Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
| Use when designing RESTful API endpoints in FastAPI or Python projects. response formatting with JSON schemas, status code selection, pagination, filtering, or sorting parameters.
| Use when writing tests for backend APIs or frontend flows. TestClient setup, mock data factories, or test coverage analysis.
| Use when implementing authentication - login/signup forms, session management, protected routes, or role-based access control. NOT when non-auth UI, plain data fetching, or unrelated backend logic.
| Use when integrating OpenAI/ChatKit chat widgets into Next.js/React applications. setting up authenticated chat access, or customizing widget branding.
| Use when integrating Context7 (knowledge/context store) for document ingestion, semantic search, or scoped context retrieval. or providing AI with document-grounded context.
| Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new skill, update an existing skill, or need guidance on skill design patterns, SKILL.md format, or verify.py implementation. NOT when just using existing skills (use those skills directly).
| Use when implementing data validation for API payloads, form inputs, or database writes. field constraints, or request/response schemas.
| Use when setting up database connections, especially for Neon PostgreSQL. connection string management, SSL configuration, or SQLAlchemy engine setup.
| Use when setting up Alembic migrations or making database schema changes. rolling back changes, or creating data migrations.
| Use when setting up environment configuration, loading .env files, or managing application settings across environments. configuration validation, or secret management.
| Use when implementing structured error handling in backend or frontend code. error logging, user-friendly error messages, or API error responses.
| Use when creating FastAPI backend applications - route handlers, dependencies, CORS config, or Pydantic models. NOT when frontend logic, non-Python backends, or unrelated server-side code.
| Use when working with Next.js App Router tasks - creating pages in /app/, setting up dynamic routes ([id]/page.tsx), implementing nested layouts/templates (layout.tsx), optimizing Server/Client components, or building ERP role-based pages (admin/teacher/student dashboards). Auto-use for all /app/ directory operations, dynamic routing, and App Router-specific features.
| Use when implementing JWT authentication in FastAPI or Python projects. access token creation, token decoding, or role-based auth.
| Use when creating UI components in React - functional components, hooks, custom hooks, or component composition patterns. NOT when backend logic, API routes, or non-React frameworks are involved.
| Use when creating SQLModel database models, CRUD operations, queries with joins, or relationships. NOT when non-database operations, plain SQL, or unrelated data handling.
| Use when styling UI components or layouts with Tailwind CSS - mobile-first design, responsive utilities, custom themes, or component styling. NOT when plain CSS, CSS-in-JS (styled-components), or non-Tailwind frameworks are involved.
| Use when deploying Next.js applications to Vercel. custom domain configuration, API proxy setup, or deployment troubleshooting.
AI collaboration workflow plugin - Implements automated collaborative development process between Claude and Copilot through structured 5-stage workflow
Direct access to GitHub Copilot MCP server tools for AI-powered development assistance
Generic AIOps (AI for IT Operations) patterns and best practices for 2025. Provides comprehensive implementation strategies for intelligent monitoring, automation, incident response, and observability across any infrastructure. Framework-agnostic approach supporting multiple monitoring platforms, cloud providers, and automation tools.
Modern API development patterns for building high-performance, scalable web services. Expert in async/await patterns, REST/GraphQL APIs, middleware, error handling, rate limiting, OpenAPI documentation, testing, and production optimizations. Framework-agnostic patterns that work with Python, Node.js, Go, and other languages.
Modern authentication and security patterns for web applications. Expert in JWT tokens, OAuth2 flows, session management, RBAC, MFA, API security, and zero-trust architectures. Framework-agnostic patterns that work with any tech stack.
Generic Cloud-Native Deployment and Infrastructure as Code patterns for 2025. Provides comprehensive implementation strategies for multi-cloud deployments, GitOps workflows, progressive delivery, and platform engineering. Framework-agnostic approach supporting any cloud provider, deployment tool, and orchestration platform.
Extracts and writes project constitutional information from documents (PDF, MD, TXT). Focuses exclusively on identifying principles, values, governance structures, and formatting them into a proper project constitution.
Universal database operations skill for modern applications. Expert in SQLModel/SQLAlchemy patterns, async database operations, connection pooling, migrations, performance optimization, and multi-database support (PostgreSQL, MySQL, SQLite). Provides production-ready patterns for any database-driven application.
Master containerization and orchestration with security-first approach. Expert in Docker multi-stage builds, Kubernetes zero-trust deployments, security hardening, GitOps workflows, and production-ready patterns for cloud-native applications. Includes 2025 best practices from CNCF and major cloud providers.
Generic Event-Driven Architecture patterns with Kafka, Dapr, and modern messaging systems. Provides reusable patterns for building scalable, resilient event-driven microservices. Framework-agnostic implementation supporting multiple message brokers, state stores, and event patterns. Follows 2025 best practices for distributed systems.
Generic MCP (Model Context Protocol) server development patterns. Provides reusable architecture and best practices for building MCP servers that expose any domain-specific operations as tools for AI agents. Framework-agnostic implementation supporting async operations, error handling, and enterprise-grade features.
| Azure Monitor OpenTelemetry Exporter for Java. Export OpenTelemetry traces, metrics, and logs to Azure Monitor/Application Insights.
React Native coding patterns, best practices, and common solutions for mobile development. Use when implementing features or refactoring code.
Debug React Native apps including metro bundler issues, native errors, performance problems, and crash analysis. Use when troubleshooting errors or investigating issues.
Write and run tests for React Native apps using Jest and React Native Testing Library. Use when creating tests, debugging failures, or setting up test infrastructure.
Set up project infrastructure including TypeScript, database, state management, navigation, and testing. Use when initializing new features or configuring development environment.
Build and manage React Native/Expo mobile apps including project setup, development workflows, and platform-specific guidance. Use when working on mobile app development, configuration, or running apps.
Collaborative programming framework for production-ready development. Use when starting features, writing code, handling security/errors, adding comments, discussing requirements, or encountering knowledge gaps. Applies to all development tasks for clear, safe, maintainable code.
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, or needs skill creation guidelines. Provides structure, naming conventions, description writing, and quality checklist.
MUST use this skill when user asks to commit, create commit, save work, or mentions "커밋". This skill OVERRIDES default git commit behavior. Creates commits following Conventional Commits format with emoji + type/scope/subject (✨ feat, 🐛 fix, ♻️ refactor, etc).
MUST use this skill when user asks to create PR, open pull request, submit for review, or mentions "PR 생성/만들기". This skill OVERRIDES default PR creation behavior. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels.
MUST use this skill when user asks to merge PR, close PR, finalize PR, or mentions "PR 머지/병합". This skill OVERRIDES default PR merge behavior. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.
MUST use this skill when user asks to resolve PR comments, handle review feedback, fix review comments, or mentions "리뷰 코멘트/피드백". This skill OVERRIDES default behavior. Fetches comments via GitHub CLI, classifies by severity, applies fixes with user confirmation, commits with proper format, replies to threads.
PDF/이미지를 Claude vision으로 OCR하여 마크다운 변환. MUST use this skill when user: (1) asks to convert PDF/image to markdown, (2) asks to OCR any file, (3) sends PDF/image file and asks to extract/read/변환/추출, (4) mentions 'OCR', 'PDF 변환', '이미지 변환', '텍스트 추출'. This skill uses Task agent to protect main context - NEVER process files directly in main context.
AppFlowy Cloud/GoTrue API 的认证与调用流程（获取 token、workspace/文档/数据库/搜索等）。在本仓库用 Python 编写或调试 AppFlowy API 客户端、脚本、自动化或排查接口问题时使用。
Apple-inspired clean, minimal, premium UI design. Use when building modern interfaces requiring exceptional UX, clean aesthetics, or Apple-like polish. Triggers on: clean UI, modern design, Apple style, minimal, premium, user-friendly, UX.
Validates type consistency across Rust, TypeScript, PostgreSQL boundaries. Use when reviewing code, debugging type mismatches, or validating API contracts. Triggers on: check consistency, validate types, find mismatches, cross-language.
Comprehensive code review expertise. Use when reviewing code, evaluating architecture, or assessing quality. Triggers on review, evaluate, assess, audit, code quality, best practices.
Orchestrates pitfall prevention skills for common development issues. Auto-triggered during code review to check for TanStack Query, Drizzle ORM, Express API, React, WebSocket, blockchain RPC, and security pitfalls.
DeFi protocol expert ensuring correct data formats, types, denominations, and API structures. MUST be consulted before writing ANY protocol integration code. Triggers on ANY mention of Aave, Compound, Uniswap, Curve, Balancer, or DeFi terms like liquidation, swap, flash loan, health factor.
Expert knowledge for DeFi/MEV bot development including critical pitfalls, backtesting realities, AMM mechanics, MEV extraction strategies, and production failure modes
Manages expansion of tokens, pools, chains, networks, and DEXes across the codebase. Use when adding new tokens, protocols, chains, networks, or updating existing DeFi registry data. Triggers on add token, new coin, add protocol, new DEX, add chain, new network, add RPC, update address.
Structured JSON logging with correlation IDs for multi-service systems. Use when implementing logging, debugging failures, or tracing errors across services. Triggers on: add logging, error handling, debug failures, trace errors.
Comprehensive code review using all available skills. Use before committing or when you want a thorough analysis of changes. Triggers on review code, check changes, full review, pre-commit review.
Runs Claude in a retry loop until tests pass or task completes. Use for TDD loops, overnight builds, or any task needing repeated iteration until success. Triggers on: loop until done, keep trying, retry until pass, TDD loop, iterate until tests pass.
Per-call and aggregated latency tracking for MEV infrastructure. Use when implementing performance monitoring or debugging slow operations. Triggers on: latency, timing, performance, slow, speed, instrumentation.
DEX liquidity analysis and slippage estimation for MEV trading. Use when implementing swaps, route selection, or position sizing. Triggers on: liquidity, slippage, price impact, depth, AMM math, Uniswap, Curve.
Blockchain RPC error handling, gas estimation, multi-chain config, and transaction management. Use when interacting with smart contracts, estimating gas, or managing transactions. Triggers on: RPC, contract call, gas, multicall, nonce, transaction, revert.
Drizzle ORM patterns and migration safety rules. Use when defining schemas, running migrations, or debugging database issues. Triggers on: Drizzle, schema, migration, db:push, $inferSelect, array column.
Express API conventions and storage patterns. Use when building REST APIs, defining routes, or implementing storage interfaces. Triggers on: Express, router, API route, status code, storage interface.
React component patterns, forms, accessibility, and responsive design. Use when building React components, handling forms, or ensuring accessibility. Triggers on: React component, useEffect, form validation, a11y, responsive, Error Boundary.
Security patterns for session keys, caching, logging, and environment variables. Use when implementing authentication, caching sensitive data, or setting up logging. Triggers on: session key, private key, cache, logging, secrets, environment variable.
Claude Skills — questions
Answers built from the skills we actually parsed.