Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
metabase
by j2h4uThis skill should be used when the user asks to "check metabase status", "inspect metabase", "find duplicate cards", "diagnose metabase issues", "backup metabase", "restore metabase backup", "create metabase card", "create metabase dashboard", "add card to dashboard", "run metabase query", mentions "metabase dashboards", "metabase cards", or needs to manage Metabase content via CLI.
infocompressor
by j2h4uThis skill should be used when the user asks to "compress this", "make it shorter but keep everything", "create a cheat sheet", "dense summary", "reference format", "compact version", "information-dense", "condense this document". NOT for casual summaries—only when user explicitly wants maximum density with zero data loss.
meeting-insights-analyzer
by j2h4uThis skill should be used when the user asks to "analyze meeting transcripts", "review my communication patterns", "tell me when I avoided conflict", "analyze my speaking ratio", "identify filler words in meetings", "review my facilitation style", "track communication improvement", "analyze leadership patterns", or mentions analyzing recordings from Granola, Zoom, Google Meet, or other transcription services. Uncovers behavioral patterns like conflict avoidance, interruptions, filler words, and listening effectiveness from meeting transcripts.
mastering-typescript
by j2h4uThis skill should be used when the user asks to "write typescript", "configure typescript project", "add type hints", "use generics", "migrate to typescript", "set up vite with typescript", "implement type-safe patterns", "use satisfies operator", "configure eslint for typescript", or needs guidance on enterprise TypeScript 5.9+ development with React, NestJS, or LangChain.js.
typescript-unbloating
by j2h4uThis skill should be used when the user asks to "simplify typescript code", "simplify javascript", "refactor this js code", "unbloat javascript", "unbloat typescript", "clean up this react component", "reduce complexity in typescript", "simplify tsx", or mentions code simplification for JS/TS/React/TSX files.
web-artifacts-builder
by j2h4uThis skill should be used when the user asks to "create React artifact", "build complex artifact", "use shadcn/ui", "create multi-component artifact", "build dashboard artifact", "create interactive app", "use Tailwind CSS artifact", "bundle React to single HTML", mentions "artifact with state management", "artifact with routing", or needs to build elaborate, multi-component claude.ai HTML artifacts using React 18, TypeScript, Vite, Tailwind CSS, and shadcn/ui. Not for simple single-file HTML/JSX artifacts.
web-design-guidelines
by j2h4uThis skill should be used when the user asks to "review my UI", "check accessibility", "audit design", "review UX", "check against Web Interface Guidelines", "review my site", "check best practices", "audit web interface", "review frontend code", "check UI compliance", or needs to review UI code for compliance with Vercel's Web Interface Guidelines covering accessibility, performance, semantic HTML, ARIA patterns, responsive design, and modern web best practices.
dignified-bash
by j2h4uThis skill should be used when the user asks to "write bash script", "create shell script", "review bash code", "write hook", "create systemd service script", "fix shellcheck warnings", "improve bash script", mentions "bash", "shell", ".sh files", or works with any shell scripting including hooks and CLI tools. Enforces bash purist style with strict mode, die() function, proper variable declarations, assertion comments, result comments, shellcheck compliance, and structured function layout.
dignified-python
by j2h4uThis skill should be used when the user asks to "write Python code", "review Python", "refactor Python", "fix Python types", "improve error handling", "use pathlib", "create ABC interface", "fix mypy errors", "add type hints", "make this pythonic", "LBYL vs EAFP", or mentions "Python", ".py files", "type annotations", "pathlib", "subprocess", or Python CLI patterns. Provides opinionated production Python standards with automatic version detection (3.10-3.13), modern type syntax, explicit condition checks where practical, pathlib operations, interface guidance, and pragmatic production patterns.
kaizen
by j2h4uThis skill should be used when the user asks about "continuous improvement", "avoid over-engineering", "simplest solution", "YAGNI", "incremental improvements", "error proofing", "poka-yoke", "premature optimization", "iterative development", "make invalid states unrepresentable", "fail fast", "standardized work patterns", or needs guidance on applying kaizen principles including continuous improvement, error-proofing by design (poka-yoke), following established patterns, and building just-in-time (JIT) without premature abstraction or optimization.
software-architecture
by j2h4uThis skill should be used when the user asks about "clean architecture", "domain driven design", "DDD", "should I use a library or write custom code", "library vs custom implementation", "avoid utils/helpers folders", "separation of concerns", "bounded contexts", "architecture best practices", "code organization patterns", "anti-patterns to avoid", requests architectural review, or wants guidance on structuring code following DDD and Clean Architecture principles with library-first approach.
postgres-patterns
by j2h4uThis skill should be used when the user asks to "write PostgreSQL query", "optimize postgres query", "use LATERAL join", "use CTE", "window functions in postgres", "explain analyze", "postgres performance", "rewrite SQL query", "postgres local variables", "advanced SQL patterns", mentions "PostgreSQL", "psql", or needs guidance on idiomatic PostgreSQL query patterns beyond basic SELECT/JOIN.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.