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.
Comprehensive knowledge about vulnerability exploitation and initial access. Provides expertise on finding and adapting exploits, adapting proof-of-concepts, gaining shells, and capturing user flags. Covers reverse shells, file uploads, SQL injection, and RCE vulnerabilities.
Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)
Comprehensive knowledge about Linux privilege escalation. Provides methodologies for enumerating and exploiting privesc vectors including SUID binaries, sudo permissions, capabilities, kernel exploits, cron jobs, and common misconfigurations. Includes systematic approach to capturing root flags.
Comprehensive knowledge about network reconnaissance and service enumeration. Provides methodologies for port scanning, service fingerprinting, web directory discovery, and vulnerability identification. Includes best practices for structured data collection.
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
A type-safe, Redis-backed caching library for Remix applications with SSE-based real-time invalidation, stale-while-revalidate, pattern matching, and automatic React revalidation. Use when working with Remix caching, Redis, cache invalidation, implementing caching strategies, or real-time data synchronization in Remix apps.
Format git commit messages combining Conventional Commits summary lines with Linux kernel-style bodies. Use when writing, reviewing, or formatting commit messages.
Manage features.yml for tracking requirements and progress; use proactively ONLY when features.yml already exists, or invoke manually to create one; complements TodoWrite for persistent project state.
Guide for breaking changes into logical, atomic commits using interactive staging. Use when committing changes that span multiple concerns, when needing to stage parts of files (hunks), when asked to create well-organized commit history, or when changes should be split into multiple commits.
Document software architecture using ARCHITECTURE.md and docs/*.md files with Mermaid diagrams. Use proactively when ARCHITECTURE.md exists in project root, or invoke to create initial architecture documentation. Covers system design, data flows, component relationships, and code organization with references to key entry points and abstractions.
Guide for writing effective log messages using wide events / canonical log lines. Use when writing logging code, adding instrumentation, improving observability, or reviewing log statements. Teaches high-cardinality, high-dimensionality structured logging that enables debugging.
Enforces strict waterfall development workflow with phase gates. Use when (1) features.yml exists in project root, (2) user asks to implement/develop/build a feature, (3) user explicitly requests waterfall workflow. Creates features.yml if missing when invoked.
This skill should be used when the user asks to "create a packmol input", "pack molecules with packmol", "solvate a protein", "build an initial configuration", "setup molecular dynamics", or discusses molecular packing, solvation, or building simulation starting structures.
How to properly create Claude Code skills - teaches global vs project-local, naming conventions, and proper file structure
**Use MCP repo-map tools when:** - Searching for symbols by name pattern (faster than Grep) - Getting all symbols in a file (faster than Read + parsing)
Context management tools for Claude Code - provides intelligent codebase mapping with Python, Rust, and C++ parsing, duplicate detection, and MCP-powered symbol queries. Use this skill when working with large codebases that need automated indexing and context management.
Formik form handling with validation patterns. Use when building forms, implementing validation, or handling form submission.
GraphQL queries, mutations, and code generation patterns. Use when creating GraphQL operations, working with Apollo Client, or generating types.
Comprehensive audit of Expo/React Native app API integration layer. Use when asked to: (1) Review API interactions, auth handling, or token management, (2) Find hardcoded data or screens bypassing API, (3) Verify user interactions properly sync to backend, (4) Analyze offline behavior and caching, (5) Audit Orval/OpenAPI code generation, (6) Check for API security issues. Supports TanStack Query, Zustand, axios, Expo Router, expo-secure-store, and expo-constants patterns.
Building and deploying Expo React Native apps to iOS. Use when configuring EAS Build, submitting to TestFlight, App Store deployment, managing certificates, or troubleshooting build issues.
PostgreSQL patterns for reviewing migrations and writing efficient queries. Use when reviewing Alembic migrations, optimizing queries, or debugging database issues.
High-performance PostgreSQL patterns. Use when optimizing queries, designing for scale, or debugging performance issues.
Alembic migration patterns for PostgreSQL. Use when creating migrations, reviewing autogenerated migrations, or handling schema changes safely.
Async/await patterns for FastAPI and SQLAlchemy. Use when working with async code, database sessions, concurrent operations, or debugging async issues in Python.
FastAPI patterns for API design. Use when creating endpoints, handling dependencies, error handling, or working with OpenAPI schemas.
Observability patterns for Python backends. Use when adding logging, metrics, tracing, or debugging production issues.
Pydantic v2 patterns for validation and serialization. Use when creating schemas, validating data, or working with request/response models.
SQLModel and async SQLAlchemy patterns. Use when working with database models, queries, relationships, or debugging ORM issues.
Async testing patterns with pytest-asyncio. Use when writing tests, mocking async code, testing database operations, or debugging test failures.
Async/await correctness in React with Zustand. Use when debugging race conditions, missing awaits, floating promises, or async timing issues. Works for both React web and React Native.
Logging, error messages, and debugging patterns for React. Use when adding logging, designing error messages, debugging production issues, or improving code observability. Works for both React web and React Native.
Performance optimization for React web applications. Use when optimizing renders, implementing virtualization, memoizing components, or debugging performance issues.
Complex multi-step operations in React. Use when implementing flows with multiple async steps, state machine patterns, or debugging flow ordering issues. Works for both React web and React Native.
Testing patterns for React with Jest and React Testing Library. Use when writing tests, mocking modules, testing Zustand stores, or debugging test failures in React web applications.
Zustand state management patterns for React. Use when working with Zustand stores, debugging state timing issues, or implementing async actions. Works for both React web and React Native.
Async/await correctness in React Native with Zustand. Use when debugging race conditions, missing awaits, floating promises, or async timing issues in Expo/React Native apps.
React Native authentication patterns for Expo apps. Use when implementing login flows, Google/Apple sign-in, token management, session handling, or debugging auth issues in Expo/React Native.
Native iOS features in Expo React Native apps. Use when implementing camera, push notifications, haptics, permissions, device sensors, or other native APIs in Expo.
Expo Router navigation patterns for React Native. Use when implementing navigation, routing, deep links, tab bars, modals, or handling navigation state in Expo apps.
Logging, error messages, and debugging patterns for React Native. Use when adding logging, designing error messages, debugging production issues, or improving code observability.
Performance optimization for React Native. Use when optimizing lists, preventing re-renders, memoizing components, or debugging performance issues in Expo/React Native apps.
Complex multi-step operations in React Native. Use when implementing flows with multiple async steps, state machine patterns, or debugging flow ordering issues.
Styling patterns for React Native with NativeWind and BrandColors. Use when working with styles, themes, colors, responsive layouts, or platform-specific UI in Expo/React Native.
Testing patterns for React Native with Jest and React Native Testing Library. Use when writing tests, mocking Expo modules, testing Zustand stores, or debugging test failures.
Zustand state management patterns for React Native. Use when working with Zustand stores, debugging state timing issues, or implementing async actions in Zustand.
Authentication patterns for React web applications. Use when implementing login flows, OAuth, JWT handling, session management, or protected routes in React web apps.
Building and deploying React web applications. Use when configuring builds, deploying to Vercel/Netlify, setting up CI/CD, Docker, or managing environments.
Navigation and routing patterns for React web applications. Use when implementing React Router, Next.js routing, deep links, or handling navigation state.
Styling patterns for React web applications. Use when working with Tailwind CSS, CSS Modules, theming, responsive design, or component styling.
功能强大的开源网页抓取和数据处理工具，支持6种工作模式，包括截图、PDF导出和智能爬取
多功能网页抓取和数据提取工具，支持同步抓取、搜索、网站地图获取和异步爬取
智谱AI的视觉语言模型，用于图像分析、内容识别和视觉问答
在沙盒环境中执行Python代码，用于数据分析、可视化和生成Excel、Word、PDF等文件。支持数据清洗、统计分析、机器学习、图表生成、文档自动化等复杂工作流。
国际象棋引擎分析工具，提供最佳走法推荐、局面评估和多种走法选择分析。支持FEN字符串直接输入分析。
使用Tavily API进行网络搜索，获取实时信息、回答问题或研究主题
恢复之前保存的会话上下文。列出所有待处理的 session，读取选定 session 的任务信息，更新进度，任务全部完成后删除文件。
当用户发送"换窗口处理-"时调用。总结当前窗口的上下文信息、已完成任务、未完成任务，保存到 docs/context-sessions/ 目录，便于新窗口恢复。
洞穴探险 - Stella发现一个深邃的洞穴系统,深入探索发现bioluminescent晶体、地下水源和神秘的古老痕迹
日常科研 - Stella建立临时研究站,进行系统的科学观察和实验,享受科学家的日常
紧急求救 - 飞船坠毁后与Stella的首次联系,帮助她评估损伤并制定初步生存计划
Claude Skills — questions
Answers built from the skills we actually parsed.