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...
htmlput
by vincentor通过 HTML 页面展示内容给用户。当需要生成可视化报表、交互式演示、数据展示、富文本页面等内容并分享给用户查看时使用。支持公开和密码保护的私密页面。触发词：发布页面、生成网页、HTML 展示、分享链接、可视化报表。
lark
by vincentor与飞书(Lark)机器人交互 - 发送消息到用户或群聊、@ 功能、监听事件、群聊管理。当用户提到飞书、Lark、发消息、群聊、@ 某人时使用。
notion
by vincentor与 Notion 工作区交互 — 搜索、查找、添加、创建、编辑、更新、删除、导出、查询页面/数据库/内容块/待办事项。当用户提到 Notion 并涉及任何操作（搜索文档、添加数据库行、加 todo、导出 markdown、查询任务状态、记笔记、写会议纪要、配置 token）时使用。这是直接执行 Notion API 操作的 CLI 工具，无需编码。不用于：编写调用 Notion API 的脚本、排查 Notion UI 显示问题、规划迁移方案。
Interact with Gmail - list, read, search emails and download attachments. Use when user asks about emails, inbox, or mail-related tasks.
mac-camera
by vincentorTake a photo using the MacBook's built-in camera and analyze it with Claude's vision. Use this skill whenever the user wants to capture a photo from their webcam/camera, see what's in front of the camera, take a selfie, snap a picture, or visually inspect something using the laptop camera. Also trigger when users say things like "look at this", "what do you see", "take a picture", "use my camera", "capture what's on my desk", or any request that involves using the MacBook's physical camera to see the real world. This is specifically for the built-in laptop camera — not screenshots or screen capture.
idea-brainstorm
by vincentorUse this skill when a user shares multiple ideas, features, or rough concepts — as a numbered list, bullet points, or loose collection — and wants them organized into structured documents. Trigger when the user has 3+ raw items and asks to: organize/整理 them, group by theme/按主题分类, expand into vision docs/展开分析, assess feasibility/可行性, write user stories, prioritize, or turn rough notes into proper specs. Covers brainstorm dumps, feature wishlists, user feedback batches, project vision lists, and whiteboard outputs. Also trigger when someone describes having collected many ideas (e.g. 'I have 20 ideas', '收集到30多条反馈') even before listing them all. Key pattern: multiple loosely-related items in → structured thematic analysis out. Do NOT use for: single-feature design docs, competitive analysis, code generation, PR reviews, or general Q&A.
beancounter
by vincentorBeancount 个人财务管理 — 账单导入、查询分析、资产盘点、投资分析。 AI 直接读取账单文件（CSV/XLSX）并生成 beancount 交易，不依赖外部 CLI 工具。 当用户提到账单、记账、beancount、财务、收支、预算、报表、盘点、对账、导入账单、 股票分析、投资建议时使用。也适用于用户提供一个 CSV/XLSX 文件并希望将其转换为 beancount 格式的场景。
context-canary
by vincentorContext health monitoring - remember the session passphrase and report it when asked.
deep-research
by vincentorIMPORTANT: This skill contains a research methodology you MUST read before doing any web research. It defines a 4-phase protocol (dimension mapping → parallel subagent allocation → T1-T4 source credibility triage → completeness gate with saturation stopping criteria) that you do not have by default. Without reading this skill, you will skip dimension mapping, run searches sequentially instead of in parallel, miss the source tier system, and lack the completeness checkpoints. Read this skill FIRST whenever the user asks to research, investigate, compare, evaluate, explain, or look into any topic — or when they need current real-world information for any task (articles, presentations, reports, decisions). Also read it for 'what is X', 'what are the best practices for X', market/technology analysis, or any question requiring synthesis of multiple web sources.
example-greeting-skill
by vincentorThis skill activates when users discuss the example plugin, demonstrating how skills auto-activate based on context. Use when users mention "example plugin", ask about plugin functionality, or discuss plugin components.
fetch-feishu-doc
by vincentorFetch content from Feishu open platform documentation (open.feishu.cn) as structured Markdown. Feishu developer docs are SPA pages — WebFetch only returns empty HTML shells with no actual content. This skill uses Playwright MCP (Chrome Extension / extend mode) to render the page and extract content via the built-in "复制页面" button, which copies the full page as Markdown to the clipboard. Use this skill PROACTIVELY whenever you encounter or need to reference: - Any open.feishu.cn/document/ URL (card components, API endpoints, SDK guides, etc.) - Feishu card JSON component specs (tag definitions, properties, examples) - Feishu API documentation (request/response formats, error codes, permissions) - Feishu event subscription or webhook documentation - Any Feishu open platform integration pattern DO NOT use this skill for: - User's own Lark cloud documents (bytedance.larkoffice.com) — use download-lark-doc or lark-parse instead - Non-Feishu URLs — use WebFetch or other tools IMPORTANT: This skill requires Playwrigh
feishu-playwright-e2e
by vincentorPlaywright MCP guide for 飞书/Feishu Lark IM messenger E2E testing and 飞书聊天自动化 (feishu.cn, larkoffice.com). Read BEFORE operating 飞书聊天窗口 with Playwright: fill() and browser_fill_form fail with 'Element is not an input' on lark__editor contenteditable — use browser_type instead; @mention picker (飞书@提及用户/bot), Thread 回复面板, and sidebar navigation all require non-standard patterns you cannot guess. Covers: 飞书发消息, 读取消息历史, lark messenger 自动化, chatbot response testing via Feishu web UI.
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.