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...
xmind-cli
by ivan-94Use this skill when working with .xmind workbooks through the xmind command line tool, especially for inspecting workbook structure, finding topics, reading topic trees, previewing safe edits, applying explicit mutations with backups, validating workbooks, importing or exporting structured content, or debugging real XMind package compatibility.
ai-wiki-xmind-ingest
by ivan-94Export, digest, and ingest raw .xmind files for this AI Obsidian wiki. Use when processing XMind sources under the AI raw source root into wiki sources, concepts, entities, synthesis, maps, index, or log pages; when the user asks to run an XMind ingest; or when avoiding unnecessary inspect, tree, or validate steps during source conversion.
ai-wiki-image-ingest
by ivan-94Ingest raw image files into this AI Obsidian wiki. Use when processing PNG, JPG, JPEG, WEBP, GIF, HEIC, or other supported image sources under the AI raw source root into source notes, index coverage, log entries, and optional compiled concept, entity, synthesis, or map pages.
ai-wiki-vault-sync
by ivan-94Sync this AI wiki repository with the official Obsidian iCloud container. Use when publishing repo-managed wiki content to iCloud, pulling human-authored Obsidian notes back from iCloud, dry-running, applying, pruning repo-managed mirror files, or checking conflicts between `/Users/ivan/workspace/ai/ai_llm_wiki` and the Obsidian app iCloud vault target `iCloud~md~obsidian/Documents/ai`.
ai-wiki-cook-github
by ivan-94将 GitHub 仓库 URL 烹饪成 AI wiki human inbox 笔记。用户给出 github.com 的仓库、branch/tag 或 commit 链接，并希望 clone 到临时 cache、创建 low-effort 子 Agent 做只读仓库探索、生成中文项目消化报告和信息图，而不是 ingest 进 canonical wiki graph 时使用。
ai-wiki-raw-diff
by ivan-94Diff the AI wiki iCloud raw source root against mirrored source notes. Use when checking added, deleted, updated, moved, unchanged, unsupported, metadata-missing, or iCloud-unavailable raw .xmind/image/Markdown/PDF/Excalidraw files before ingest, refresh, lint, or source maintenance.
ai-wiki-cook-podcast
by ivan-94将 Apple Podcasts 单集烹饪成可消化的 AI wiki inbox 单文件笔记。用户给出 Apple Podcasts 单集链接，并希望自动提取音频、本地 Whisper 转写、使用 imagegen 生成信息图、最终写入 human/inbox 下的 Obsidian Markdown，而不是立刻 ingest 进 canonical wiki graph 时使用。
ai-wiki-codex-weekly
by ivan-94Generate a weekly work review from existing Codex daily reports in this AI wiki. Use when the user asks for a Codex weekly report, seven-day daily report synthesis, weekly workflow/work-efficiency review, or writing to human/inbox/codex-weekly.
ai-wiki-cook-tweet
by ivan-94将 X/Twitter 单条 post、thread 或 X article 链接烹饪成 AI wiki human inbox 笔记。用户给出 x.com/twitter.com 的推文、thread 或文章链接，并希望用未登录可见页面浏览器自动化（browser-use/agent-browser）打开页面、消费可见内容、生成中文消化笔记和信息图，而不是 ingest 进 canonical wiki graph 时使用。
ai-wiki-obsidian-doctor
by ivan-94结合 Obsidian CLI 链接检查和本仓库 wiki 契约检查，诊断这个 AI wiki 的 Obsidian vault 健康状况。用户要求 Obsidian doctor、坏链审计、损坏笔记检查、孤岛/死端页面检查或 `/Users/ivan/workspace/ai/ai_llm_wiki` vault 健康报告时使用。
ai-wiki-cook-blog
by ivan-94用户给出单篇公开可见 blog/article URL，并要求 cook、烹饪或消化成 AI wiki human inbox 笔记和必选信息图时使用；浏览器优先，同 URL 公开 HTML/readability fallback，不进入 canonical wiki ingest。
ai-wiki-markdown-ingest
by ivan-94Ingest raw Markdown files into this AI Obsidian wiki. Use when processing .md sources under the AI raw source root into source notes, index coverage, log entries, and optional compiled concept, entity, synthesis, or map pages without copying the raw document into the wiki.
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.