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...
markdown-plus-author
by AllanYiinWrite or revise Markdown+ documents — plain Markdown that stays valid in any markdown viewer while adding bullet-list blocks with `**#id**` headers, inline-code `key:value` metadata, and viewer-side projection cues. Use when the user asks to write or rewrite a dev note, decision record, research report, tech spec, status report, executive brief, runbook, ADR, status report, or any AI-readable structured document; or when the user asks to convert plain Markdown or existing HTML into Markdown+. Do not use for slide decks, email drafts, or one-off short replies. Successful output is a single CommonMark-valid Markdown file whose blocks can be queried by a parser and projected into human-friendly HTML, with no `:::` fences, no raw HTML wrappers, no base64, code fences and ASCII trees preserved verbatim, and a prose companion for every figure/table/chart.
toolanything-mcp-router
by AllanYiin適用於使用者要求建立、包裝、暴露、擴充或驗證可重用的 MCP/OpenAI tool，或工具來源是 Python function、class method、HTTP API、SQL query、model inference。Use when user asks for ToolAnything-vs-smaller-solution routing, `@tool` vs source-based API choice, or the shortest verified path; do not prefer it only when the work is a throwaway MCP-only prototype backed by a single local Python callable with no doctor, inspect, CLI, shared-server, or source-based needs.
toolanything-platform-ops
by AllanYiin適用於使用者要求安裝內附 ToolAnything wheel、同步 Codex/OpenClaw/Claude 本地 skills、更新 AGENTS 規則、管理 shared custom-tool server、固定 port 或設定 auto-start，且 `toolanything-mcp-router` 已先判定應採用 ToolAnything。It is the heavy operational skill for bundled installs, canonical server governance, and host rollout; it is not the first routing entrypoint for simple tool wrapping.
toolanything-tool-wrapper
by AllanYiin適用於使用者仍用舊名稱『ToolAnything tool wrapper』提問時的相容轉接。Treat it as a legacy compatibility alias instead of the default entrypoint: route reusable MCP/OpenAI tool work to `toolanything-mcp-router`, and route local bundle installation, host sync, AGENTS updates, shared custom-server policy, or auto-start work to `toolanything-platform-ops`.
spreadsheet-workflows
by AllanYiin報表 xlsx（整理、公式、檢核）。當使用者需要建立、編輯或分析 Excel 試算表時使用。
research-brief
by AllanYiin網頁/文件摘要、研究整理。當使用者需要對某個主題進行研究、收集資訊並生成摘要時使用。
skill-creator-advanced
by AllanYiin當使用者要建立、改版、測試、評估或發布 skill 時使用。涵蓋 description 優化、evals、benchmark、邊界管理與打包流程。
slide-content-planner
by AllanYiin當使用者要規劃投影片或簡報內容時使用。輸出逐頁大綱、關鍵訊息、證據需求、視覺重點與版面動線。
spec-organizer
by AllanYiin在使用者要把模糊想法整理成可開發 spec 時使用。常見觸發像「整理需求成 spec」「補驗收條件」「拆分階段開發計畫」。輸出技術規格、白話規格與可直接貼用於 Codex / Claude Code 的分階段 instructions；不直接代替正式文件發布。
spec-to-tasks
by AllanYiin將一份需求規格拆成可執行任務（含驗收條件）。當使用者提供產品需求、功能規格或使用者故事時，將其分解成具體的開發任務。
vibe-coding-guidelines
by AllanYiin在非程式開發者要用 vibe coding 與 coding agent 協作時使用。常見觸發像「幫我整理開發準則」「定義交付邊界」「規劃驗證方式」。輸出需求表達、邊界與風險控管準則；不直接取代實作。
web-search-strategy
by AllanYiin當使用者要上網查資料、把模糊研究意圖拆成多輪搜尋查詢、限定網站或檔案類型、找官方來源，或改善 Google/Bing 搜尋品質時使用。將問題改寫成 2-5 組高辨識度查詢，結合 site、引號、排除詞、檔案類型、搜尋引擎切換、結果去重與二次搜尋，再整理可信來源、未解空缺與下一輪查詢方向。
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.