
+## Follow Workflow Constraints
+
+Workflows have specific constraints to maintain durability guarantees. Violating them can break recovery.
+
+**Incorrect (starting workflows from steps):**
+
+```go
+func myStep(ctx context.Context) (string, error) {
+	// Don't start workflows from steps!
+	// The step's context.Context does not support workflow operations
+	return "", nil
+}
+
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	// Starting a child workflow inside a step breaks determinism
+	dbos.RunAsStep(ctx, func(ctx context.Context) (string, error) {
+		handle, _ := dbos.RunWorkflow(ctx.(dbos.DBOSContext), otherWorkflow, "data") // WRONG
+		return handle.GetWorkflowID(), nil
+	})
+	return "", nil
+}
+```
+
+**Correct (workflow operations only from workflows):**
+
+```go
+func fetchData(ctx context.Context) (string, error) {
+	// Steps only do external operations
+	resp, err := http.Get("https://api.example.com")
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	body, _ := io.ReadAll(resp.Body)
+	return string(body), nil
+}
+
+func myWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	data, err := dbos.RunAsStep(ctx, fetchData, dbos.WithStepName("fetchData"))
+	if err != nil {
+		return "", err
+	}
+	// Start child workflows from the parent workflow
+	handle, err := dbos.RunWorkflow(ctx, otherWorkflow, data)
+	if err != nil {
+		return "", err
+	}
+	// Receive messages from the workflow
+	msg, err := dbos.Recv[string](ctx, "topic", 60*time.Second)
+	// Set events from the workflow
+	dbos.SetEvent(ctx, "status", "done")
+	return data, nil
+}
+```
+
+Additional constraints:
+- Don't modify global variables from workflows or steps
+- All workflows and queues must be registered **before** `Launch()`
+- Concurrent steps must start in deterministic order using `dbos.Go`/`dbos.Select`
+
+Reference: [Workflow Guarantees](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#workflow-guarantees)

skills/dbos-golang/references/workflow-control.md

@@ -0,0 +1,53 @@
+---
+title: Cancel, Resume, and Fork Workflows
+impact: MEDIUM
+impactDescription: Enables operational control over long-running workflows
+tags: workflow, cancel, resume, fork, management
+---
+
+## Cancel, Resume, and Fork Workflows
+
+DBOS provides functions to cancel, resume, and fork workflows for operational control.
+
+**Incorrect (no way to handle stuck or failed workflows):**
+
+```go
+// Workflow is stuck or failed - no recovery mechanism
+handle, _ := dbos.RunWorkflow(ctx, processTask, "data")
+// If the workflow fails, there's no way to retry or recover
+```
+
+**Correct (using cancel, resume, and fork):**
+
+```go
+// Cancel a workflow - stops at its next step
+err := dbos.CancelWorkflow(ctx, workflowID)
+
+// Resume from the last completed step
+handle, err := dbos.ResumeWorkflow[string](ctx, workflowID)
+result, err := handle.GetResult()
+```
+
+Cancellation sets the workflow status to `CANCELLED` and preempts execution at the beginning of the next step. Cancelling also cancels all child workflows.
+
+Resume restarts a workflow from its last completed step. Use this for workflows that are cancelled or have exceeded their maximum recovery attempts. You can also use this to start an enqueued workflow immediately, bypassing its queue.
+
+Fork a workflow from a specific step:
+
+```go
+// List steps to find the right step ID
+steps, err := dbos.GetWorkflowSteps(ctx, workflowID)
+
+// Fork from a specific step
+forkHandle, err := dbos.ForkWorkflow[string](ctx, dbos.ForkWorkflowInput{
+	OriginalWorkflowID: workflowID,
+	StartStep:          2, // Fork from step 2
+	ForkedWorkflowID:   "new-wf-id",       // Optional
+	ApplicationVersion: "2.0.0",            // Optional
+})
+result, err := forkHandle.GetResult()
+```
+
+Forking creates a new workflow with a new ID, copying the original workflow's inputs and step outputs up to the selected step.
+
+Reference: [Workflow Management](https://docs.dbos.dev/golang/tutorials/workflow-management)

skills/dbos-golang/references/workflow-determinism.md

@@ -0,0 +1,51 @@
+---
+title: Keep Workflows Deterministic
+impact: CRITICAL
+impactDescription: Non-deterministic workflows cannot recover correctly
+tags: workflow, determinism, recovery, reliability
+---
+
+## Keep Workflows Deterministic
+
+Workflow functions must be deterministic: given the same inputs and step return values, they must invoke the same steps in the same order. Non-deterministic operations must be moved to steps.
+
+**Incorrect (non-deterministic workflow):**
+
+```go
+func exampleWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	// Random value in workflow breaks recovery!
+	// On replay, rand.Intn returns a different value,
+	// so the workflow may take a different branch.
+	if rand.Intn(2) == 0 {
+		return stepOne(ctx)
+	}
+	return stepTwo(ctx)
+}
+```
+
+**Correct (non-determinism in step):**
+
+```go
+func exampleWorkflow(ctx dbos.DBOSContext, input string) (string, error) {
+	// Step result is checkpointed - replay uses the saved value
+	choice, err := dbos.RunAsStep(ctx, func(ctx context.Context) (int, error) {
+		return rand.Intn(2), nil
+	}, dbos.WithStepName("generateChoice"))
+	if err != nil {
+		return "", err
+	}
+	if choice == 0 {
+		return stepOne(ctx)
+	}
+	return stepTwo(ctx)
+}
+```
+
+Non-deterministic operations that must be in steps:
+- Random number generation
+- Getting current time (`time.Now()`)
+- Accessing external APIs (`http.Get`, etc.)
+- Reading files
+- Database queries
+
+Reference: [Workflow Determinism](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#determinism)

skills/dbos-golang/references/workflow-introspection.md

@@ -0,0 +1,64 @@
+---
+title: List and Inspect Workflows
+impact: MEDIUM
+impactDescription: Enables monitoring and debugging of workflow executions
+tags: workflow, list, inspect, status, monitoring
+---
+
+## List and Inspect Workflows
+
+Use `dbos.ListWorkflows` to query workflow executions by status, name, time range, and other criteria.
+
+**Incorrect (no monitoring of workflow state):**
+
+```go
+// Start workflow with no way to check on it later
+dbos.RunWorkflow(ctx, processTask, "data")
+// If something goes wrong, no way to find or debug it
+```
+
+**Correct (listing and inspecting workflows):**
+
+```go
+// List workflows by status
+erroredWorkflows, err := dbos.ListWorkflows(ctx,
+	dbos.WithStatus([]dbos.WorkflowStatusType{dbos.WorkflowStatusError}),
+)
+
+for _, wf := range erroredWorkflows {
+	fmt.Printf("Workflow %s: %s - %v\n", wf.ID, wf.Name, wf.Error)
+}
+```
+
+List workflows with multiple filters:
+
+```go
+workflows, err := dbos.ListWorkflows(ctx,
+	dbos.WithName("processOrder"),
+	dbos.WithStatus([]dbos.WorkflowStatusType{dbos.WorkflowStatusSuccess}),
+	dbos.WithLimit(100),
+	dbos.WithSortDesc(),
+	dbos.WithLoadOutput(true),
+)
+```
+
+List workflow steps:
+
+```go
+steps, err := dbos.GetWorkflowSteps(ctx, workflowID)
+for _, step := range steps {
+	fmt.Printf("Step %d: %s\n", step.StepID, step.StepName)
+	if step.Error != nil {
+		fmt.Printf("  Error: %v\n", step.Error)
+	}
+	if step.ChildWorkflowID != "" {
+		fmt.Printf("  Child: %s\n", step.ChildWorkflowID)
+	}
+}
+```
+
+Workflow status values: `WorkflowStatusPending`, `WorkflowStatusEnqueued`, `WorkflowStatusSuccess`, `WorkflowStatusError`, `WorkflowStatusCancelled`, `WorkflowStatusMaxRecoveryAttemptsExceeded`
+
+To optimize performance, avoid loading inputs/outputs when you don't need them (they are not loaded by default).
+
+Reference: [Workflow Management](https://docs.dbos.dev/golang/tutorials/workflow-management#listing-workflows)

skills/dbos-golang/references/workflow-timeout.md

@@ -0,0 +1,38 @@
+---
+title: Set Workflow Timeouts
+impact: CRITICAL
+impactDescription: Prevents workflows from running indefinitely
+tags: workflow, timeout, cancellation, duration
+---
+
+## Set Workflow Timeouts
+
+Set a timeout for a workflow by using Go's `context.WithTimeout` or `dbos.WithTimeout` on the DBOS context. When the timeout expires, the workflow and all its children are cancelled.
+
+**Incorrect (no timeout for potentially long workflow):**
+
+```go
+// No timeout - could run indefinitely
+handle, err := dbos.RunWorkflow(ctx, processTask, "data")
+```
+
+**Correct (with timeout):**
+
+```go
+// Create a context with a 5-minute timeout
+timedCtx, cancel := dbos.WithTimeout(ctx, 5*time.Minute)
+defer cancel()
+
+handle, err := dbos.RunWorkflow(timedCtx, processTask, "data")
+if err != nil {
+	log.Fatal(err)
+}
+```
+
+Key timeout behaviors:
+- Timeouts are **start-to-completion**: the timeout begins when the workflow starts execution, not when it's enqueued
+- Timeouts are **durable**: they persist across restarts, so workflows can have very long timeouts (hours, days, weeks)
+- Cancellation happens at the **beginning of the next step** - the current step completes first
+- Cancelling a workflow also cancels all **child workflows**
+
+Reference: [Workflow Timeouts](https://docs.dbos.dev/golang/tutorials/workflow-tutorial#workflow-timeouts)

skills/dbos-python/AGENTS.md

@@ -0,0 +1,95 @@
+# dbos-python
+
+> **Note:** `CLAUDE.md` is a symlink to this file.
+
+## Overview
+
+DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.
+
+## Structure
+
+```
+dbos-python/
+  SKILL.md       # Main skill file - read this first
+  AGENTS.md      # This navigation guide
+  CLAUDE.md      # Symlink to AGENTS.md
+  references/    # Detailed reference files
+```
+
+## Usage
+
+1. Read `SKILL.md` for the main skill instructions
+2. Browse `references/` for detailed documentation on specific topics
+3. Reference files are loaded on-demand - read only what you need
+
+## Reference Categories
+
+| Priority | Category | Impact | Prefix |
+|----------|----------|--------|--------|
+| 1 | Lifecycle | CRITICAL | `lifecycle-` |
+| 2 | Workflow | CRITICAL | `workflow-` |
+| 3 | Step | HIGH | `step-` |
+| 4 | Queue | HIGH | `queue-` |
+| 5 | Communication | MEDIUM | `comm-` |
+| 6 | Pattern | MEDIUM | `pattern-` |
+| 7 | Testing | LOW-MEDIUM | `test-` |
+| 8 | Client | MEDIUM | `client-` |
+| 9 | Advanced | LOW | `advanced-` |
+
+Reference files are named `{prefix}-{topic}.md` (e.g., `query-missing-indexes.md`).
+
+## Available References
+
+**Advanced** (`advanced-`):
+- `references/advanced-async.md`
+- `references/advanced-patching.md`
+- `references/advanced-versioning.md`
+
+**Client** (`client-`):
+- `references/client-enqueue.md`
+- `references/client-setup.md`
+
+**Communication** (`comm-`):
+- `references/comm-events.md`
+- `references/comm-messages.md`
+- `references/comm-streaming.md`
+
+**Lifecycle** (`lifecycle-`):
+- `references/lifecycle-config.md`
+- `references/lifecycle-fastapi.md`
+
+**Pattern** (`pattern-`):
+- `references/pattern-classes.md`
+- `references/pattern-debouncing.md`
+- `references/pattern-idempotency.md`
+- `references/pattern-scheduled.md`
+- `references/pattern-sleep.md`
+
+**Queue** (`queue-`):
+- `references/queue-basics.md`
+- `references/queue-concurrency.md`
+- `references/queue-deduplication.md`
+- `references/queue-listening.md`
+- `references/queue-partitioning.md`
+- `references/queue-priority.md`
+- `references/queue-rate-limiting.md`
+
+**Step** (`step-`):
+- `references/step-basics.md`
+- `references/step-retries.md`
+- `references/step-transactions.md`
+
+**Testing** (`test-`):
+- `references/test-fixtures.md`
+
+**Workflow** (`workflow-`):
+- `references/workflow-background.md`
+- `references/workflow-constraints.md`
+- `references/workflow-control.md`
+- `references/workflow-determinism.md`
+- `references/workflow-introspection.md`
+- `references/workflow-timeout.md`
+
+---
+
+*32 reference files across 9 categories*

skills/dbos-python/CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

skills/dbos-python/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: dbos-python
+description: DBOS Python SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Python code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.
+risk: safe
+source: https://docs.dbos.dev/
+license: MIT
+metadata:
+  author: dbos
+  version: "1.0.0"
+  organization: DBOS
+  date: January 2026
+  abstract: Comprehensive guide for building fault-tolerant Python applications with DBOS. Covers workflows, steps, queues, communication patterns, and best practices for durable execution.
+---
+
+# DBOS Python Best Practices
+
+Guide for building reliable, fault-tolerant Python applications with DBOS durable workflows.
+
+## When to Use
+
+Reference these guidelines when:
+- Adding DBOS to existing Python code
+- Creating workflows and steps
+- Using queues for concurrency control
+- Implementing workflow communication (events, messages, streams)
+- Configuring and launching DBOS applications
+- Using DBOSClient from external applications
+- Testing DBOS applications
+
+## Rule Categories by Priority
+
+| Priority | Category | Impact | Prefix |
+|----------|----------|--------|--------|
+| 1 | Lifecycle | CRITICAL | `lifecycle-` |
+| 2 | Workflow | CRITICAL | `workflow-` |
+| 3 | Step | HIGH | `step-` |
+| 4 | Queue | HIGH | `queue-` |
+| 5 | Communication | MEDIUM | `comm-` |
+| 6 | Pattern | MEDIUM | `pattern-` |
+| 7 | Testing | LOW-MEDIUM | `test-` |
+| 8 | Client | MEDIUM | `client-` |
+| 9 | Advanced | LOW | `advanced-` |
+
+## Critical Rules
+
+### DBOS Configuration and Launch
+
+A DBOS application MUST configure and launch DBOS inside its main function:
+
+```python
+import os
+from dbos import DBOS, DBOSConfig
+
+@DBOS.workflow()
+def my_workflow():
+    pass
+
+if __name__ == "__main__":
+    config: DBOSConfig = {
+        "name": "my-app",
+        "system_database_url": os.environ.get("DBOS_SYSTEM_DATABASE_URL"),
+    }
+    DBOS(config=config)
+    DBOS.launch()
+```
+
+### Workflow and Step Structure
+
+Workflows are comprised of steps. Any function performing complex operations or accessing external services must be a step:
+
+```python
+@DBOS.step()
+def call_external_api():
+    return requests.get("https://api.example.com").json()
+
+@DBOS.workflow()
+def my_workflow():
+    result = call_external_api()
+    return result
+```
+
+### Key Constraints
+
+- Do NOT call `DBOS.start_workflow` or `DBOS.recv` from a step
+- Do NOT use threads to start workflows - use `DBOS.start_workflow` or queues
+- Workflows MUST be deterministic - non-deterministic operations go in steps
+- Do NOT create/update global variables from workflows or steps
+
+## How to Use
+
+Read individual rule files for detailed explanations and examples:
+
+```
+references/lifecycle-config.md
+references/workflow-determinism.md
+references/queue-concurrency.md
+```
+
+## References
+
+- https://docs.dbos.dev/
+- https://github.com/dbos-inc/dbos-transact-py

skills/dbos-python/references/_sections.md

@@ -0,0 +1,41 @@
+# Section Definitions
+
+This file defines the rule categories for DBOS Python best practices. Rules are automatically assigned to sections based on their filename prefix.
+
+---
+
+## 1. Lifecycle (lifecycle)
+**Impact:** CRITICAL
+**Description:** DBOS configuration, initialization, and launch patterns. Foundation for all DBOS applications.
+
+## 2. Workflow (workflow)
+**Impact:** CRITICAL
+**Description:** Workflow creation, determinism requirements, background execution, and workflow IDs.
+
+## 3. Step (step)
+**Impact:** HIGH
+**Description:** Step creation, retries, transactions, and when to use steps vs workflows.
+
+## 4. Queue (queue)
+**Impact:** HIGH
+**Description:** Queue creation, concurrency limits, rate limiting, partitioning, and priority.
+
+## 5. Communication (comm)
+**Impact:** MEDIUM
+**Description:** Workflow events, messages, and streaming for inter-workflow communication.
+
+## 6. Pattern (pattern)
+**Impact:** MEDIUM
+**Description:** Common patterns including idempotency, scheduled workflows, debouncing, and classes.
+
+## 7. Testing (test)
+**Impact:** LOW-MEDIUM
+**Description:** Testing DBOS applications with pytest, fixtures, and best practices.
+
+## 8. Client (client)
+**Impact:** MEDIUM
+**Description:** DBOSClient for interacting with DBOS from external applications.
+
+## 9. Advanced (advanced)
+**Impact:** LOW
+**Description:** Async workflows, workflow versioning, patching, and code upgrades.

skills/dbos-python/references/advanced-async.md

@@ -0,0 +1,101 @@
+---
+title: Use Async Workflows Correctly
+impact: LOW
+impactDescription: Enables non-blocking I/O in workflows
+tags: async, coroutine, await, asyncio
+---
+
+## Use Async Workflows Correctly
+
+Coroutine (async) functions can be DBOS workflows. Use async-specific methods and patterns.
+
+**Incorrect (mixing sync and async):**
+
+```python
+@DBOS.workflow()
+async def async_workflow():
+    # Don't use sync sleep in async workflow!
+    DBOS.sleep(10)
+
+    # Don't use sync start_workflow for async workflows
+    handle = DBOS.start_workflow(other_async_workflow)
+```
+
+**Correct (async patterns):**
+
+```python
+import asyncio
+import aiohttp
+
+@DBOS.step()
+async def fetch_async():
+    async with aiohttp.ClientSession() as session:
+        async with session.get("https://example.com") as response:
+            return await response.text()
+
+@DBOS.workflow()
+async def async_workflow():
+    # Use async sleep
+    await DBOS.sleep_async(10)
+
+    # Await async steps
+    result = await fetch_async()
+
+    # Use async start_workflow
+    handle = await DBOS.start_workflow_async(other_async_workflow)
+
+    return result
+```
+
+### Running Async Steps In Parallel
+
+You can run async steps in parallel if they are started in **deterministic order**:
+
+**Correct (deterministic start order):**
+
+```python
+@DBOS.workflow()
+async def parallel_workflow():
+    # Start steps in deterministic order, then await together
+    tasks = [
+        asyncio.create_task(step1("arg1")),
+        asyncio.create_task(step2("arg2")),
+        asyncio.create_task(step3("arg3")),
+    ]
+    # Use return_exceptions=True for proper error handling
+    results = await asyncio.gather(*tasks, return_exceptions=True)
+    return results
+```
+
+**Incorrect (non-deterministic order):**
+
+```python
+@DBOS.workflow()
+async def bad_parallel_workflow():
+    async def seq_a():
+        await step1("arg1")
+        await step2("arg2")  # Order depends on step1 timing
+
+    async def seq_b():
+        await step3("arg3")
+        await step4("arg4")  # Order depends on step3 timing
+
+    # step2 and step4 may run in either order - non-deterministic!
+    await asyncio.gather(seq_a(), seq_b())
+```
+
+If you need concurrent sequences, use child workflows instead of interleaving steps.
+
+For transactions in async workflows, use `asyncio.to_thread`:
+
+```python
+@DBOS.transaction()
+def sync_transaction(data):
+    DBOS.sql_session.execute(...)
+
+@DBOS.workflow()
+async def async_workflow():
+    result = await asyncio.to_thread(sync_transaction, data)
+```
+
+Reference: [Async Workflows](https://docs.dbos.dev/python/tutorials/workflow-tutorial#coroutine-async-workflows)

skills/dbos-python/references/advanced-patching.md

@@ -0,0 +1,68 @@
+---
+title: Use Patching for Safe Workflow Upgrades
+impact: LOW
+impactDescription: Deploy breaking changes without disrupting in-progress workflows
+tags: patching, upgrade, versioning, migration
+---
+
+## Use Patching for Safe Workflow Upgrades
+
+Use `DBOS.patch()` to safely deploy breaking workflow changes. Breaking changes alter what steps run or their order.
+
+**Incorrect (breaking change without patch):**
+
+```python
+# Original
+@DBOS.workflow()
+def workflow():
+    foo()
+    bar()
+
+# Updated - breaks in-progress workflows!
+@DBOS.workflow()
+def workflow():
+    baz()  # Replaced foo() - checkpoints don't match
+    bar()
+```
+
+**Correct (using patch):**
+
+```python
+# Enable patching in config
+config: DBOSConfig = {
+    "name": "my-app",
+    "enable_patching": True,
+}
+DBOS(config=config)
+
+@DBOS.workflow()
+def workflow():
+    if DBOS.patch("use-baz"):
+        baz()  # New workflows use baz
+    else:
+        foo()  # Old workflows continue with foo
+    bar()
+```
+
+Deprecating patches after all old workflows complete:
+
+```python
+# Step 1: Deprecate (runs all workflows, stops inserting marker)
+@DBOS.workflow()
+def workflow():
+    DBOS.deprecate_patch("use-baz")
+    baz()
+    bar()
+
+# Step 2: Remove entirely (after all deprecated workflows complete)
+@DBOS.workflow()
+def workflow():
+    baz()
+    bar()
+```
+
+`DBOS.patch(name)` returns:
+- `True` for new workflows (started after patch deployed)
+- `False` for old workflows (started before patch deployed)
+
+Reference: [Patching](https://docs.dbos.dev/python/tutorials/upgrading-workflows#patching)

skills/dbos-python/references/advanced-versioning.md

@@ -0,0 +1,66 @@
+---
+title: Use Versioning for Blue-Green Deployments
+impact: LOW
+impactDescription: Safely deploy new code with version tagging
+tags: versioning, blue-green, deployment, recovery
+---
+
+## Use Versioning for Blue-Green Deployments
+
+DBOS versions workflows to prevent unsafe recovery. Use blue-green deployments to safely upgrade.
+
+**Incorrect (deploying breaking changes without versioning):**
+
+```python
+# Deploying new code directly kills in-progress workflows
+# because their checkpoints don't match the new code
+
+# Old code
+@DBOS.workflow()
+def workflow():
+    step_a()
+    step_b()
+
+# New code replaces old immediately - breaks recovery!
+@DBOS.workflow()
+def workflow():
+    step_a()
+    step_c()  # Changed step - old workflows can't recover
+```
+
+**Correct (using versioning with blue-green deployment):**
+
+```python
+# Set explicit version in config
+config: DBOSConfig = {
+    "name": "my-app",
+    "application_version": "2.0.0",  # New version
+}
+DBOS(config=config)
+
+# Deploy new version alongside old version
+# New traffic goes to v2.0.0, old workflows drain on v1.0.0
+
+# Check for remaining old workflows before retiring v1.0.0
+old_workflows = DBOS.list_workflows(
+    app_version="1.0.0",
+    status=["PENDING", "ENQUEUED"]
+)
+
+if len(old_workflows) == 0:
+    # Safe to retire old version
+    pass
+```
+
+Fork a workflow to run on a new version:
+
+```python
+# Fork workflow from step 5 on version 2.0.0
+new_handle = DBOS.fork_workflow(
+    workflow_id="old-workflow-id",
+    start_step=5,
+    application_version="2.0.0"
+)
+```
+
+Reference: [Versioning](https://docs.dbos.dev/python/tutorials/upgrading-workflows#versioning)

skills/dbos-python/references/client-enqueue.md

@@ -0,0 +1,54 @@
+---
+title: Enqueue Workflows from External Applications
+impact: HIGH
+impactDescription: Enables decoupled architecture with separate API and worker services
+tags: client, enqueue, workflow, external
+---
+
+## Enqueue Workflows from External Applications
+
+Use `client.enqueue()` to submit workflows from outside the DBOS application. Must specify workflow and queue names explicitly.
+
+**Incorrect (missing required options):**
+
+```python
+from dbos import DBOSClient
+
+client = DBOSClient(system_database_url=db_url)
+
+# Missing workflow_name and queue_name!
+handle = client.enqueue({}, task_data)
+```
+
+**Correct (with required options):**
+
+```python
+from dbos import DBOSClient, EnqueueOptions
+
+client = DBOSClient(system_database_url=db_url)
+
+options: EnqueueOptions = {
+    "workflow_name": "process_task",  # Required
+    "queue_name": "task_queue",       # Required
+}
+handle = client.enqueue(options, task_data)
+result = handle.get_result()
+client.destroy()
+```
+
+With optional parameters:
+
+```python
+options: EnqueueOptions = {
+    "workflow_name": "process_task",
+    "queue_name": "task_queue",
+    "workflow_id": "custom-id-123",
+    "workflow_timeout": 300,
+    "deduplication_id": "user-123",
+    "priority": 1,
+}
+```
+
+Limitation: Cannot enqueue workflows that are methods on Python classes.
+
+Reference: [DBOSClient.enqueue](https://docs.dbos.dev/python/reference/client#enqueue)

skills/dbos-python/references/client-setup.md

@@ -0,0 +1,57 @@
+---
+title: Initialize DBOSClient for External Access
+impact: HIGH
+impactDescription: Enables external applications to interact with DBOS
+tags: client, setup, initialization, external
+---
+
+## Initialize DBOSClient for External Access
+
+Use `DBOSClient` to interact with DBOS from external applications (API servers, CLI tools, etc.).
+
+**Incorrect (no cleanup):**
+
+```python
+from dbos import DBOSClient
+
+client = DBOSClient(system_database_url=db_url)
+handle = client.enqueue(options, data)
+# Connection leaked - no destroy()!
+```
+
+**Correct (with cleanup):**
+
+```python
+import os
+from dbos import DBOSClient
+
+client = DBOSClient(
+    system_database_url=os.environ["DBOS_SYSTEM_DATABASE_URL"]
+)
+
+try:
+    handle = client.enqueue(options, data)
+    result = handle.get_result()
+finally:
+    client.destroy()
+```
+
+Constructor parameters:
+- `system_database_url`: Connection string to DBOS system database
+- `serializer`: Must match the DBOS application's serializer (default: pickle)
+
+## API Reference
+
+Beyond `enqueue`, DBOSClient mirrors the DBOS API. Use the same patterns from other reference files:
+
+| DBOSClient method | Same as DBOS method |
+|-------------------|---------------------|
+| `client.send()` | `DBOS.send()` - add `idempotency_key` for exactly-once |
+| `client.get_event()` | `DBOS.get_event()` |
+| `client.read_stream()` | `DBOS.read_stream()` |
+| `client.list_workflows()` | `DBOS.list_workflows()` |
+| `client.cancel_workflow()` | `DBOS.cancel_workflow()` |
+| `client.resume_workflow()` | `DBOS.resume_workflow()` |
+| `client.retrieve_workflow()` | `DBOS.retrieve_workflow()` |
+
+Reference: [DBOSClient](https://docs.dbos.dev/python/reference/client)

skills/dbos-python/references/comm-events.md

@@ -0,0 +1,61 @@
+---
+title: Use Events for Workflow Status Publishing
+impact: MEDIUM
+impactDescription: Enables real-time workflow status monitoring
+tags: events, set_event, get_event, status
+---
+
+## Use Events for Workflow Status Publishing
+
+Workflows can publish key-value events that clients can read. Events are persisted and useful for status updates.
+
+**Incorrect (no way to monitor progress):**
+
+```python
+@DBOS.workflow()
+def long_workflow():
+    step_one()
+    step_two()  # Client can't see progress
+    step_three()
+    return "done"
+```
+
+**Correct (publishing events):**
+
+```python
+@DBOS.workflow()
+def long_workflow():
+    DBOS.set_event("status", "starting")
+
+    step_one()
+    DBOS.set_event("status", "step_one_complete")
+
+    step_two()
+    DBOS.set_event("status", "step_two_complete")
+
+    step_three()
+    DBOS.set_event("status", "finished")
+    return "done"
+
+# Client code to read events
+@app.post("/start")
+def start_workflow():
+    handle = DBOS.start_workflow(long_workflow)
+    return {"workflow_id": handle.get_workflow_id()}
+
+@app.get("/status/{workflow_id}")
+def get_status(workflow_id: str):
+    status = DBOS.get_event(workflow_id, "status", timeout_seconds=0) or "not started"
+    return {"status": status}
+```
+
+Get all events from a workflow:
+
+```python
+all_events = DBOS.get_all_events(workflow_id)
+# Returns: {"status": "finished", "other_key": "value"}
+```
+
+Events can be called from `set_event` from workflows or steps.
+
+Reference: [Workflow Events](https://docs.dbos.dev/python/tutorials/workflow-communication#workflow-events)

skills/dbos-python/references/comm-messages.md

@@ -0,0 +1,56 @@
+---
+title: Use Messages for Workflow Notifications
+impact: MEDIUM
+impactDescription: Enables external signals to control workflow execution
+tags: messages, send, recv, notifications
+---
+
+## Use Messages for Workflow Notifications
+
+Send messages to workflows to signal or notify them while running. Messages are persisted and queued per topic.
+
+**Incorrect (polling external state):**
+
+```python
+@DBOS.workflow()
+def payment_workflow():
+    # Polling is inefficient and not durable
+    while True:
+        status = check_payment_status()
+        if status == "paid":
+            break
+        time.sleep(1)
+```
+
+**Correct (using messages):**
+
+```python
+PAYMENT_STATUS = "payment_status"
+
+@DBOS.workflow()
+def payment_workflow():
+    # Process order...
+    DBOS.set_event("payment_id", payment_id)
+
+    # Wait for payment notification (60 second timeout)
+    payment_status = DBOS.recv(PAYMENT_STATUS, timeout_seconds=60)
+
+    if payment_status == "paid":
+        fulfill_order()
+    else:
+        cancel_order()
+
+# Webhook endpoint to receive payment notification
+@app.post("/payment_webhook/{workflow_id}/{status}")
+def payment_webhook(workflow_id: str, status: str):
+    DBOS.send(workflow_id, status, PAYMENT_STATUS)
+    return {"ok": True}
+```
+
+Key points:
+- `DBOS.recv()` can only be called from workflows
+- Messages are queued per topic
+- `recv()` returns `None` on timeout
+- Messages are persisted for exactly-once delivery
+
+Reference: [Workflow Messaging](https://docs.dbos.dev/python/tutorials/workflow-communication#workflow-messaging-and-notifications)

skills/dbos-python/references/comm-streaming.md

@@ -0,0 +1,57 @@
+---
+title: Use Streams for Real-Time Data
+impact: MEDIUM
+impactDescription: Enables real-time progress and LLM streaming
+tags: streaming, write_stream, read_stream, realtime
+---
+
+## Use Streams for Real-Time Data
+
+Workflows can stream data in real-time to clients. Useful for LLM responses, progress reporting, or long-running results.
+
+**Incorrect (returning all data at end):**
+
+```python
+@DBOS.workflow()
+def llm_workflow(prompt):
+    # Client waits for entire response
+    response = call_llm(prompt)
+    return response
+```
+
+**Correct (streaming results):**
+
+```python
+@DBOS.workflow()
+def llm_workflow(prompt):
+    for chunk in call_llm_streaming(prompt):
+        DBOS.write_stream("response", chunk)
+    DBOS.close_stream("response")
+    return "complete"
+
+# Client reads stream
+@app.get("/stream/{workflow_id}")
+def stream_response(workflow_id: str):
+    def generate():
+        for value in DBOS.read_stream(workflow_id, "response"):
+            yield value
+    return StreamingResponse(generate())
+```
+
+Stream characteristics:
+- Streams are immutable and append-only
+- Writes from workflows happen exactly-once
+- Writes from steps happen at-least-once (may duplicate on retry)
+- Streams auto-close when workflow terminates
+
+Close streams explicitly when done:
+
+```python
+@DBOS.workflow()
+def producer():
+    DBOS.write_stream("data", {"step": 1})
+    DBOS.write_stream("data", {"step": 2})
+    DBOS.close_stream("data")  # Signal completion
+```
+
+Reference: [Workflow Streaming](https://docs.dbos.dev/python/tutorials/workflow-communication#workflow-streaming)

skills/dbos-python/references/lifecycle-config.md

@@ -0,0 +1,74 @@
+---
+title: Configure and Launch DBOS Properly
+impact: CRITICAL
+impactDescription: Application won't function without proper setup
+tags: configuration, launch, setup, initialization
+---
+
+## Configure and Launch DBOS Properly
+
+Every DBOS application must configure and launch DBOS inside the main function.
+
+**Incorrect (configuration at module level):**
+
+```python
+from dbos import DBOS, DBOSConfig
+
+# Don't configure at module level!
+config: DBOSConfig = {
+    "name": "my-app",
+}
+DBOS(config=config)
+
+@DBOS.workflow()
+def my_workflow():
+    pass
+
+if __name__ == "__main__":
+    DBOS.launch()
+    my_workflow()
+```
+
+**Correct (configuration in main):**
+
+```python
+import os
+from dbos import DBOS, DBOSConfig
+
+@DBOS.workflow()
+def my_workflow():
+    pass
+
+if __name__ == "__main__":
+    config: DBOSConfig = {
+        "name": "my-app",
+        "system_database_url": os.environ.get("DBOS_SYSTEM_DATABASE_URL"),
+    }
+    DBOS(config=config)
+    DBOS.launch()
+    my_workflow()
+```
+
+For scheduled-only applications (no HTTP server), block the main thread:
+
+```python
+import os
+import threading
+from dbos import DBOS, DBOSConfig
+
+@DBOS.scheduled("* * * * *")
+@DBOS.workflow()
+def scheduled_task(scheduled_time, actual_time):
+    pass
+
+if __name__ == "__main__":
+    config: DBOSConfig = {
+        "name": "my-app",
+        "system_database_url": os.environ.get("DBOS_SYSTEM_DATABASE_URL"),
+    }
+    DBOS(config=config)
+    DBOS.launch()
+    threading.Event().wait()  # Block forever
+```
+
+Reference: [DBOS Configuration](https://docs.dbos.dev/python/reference/configuration)

skills/dbos-python/references/lifecycle-fastapi.md

@@ -0,0 +1,66 @@
+---
+title: Integrate DBOS with FastAPI
+impact: CRITICAL
+impactDescription: Proper integration ensures workflows survive server restarts
+tags: fastapi, http, server, integration
+---
+
+## Integrate DBOS with FastAPI
+
+When using DBOS with FastAPI, configure and launch DBOS inside the main function before starting uvicorn.
+
+**Incorrect (configuration at module level):**
+
+```python
+from fastapi import FastAPI
+from dbos import DBOS, DBOSConfig
+
+app = FastAPI()
+
+# Don't configure at module level!
+config: DBOSConfig = {"name": "my-app"}
+DBOS(config=config)
+
+@app.get("/")
+@DBOS.workflow()
+def endpoint():
+    return {"status": "ok"}
+
+if __name__ == "__main__":
+    DBOS.launch()
+    uvicorn.run(app)
+```
+
+**Correct (configuration in main):**
+
+```python
+import os
+from fastapi import FastAPI
+from dbos import DBOS, DBOSConfig
+import uvicorn
+
+app = FastAPI()
+
+@DBOS.step()
+def process_data():
+    return "processed"
+
+@app.get("/")
+@DBOS.workflow()
+def endpoint():
+    result = process_data()
+    return {"result": result}
+
+if __name__ == "__main__":
+    config: DBOSConfig = {
+        "name": "my-app",
+        "system_database_url": os.environ.get("DBOS_SYSTEM_DATABASE_URL"),
+    }
+    DBOS(config=config)
+    DBOS.launch()
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+```
+
+The workflow decorator can be combined with FastAPI route decorators. The FastAPI decorator should come first (outermost).
+
+Reference: [DBOS with FastAPI](https://docs.dbos.dev/python/tutorials/workflow-tutorial)

skills/dbos-python/references/pattern-classes.md

@@ -0,0 +1,61 @@
+---
+title: Use DBOS Decorators with Classes
+impact: MEDIUM
+impactDescription: Enables stateful workflow patterns with class instances
+tags: classes, dbos_class, instance, oop
+---
+
+## Use DBOS Decorators with Classes
+
+DBOS decorators work with class methods. Workflow classes must inherit from `DBOSConfiguredInstance`.
+
+**Incorrect (missing class setup):**
+
+```python
+class MyService:
+    def __init__(self, url):
+        self.url = url
+
+    @DBOS.workflow()  # Won't work without proper setup
+    def fetch_data(self):
+        return self.fetch()
+```
+
+**Correct (proper class setup):**
+
+```python
+from dbos import DBOS, DBOSConfiguredInstance
+
+@DBOS.dbos_class()
+class URLFetcher(DBOSConfiguredInstance):
+    def __init__(self, url: str):
+        self.url = url
+        # instance_name must be unique and passed to super()
+        super().__init__(instance_name=url)
+
+    @DBOS.workflow()
+    def fetch_workflow(self):
+        return self.fetch_url()
+
+    @DBOS.step()
+    def fetch_url(self):
+        return requests.get(self.url).text
+
+# Instantiate BEFORE DBOS.launch()
+example_fetcher = URLFetcher("https://example.com")
+api_fetcher = URLFetcher("https://api.example.com")
+
+if __name__ == "__main__":
+    DBOS.launch()
+    print(example_fetcher.fetch_workflow())
+```
+
+Requirements:
+- Class must be decorated with `@DBOS.dbos_class()`
+- Class must inherit from `DBOSConfiguredInstance`
+- `instance_name` must be unique and passed to `super().__init__()`
+- All instances must be created before `DBOS.launch()`
+
+Steps can be added to any class without these requirements.
+
+Reference: [Python Classes](https://docs.dbos.dev/python/tutorials/classes)

skills/dbos-python/references/pattern-debouncing.md

@@ -0,0 +1,59 @@
+---
+title: Debounce Workflows to Prevent Wasted Work
+impact: MEDIUM
+impactDescription: Reduces redundant executions during rapid input
+tags: debounce, throttle, input, optimization
+---
+
+## Debounce Workflows to Prevent Wasted Work
+
+Debouncing delays workflow execution until some time has passed since the last trigger. Useful for user input processing.
+
+**Incorrect (processing every input):**
+
+```python
+@DBOS.workflow()
+def process_input(user_input):
+    # Expensive processing
+    analyze(user_input)
+
+@app.post("/input")
+def on_input(user_id: str, input: str):
+    # Every keystroke triggers processing!
+    DBOS.start_workflow(process_input, input)
+```
+
+**Correct (debounced processing):**
+
+```python
+from dbos import Debouncer
+
+@DBOS.workflow()
+def process_input(user_input):
+    analyze(user_input)
+
+# Create a debouncer for the workflow
+debouncer = Debouncer.create(process_input)
+
+@app.post("/input")
+def on_input(user_id: str, input: str):
+    # Wait 5 seconds after last input before processing
+    debounce_key = user_id  # Debounce per user
+    debounce_period = 5.0   # Seconds
+    handle = debouncer.debounce(debounce_key, debounce_period, input)
+    return {"workflow_id": handle.get_workflow_id()}
+```
+
+Debouncer with timeout (max wait time):
+
+```python
+# Process after 5s idle OR 60s max wait
+debouncer = Debouncer.create(process_input, debounce_timeout_sec=60)
+
+def on_input(user_id: str, input: str):
+    debouncer.debounce(user_id, 5.0, input)
+```
+
+When workflow executes, it uses the **last** inputs passed to `debounce`.
+
+Reference: [Debouncing Workflows](https://docs.dbos.dev/python/tutorials/workflow-tutorial#debouncing-workflows)

skills/dbos-python/references/pattern-idempotency.md

@@ -0,0 +1,52 @@
+---
+title: Use Workflow IDs for Idempotency
+impact: MEDIUM
+impactDescription: Prevents duplicate executions of critical operations
+tags: idempotency, workflow-id, deduplication, exactly-once
+---
+
+## Use Workflow IDs for Idempotency
+
+Set workflow IDs to make operations idempotent. A workflow with the same ID executes only once.
+
+**Incorrect (duplicate payments possible):**
+
+```python
+@app.post("/pay/{order_id}")
+def process_payment(order_id: str):
+    # Multiple clicks = multiple payments!
+    handle = DBOS.start_workflow(payment_workflow, order_id)
+    return handle.get_result()
+```
+
+**Correct (idempotent with workflow ID):**
+
+```python
+from dbos import SetWorkflowID
+
+@app.post("/pay/{order_id}")
+def process_payment(order_id: str):
+    # Same order_id = same workflow ID = only one execution
+    with SetWorkflowID(f"payment-{order_id}"):
+        handle = DBOS.start_workflow(payment_workflow, order_id)
+    return handle.get_result()
+
+@DBOS.workflow()
+def payment_workflow(order_id: str):
+    charge_customer(order_id)
+    send_confirmation(order_id)
+    return "success"
+```
+
+Access the workflow ID inside workflows:
+
+```python
+@DBOS.workflow()
+def my_workflow():
+    current_id = DBOS.workflow_id
+    DBOS.logger.info(f"Running workflow {current_id}")
+```
+
+Workflow IDs must be globally unique. Duplicate IDs return the existing workflow's result without re-executing.
+
+Reference: [Workflow IDs and Idempotency](https://docs.dbos.dev/python/tutorials/workflow-tutorial#workflow-ids-and-idempotency)

skills/dbos-python/references/pattern-scheduled.md

@@ -0,0 +1,56 @@
+---
+title: Create Scheduled Workflows
+impact: MEDIUM
+impactDescription: Run workflows exactly once per time interval
+tags: scheduled, cron, recurring, timer
+---
+
+## Create Scheduled Workflows
+
+Use `@DBOS.scheduled` to run workflows on a schedule. Workflows run exactly once per interval.
+
+**Incorrect (manual scheduling):**
+
+```python
+# Don't use external cron or manual timers
+import schedule
+schedule.every(1).minute.do(my_task)
+```
+
+**Correct (DBOS scheduled workflow):**
+
+```python
+@DBOS.scheduled("* * * * *")  # Every minute
+@DBOS.workflow()
+def run_every_minute(scheduled_time, actual_time):
+    print(f"Running at {scheduled_time}")
+    do_maintenance_task()
+
+@DBOS.scheduled("0 */6 * * *")  # Every 6 hours
+@DBOS.workflow()
+def periodic_cleanup(scheduled_time, actual_time):
+    cleanup_old_records()
+```
+
+Scheduled workflow requirements:
+- Must have `@DBOS.scheduled` decorator with crontab syntax
+- Must accept two arguments: `scheduled_time` and `actual_time` (both `datetime`)
+- Main thread must stay alive for scheduled workflows
+
+For apps with only scheduled workflows (no HTTP server):
+
+```python
+import threading
+
+if __name__ == "__main__":
+    DBOS.launch()
+    threading.Event().wait()  # Block forever
+```
+
+Crontab format: `minute hour day month weekday`
+- `* * * * *` = every minute
+- `0 * * * *` = every hour
+- `0 0 * * *` = daily at midnight
+- `0 0 * * 0` = weekly on Sunday
+
+Reference: [Scheduled Workflows](https://docs.dbos.dev/python/tutorials/scheduled-workflows)

skills/dbos-python/references/pattern-sleep.md

@@ -0,0 +1,58 @@
+---
+title: Use Durable Sleep for Delayed Execution
+impact: MEDIUM
+impactDescription: Survives restarts and can span days or weeks
+tags: sleep, delay, schedule, durable
+---
+
+## Use Durable Sleep for Delayed Execution
+
+Use `DBOS.sleep()` for durable delays that survive restarts. The wakeup time is persisted in the database.
+
+**Incorrect (regular sleep):**
+
+```python
+import time
+
+@DBOS.workflow()
+def delayed_task(delay_seconds, task):
+    # Regular sleep is lost on restart!
+    time.sleep(delay_seconds)
+    run_task(task)
+```
+
+**Correct (durable sleep):**
+
+```python
+@DBOS.workflow()
+def delayed_task(delay_seconds, task):
+    # Durable sleep - survives restarts
+    DBOS.sleep(delay_seconds)
+    run_task(task)
+```
+
+Use cases for durable sleep:
+- Schedule a task for the future
+- Wait between retries
+- Implement delays spanning hours, days, or weeks
+
+Example: Schedule a reminder:
+
+```python
+@DBOS.workflow()
+def send_reminder(user_id: str, message: str, delay_days: int):
+    # Sleep for days - survives any restart
+    DBOS.sleep(delay_days * 24 * 60 * 60)
+    send_notification(user_id, message)
+```
+
+For async workflows, use `DBOS.sleep_async()`:
+
+```python
+@DBOS.workflow()
+async def async_delayed_task():
+    await DBOS.sleep_async(60)
+    await run_async_task()
+```
+
+Reference: [Durable Sleep](https://docs.dbos.dev/python/tutorials/workflow-tutorial#durable-sleep)

skills/dbos-python/references/queue-basics.md

@@ -0,0 +1,60 @@
+---
+title: Use Queues for Concurrent Workflows
+impact: HIGH
+impactDescription: Queues provide managed concurrency and flow control
+tags: queue, concurrency, enqueue, workflow
+---
+
+## Use Queues for Concurrent Workflows
+
+Queues run many workflows concurrently with managed flow control. Use them when you need to control how many workflows run at once.
+
+**Incorrect (uncontrolled concurrency):**
+
+```python
+@DBOS.workflow()
+def process_task(task):
+    pass
+
+# Starting many workflows without control
+for task in tasks:
+    DBOS.start_workflow(process_task, task)  # Could overwhelm resources
+```
+
+**Correct (using queue):**
+
+```python
+from dbos import Queue
+
+queue = Queue("task_queue")
+
+@DBOS.workflow()
+def process_task(task):
+    pass
+
+@DBOS.workflow()
+def process_all_tasks(tasks):
+    handles = []
+    for task in tasks:
+        # Queue manages concurrency
+        handle = queue.enqueue(process_task, task)
+        handles.append(handle)
+    # Wait for all tasks
+    return [h.get_result() for h in handles]
+```
+
+Queues process workflows in FIFO order. You can enqueue both workflows and steps.
+
+```python
+queue = Queue("example_queue")
+
+@DBOS.step()
+def my_step(data):
+    return process(data)
+
+# Enqueue a step
+handle = queue.enqueue(my_step, data)
+result = handle.get_result()
+```
+
+Reference: [DBOS Queues](https://docs.dbos.dev/python/tutorials/queue-tutorial)

skills/dbos-python/references/queue-concurrency.md

@@ -0,0 +1,57 @@
+---
+title: Control Queue Concurrency
+impact: HIGH
+impactDescription: Prevents resource exhaustion with concurrent limits
+tags: queue, concurrency, worker_concurrency, limits
+---
+
+## Control Queue Concurrency
+
+Queues support worker-level and global concurrency limits to prevent resource exhaustion.
+
+**Incorrect (no concurrency control):**
+
+```python
+queue = Queue("heavy_tasks")  # No limits - could exhaust memory
+
+@DBOS.workflow()
+def memory_intensive_task(data):
+    # Uses lots of memory
+    pass
+```
+
+**Correct (worker concurrency):**
+
+```python
+# Each process runs at most 5 tasks from this queue
+queue = Queue("heavy_tasks", worker_concurrency=5)
+
+@DBOS.workflow()
+def memory_intensive_task(data):
+    pass
+```
+
+**Correct (global concurrency):**
+
+```python
+# At most 10 tasks run across ALL processes
+queue = Queue("limited_tasks", concurrency=10)
+```
+
+**In-order processing (sequential):**
+
+```python
+# Only one task at a time - guarantees order
+queue = Queue("sequential_queue", concurrency=1)
+
+@DBOS.step()
+def process_event(event):
+    pass
+
+def handle_event(event):
+    queue.enqueue(process_event, event)
+```
+
+Worker concurrency is recommended for most use cases. Global concurrency should be used carefully as pending workflows count toward the limit.
+
+Reference: [Managing Concurrency](https://docs.dbos.dev/python/tutorials/queue-tutorial#managing-concurrency)

skills/dbos-python/references/queue-deduplication.md

@@ -0,0 +1,51 @@
+---
+title: Deduplicate Queued Workflows
+impact: HIGH
+impactDescription: Prevents duplicate work and resource waste
+tags: queue, deduplication, duplicate, idempotent
+---
+
+## Deduplicate Queued Workflows
+
+Use deduplication IDs to ensure only one workflow with a given ID is active in a queue at a time.
+
+**Incorrect (duplicate workflows possible):**
+
+```python
+queue = Queue("user_tasks")
+
+@app.post("/process/{user_id}")
+def process_for_user(user_id: str):
+    # Multiple requests = multiple workflows for same user!
+    queue.enqueue(process_workflow, user_id)
+```
+
+**Correct (deduplicated by user):**
+
+```python
+from dbos import Queue, SetEnqueueOptions
+from dbos import error as dboserror
+
+queue = Queue("user_tasks")
+
+@app.post("/process/{user_id}")
+def process_for_user(user_id: str):
+    with SetEnqueueOptions(deduplication_id=user_id):
+        try:
+            handle = queue.enqueue(process_workflow, user_id)
+            return {"workflow_id": handle.get_workflow_id()}
+        except dboserror.DBOSQueueDeduplicatedError:
+            return {"status": "already processing"}
+```
+
+Deduplication behavior:
+- If a workflow with the same deduplication ID is `ENQUEUED` or `PENDING`, new enqueue raises `DBOSQueueDeduplicatedError`
+- Once the workflow completes, a new workflow with the same ID can be enqueued
+- Deduplication is per-queue (same ID can exist in different queues)
+
+Use cases:
+- One active task per user
+- Preventing duplicate job submissions
+- Rate limiting by entity
+
+Reference: [Queue Deduplication](https://docs.dbos.dev/python/tutorials/queue-tutorial#deduplication)

skills/dbos-python/references/queue-listening.md

@@ -0,0 +1,64 @@
+---
+title: Control Which Queues a Worker Listens To
+impact: HIGH
+impactDescription: Enables heterogeneous worker pools (CPU/GPU)
+tags: queue, listen, worker, heterogeneous
+---
+
+## Control Which Queues a Worker Listens To
+
+Use `DBOS.listen_queues()` to make a process only handle specific queues. Useful for CPU vs GPU workers.
+
+**Incorrect (all workers handle all queues):**
+
+```python
+cpu_queue = Queue("cpu_tasks")
+gpu_queue = Queue("gpu_tasks")
+
+# Every worker processes both queues
+# GPU tasks may run on CPU-only machines!
+if __name__ == "__main__":
+    DBOS(config=config)
+    DBOS.launch()
+```
+
+**Correct (workers listen to specific queues):**
+
+```python
+from dbos import DBOS, DBOSConfig, Queue
+
+cpu_queue = Queue("cpu_queue")
+gpu_queue = Queue("gpu_queue")
+
+@DBOS.workflow()
+def cpu_task(data):
+    pass
+
+@DBOS.workflow()
+def gpu_task(data):
+    pass
+
+if __name__ == "__main__":
+    worker_type = os.environ.get("WORKER_TYPE")  # "cpu" or "gpu"
+    config: DBOSConfig = {"name": "worker"}
+    DBOS(config=config)
+
+    if worker_type == "gpu":
+        DBOS.listen_queues([gpu_queue])
+    elif worker_type == "cpu":
+        DBOS.listen_queues([cpu_queue])
+
+    DBOS.launch()
+```
+
+Key points:
+- Call `DBOS.listen_queues()` **before** `DBOS.launch()`
+- Workers can still **enqueue** to any queue, just won't **dequeue** from others
+- By default, workers listen to all declared queues
+
+Use cases:
+- CPU vs GPU workers
+- Memory-intensive vs lightweight tasks
+- Geographic task routing
+
+Reference: [Explicit Queue Listening](https://docs.dbos.dev/python/tutorials/queue-tutorial#explicit-queue-listening)

skills/dbos-python/references/queue-partitioning.md

@@ -0,0 +1,62 @@
+---
+title: Partition Queues for Per-Entity Limits
+impact: HIGH
+impactDescription: Enables per-user or per-entity flow control
+tags: queue, partition, per-user, flow-control
+---
+
+## Partition Queues for Per-Entity Limits
+
+Partitioned queues apply flow control limits per partition, not globally. Useful for per-user or per-entity concurrency limits.
+
+**Incorrect (global limit affects all users):**
+
+```python
+queue = Queue("user_tasks", concurrency=1)  # Only 1 task total
+
+def handle_user_task(user_id, task):
+    # One user blocks all other users!
+    queue.enqueue(process_task, task)
+```
+
+**Correct (per-user limits with partitioning):**
+
+```python
+from dbos import Queue, SetEnqueueOptions
+
+# Partition queue with concurrency=1 per partition
+queue = Queue("user_tasks", partition_queue=True, concurrency=1)
+
+@DBOS.workflow()
+def process_task(task):
+    pass
+
+def handle_user_task(user_id: str, task):
+    # Each user gets their own "subqueue" with concurrency=1
+    with SetEnqueueOptions(queue_partition_key=user_id):
+        queue.enqueue(process_task, task)
+```
+
+For both per-partition AND global limits, use two-level queueing:
+
+```python
+# Global limit of 5 concurrent tasks
+global_queue = Queue("global_queue", concurrency=5)
+# Per-user limit of 1 concurrent task
+user_queue = Queue("user_queue", partition_queue=True, concurrency=1)
+
+def handle_task(user_id: str, task):
+    with SetEnqueueOptions(queue_partition_key=user_id):
+        user_queue.enqueue(concurrency_manager, task)
+
+@DBOS.workflow()
+def concurrency_manager(task):
+    # Enforces global limit
+    return global_queue.enqueue(process_task, task).get_result()
+
+@DBOS.workflow()
+def process_task(task):
+    pass
+```
+
+Reference: [Partitioning Queues](https://docs.dbos.dev/python/tutorials/queue-tutorial#partitioning-queues)

skills/dbos-python/references/queue-priority.md

@@ -0,0 +1,62 @@
+---
+title: Set Queue Priority for Workflows
+impact: HIGH
+impactDescription: Ensures important work runs first
+tags: queue, priority, ordering, scheduling
+---
+
+## Set Queue Priority for Workflows
+
+Use priority to control which workflows run first. Lower numbers = higher priority.
+
+**Incorrect (no priority control):**
+
+```python
+queue = Queue("tasks")
+
+# All tasks treated equally - urgent tasks may wait
+for task in tasks:
+    queue.enqueue(process_task, task)
+```
+
+**Correct (with priority):**
+
+```python
+from dbos import Queue, SetEnqueueOptions
+
+# Must enable priority on the queue
+queue = Queue("tasks", priority_enabled=True)
+
+@DBOS.workflow()
+def process_task(task):
+    pass
+
+def enqueue_task(task, is_urgent: bool):
+    # Priority 1 = highest, runs before priority 10
+    priority = 1 if is_urgent else 10
+    with SetEnqueueOptions(priority=priority):
+        queue.enqueue(process_task, task)
+```
+
+Priority behavior:
+- Range: 1 to 2,147,483,647 (lower = higher priority)
+- Workflows without priority have highest priority (run first)
+- Same priority = FIFO order
+- Must set `priority_enabled=True` on queue
+
+Example with multiple priority levels:
+
+```python
+queue = Queue("jobs", priority_enabled=True)
+
+PRIORITY_CRITICAL = 1
+PRIORITY_HIGH = 10
+PRIORITY_NORMAL = 100
+PRIORITY_LOW = 1000
+
+def enqueue_job(job, level):
+    with SetEnqueueOptions(priority=level):
+        queue.enqueue(process_job, job)
+```
+
+Reference: [Queue Priority](https://docs.dbos.dev/python/tutorials/queue-tutorial#priority)

skills/dbos-python/references/queue-rate-limiting.md

@@ -0,0 +1,55 @@
+---
+title: Rate Limit Queue Execution
+impact: HIGH
+impactDescription: Prevents hitting API rate limits
+tags: queue, rate-limit, api, throttle
+---
+
+## Rate Limit Queue Execution
+
+Use rate limits when working with rate-limited APIs (like LLM APIs). Limits are global across all processes.
+
+**Incorrect (no rate limiting):**
+
+```python
+queue = Queue("llm_tasks")
+
+@DBOS.step()
+def call_llm(prompt):
+    # May hit rate limits if too many calls
+    return openai.chat.completions.create(...)
+```
+
+**Correct (with rate limit):**
+
+```python
+# Max 50 tasks started per 30 seconds
+queue = Queue("llm_tasks", limiter={"limit": 50, "period": 30})
+
+@DBOS.step()
+def call_llm(prompt):
+    return openai.chat.completions.create(...)
+
+@DBOS.workflow()
+def process_prompts(prompts):
+    handles = []
+    for prompt in prompts:
+        # Queue enforces rate limit
+        handle = queue.enqueue(call_llm, prompt)
+        handles.append(handle)
+    return [h.get_result() for h in handles]
+```
+
+Rate limit parameters:
+- `limit`: Maximum number of functions to start in the period
+- `period`: Time period in seconds
+
+Rate limits can be combined with concurrency limits:
+
+```python
+queue = Queue("api_tasks",
+    worker_concurrency=5,
+    limiter={"limit": 100, "period": 60})
+```
+
+Reference: [Rate Limiting](https://docs.dbos.dev/python/tutorials/queue-tutorial#rate-limiting)