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...
persona-sommelier
by sylvanus4Channel a Master Sommelier-style advisor: structured tasting, terroir-led recommendations, food pairing logic, service ritual, and story through provenance. Use for wine lists, pairings, cellaring, and hospitality training.
china-market-localization-strategist
by sylvanus4Full-stack China market localization expert transforming real-time trend signals into executable GTM strategies across Douyin, Xiaohongshu, WeChat, Bilibili, Weibo, Zhihu, and e-commerce platforms. Engineers closed-loop systems: signal detection -> insight extraction -> action planning -> measurement -> iteration. Use when "China market entry strategy", "中国市场进入"; "China trend intelligence", "中国热搜分析"; "Cross-platform China marketing", "中国 플랫폼 전략"; "China localization", "문화 현지화", "중국 시장 현지화"; "GTM plan for China market", "중국 GTM 전략"; "Trend-to-action analysis", "트렌드 분석 후 실행"; "China seasonal marketing (618, Double 11, CNY)"; "One-person-company China strategy", "一人公司 중국 전략" Do NOT use for individual platform strategy (use the specific china-* platform skill); general market research without China focus (use pm-market-research); global GTM strategy (use pm-go-to-market); Korea/Japan localization (handle directly); cross-border e-commerce operations (use china-cross-border-ecommerce)
role-strategist
by sylvanus4Convert a validated customer pain into 5 irresistible lead-magnet concepts, score each on buildability × desirability × uniqueness, and output a ranked recommendation with the winning concept's full spec. Consumes role-researcher's Pain Validation Report as primary input. Korean triggers: "리드 매그넷 전략", "무료 자료 아이디어", "리드 매그넷 5안", "전략가 모드", "lead magnet brainstorm". Do NOT use for email sequence/funnel design (use role-copywriter), landing page implementation (use role-builder), paid channel selection (use goose-paid-channel-prioritizer), or full GTM strategy without pain validation (use pm-go-to-market).
persona-peterson
by sylvanus4Channel Jordan Peterson-style synthesis of clinical psychology, mythic narrative, and responsibility ethics: order versus chaos, incremental repair, and meaning through burden carried well. Triggers: peterson mode, personal responsibility, confront chaos.
persona-peterson
by sylvanus4Channel Jordan Peterson-style synthesis of clinical psychology, mythic narrative, and responsibility ethics: order versus chaos, incremental repair, and meaning through burden carried well. Triggers: peterson mode, personal responsibility, confront chaos.
evals-skills
by sylvanus4Orchestrate LLM eval pipeline tasks: audit existing evals, analyze errors in traces, generate synthetic test data, write LLM judge prompts, validate evaluators against human labels, evaluate RAG pipelines, and build annotation interfaces. Based on hamelsmu/evals-skills (50+ company patterns). Use when the user asks for "eval audit", "error analysis", "judge prompt", "validate evaluator", "synthetic data", "evaluate RAG", "annotation interface", "review traces", "evals", or "LLM evaluation". Do NOT use for general code review (use backend-expert or frontend-expert), ML model training, unit testing (use qa-test-expert), or non-LLM evaluation tasks. Korean triggers: "LLM 평가", "eval 파이프라인".
evals-skills
by sylvanus4Orchestrate LLM eval pipeline tasks: audit existing evals, analyze errors in traces, generate synthetic test data, write LLM judge prompts, validate evaluators against human labels, evaluate RAG pipelines, and build annotation interfaces. Based on hamelsmu/evals-skills (50+ company patterns). Use when the user asks for "eval audit", "error analysis", "judge prompt", "validate evaluator", "synthetic data", "evaluate RAG", "annotation interface", "review traces", "evals", or "LLM evaluation". Do NOT use for general code review (use backend-expert or frontend-expert), ML model training, unit testing (use qa-test-expert), or non-LLM evaluation tasks. Korean triggers: "LLM 평가", "eval 파이프라인".
tailwind-design-system
by sylvanus4Build scalable design systems with Tailwind CSS v4, including CSS-first configuration, OKLCH design tokens, CVA-based component variants, compound components, form patterns, responsive grids, dark mode, and native CSS animations. Use when the user asks to "create a component library", "implement design tokens", "build a design system", "standardize UI patterns", "set up Tailwind v4 theming", "create responsive components", "tailwind-design-system", "Tailwind v4 setup", "CVA component", "design system with Tailwind", or wants to build a systematic UI foundation. Do NOT use for building specific UIs from scratch (use anthropic-frontend-design). Do NOT use for polishing existing work (use polish). Do NOT use for Figma-to-code workflows (use figma-dev-pipeline). Do NOT use for TDS (@thakicloud/shared) component usage (follow 03-tds-essentials.mdc). Do NOT use for mobile app design via Sleek (use sleek-design-mobile-apps). Korean triggers: "디자인 시스템", "Tailwind v4", "컴포넌트 라이브러리", "디자인 토큰", "CVA 컴포넌트", "다크 모드 설정", "
tailwind-design-system
by sylvanus4Build scalable design systems with Tailwind CSS v4, including CSS-first configuration, OKLCH design tokens, CVA-based component variants, compound components, form patterns, responsive grids, dark mode, and native CSS animations. Use when the user asks to "create a component library", "implement design tokens", "build a design system", "standardize UI patterns", "set up Tailwind v4 theming", "create responsive components", "tailwind-design-system", "Tailwind v4 setup", "CVA component", "design system with Tailwind", or wants to build a systematic UI foundation. Do NOT use for building specific UIs from scratch (use anthropic-frontend-design). Do NOT use for polishing existing work (use polish). Do NOT use for Figma-to-code workflows (use figma-dev-pipeline). Do NOT use for TDS (@thakicloud/shared) component usage (follow 03-tds-essentials.mdc). Do NOT use for mobile app design via Sleek (use sleek-design-mobile-apps). Korean triggers: "디자인 시스템", "Tailwind v4", "컴포넌트 라이브러리", "디자인 토큰", "CVA 컴포넌트", "다크 모드 설정", "
notebooklm-research
by sylvanus4Run web and Google Drive research through NotebookLM -- start research queries, poll progress, and import discovered sources into notebooks. Use when the user asks to "research a topic in NotebookLM", "start NLM research", "web research and import sources", "Drive research", "deep research in NLM", "find sources for notebook", "discover sources", "import research sources", "research and build notebook", "NLM deep research", "poll research status", "NLM 리서치", "노트북LM 연구", "웹 리서치 시작", "소스 탐색", "리서치 시작", "딥 리서치", "드라이브 검색", "소스 발견", "NLM 웹 리서치", "리서치 결과 가져오기", or any NotebookLM research/discovery workflow. Do NOT use for notebook/source/note CRUD or querying -- use notebooklm. Do NOT use for content generation (audio, video, reports) -- use notebooklm-studio. Do NOT use for general web search without NotebookLM -- use parallel-web-search. Do NOT use for finance-specific web search -- use alphaear-search.
tv-live-data
by sylvanus4Fetch real-time stock prices and global market snapshots via TradingView MCP (`yahoo_price`, `market_snapshot`).
tv-multi-timeframe
by sylvanus4Multi-timeframe technical analysis and candlestick pattern recognition via TradingView MCP (`get_multi_timeframe_analysis`, `advanced_candle_pattern`, `consecutive_candles_scan`).
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.