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...
pj-hub
by 38kta-labCreate, update, and review project hub Markdown files under projects/active/ for research projects, manuscripts, server/admin work, tooling, and other multi-step efforts. Use when the user says pj-hub, project hub, PJ管理, Project管理, プロジェクト整理, MTGまでのTodo, checkpoint, milestone, deadline, repo付きProject, or wants goals, context, milestones, meetings/checkpoints, tasks, outputs, blockers, next actions, and related issues organized without immediately creating GitHub Issues.
session-wrap
by 38kta-labTriage all pending and in_progress TaskList items before /clear, routing each to a durable location (GitHub Issue / PJ hub Tasks / inbox / Calendar / keep / drop) so nothing is lost on session clear. Use when the user says session-wrap, /session-wrap, セッション終わる前にタスク整理, /clear する前に, wrap up tasks, 残タスク振り分け, 残 task 整理, or wants pending tasks rescued from the session-scoped TaskList before clearing.
task-review
by 38kta-labReview and plan Japanese tasks for today, tomorrow, this week, next week, or a specified period by combining Google Calendar, ideas/inbox notes, projects/active hubs, agent-memory, and optionally GitHub Issues. Use when the user asks 今日のタスクは, 明日のタスクは, 来週のタスクは, 今週やること, タスク整理, 予定を組んで, Calendarに入れる候補, or wants actionable task priorities and calendar block suggestions.
url-digest
by 38kta-labCreate or append a Japanese digest from a required URL into ideas/daily/md/YYYY-MM-DD-digest.md, then render ideas/daily/YYYY-MM-DD-digest.html. Use when the user says url-digest, /url-digest, digest this URL, このURLをdigest, 論文を数行でまとめて, ニュースを数行でまとめて, or wants a concise core-message summary of a paper, preprint, DOI page, publisher page, official news article, or research news URL.
weekly-review
by 38kta-labCreate a Japanese weekly review from ideas/daily/md/*-digest.md and relevant agent-memory Markdown files for a specified date range, or by default the current Saturday-through-Friday review window, then render ideas/weekly/YYYY-MM-DD-weekly-review.html. Use when the user asks for weekly-review, 週次レビュー, 今週の振り返り, ideas/weeklyへのreview作成, digestやmemoryから次アクションを整理, or wants weekly highlights, research signals, decisions, possible issues, and next actions.
agent-memory
by 38kta-labSave, recall, list, update, and organize repository working memories. Use when the user says or implies: 記憶して, 覚えておいて, 保存して, 思い出して, 前のメモを確認して, memory一覧, メモを探して, remember this, save this, recall, list memories, check notes, or when context should be preserved for resuming later.
daily-search-trend
by 38kta-labCreate Japanese daily search trend reports from PubMed, Europe PMC/bioRxiv preprint searches, Nature News, Science/AAAS News, and ナゾロジー（自然科学） for the previous calendar day, then render the Markdown to a Newsprint-themed HTML file. Use when the user asks for daily-search-trend, search trend, trend.md, trend.html, 今日の研究トレンド, 論文検索, 新着論文, 研究ニュース, 前日の論文, ideas/dailyへのtrend作成, or wants titles translated to Japanese and ranked strictly from portfolio context.
drive-digest
by 38kta-labPull new files from a designated Google Drive inbox folder (under a secondary Google account) and digest them into ideas/daily/md/YYYY-MM-DD-digest.md. Supports Google Doc, PDF, HTML, Markdown, and image files. Use when the user says or implies: drive-digest, /drive-digest, Drive から取り込んで, Drive の youtube-digest を読んで, life-inbox を digest, ドライブの新着を確認して, または youtube-digest, paper-close-reading フォルダを処理してほしいとき.
english-from-paper
by 38kta-labGenerate English learning artifacts from a finished paper close-reading (<slug>-ja.md must already exist). Produces vocabulary / collocation / grammar study material, a quiz + answer key, an English-only podcast script, and a NotebookLM Audio Overview customize prompt. Outputs are co-located in portfolio/paper-close-readings/. The 2 NotebookLM input files (clean-original.html + <slug>-en-study.md) plus the prompt.txt are staged to Google Drive's paper-podcasts/<slug>/ for manual upload to NotebookLM (typically via fenrir remote desktop). Use when the user says english-from-paper, 英語学習素材, 論文から英語学習, NotebookLM script, X04 英語, or wants vocab / quiz / podcast assets generated from a finished paper close-reading.
find-notes
by 38kta-labCross-cutting knowledge search across Drive desktop (local), Drive API, and Paperpile PDFs. Returns hits grouped by source with file path / URL / snippet. Use when the user says find-notes, /find-notes, メモを探して, あのメモどこ, 論文探して, papers about X, find that doc about X, Drive で X を探して, or wants to locate any note / doc / paper from across their knowledge base.
issue-capture
by 38kta-labExtract, structure, create, and update GitHub Issues from conversations, notes, plans, and task descriptions. Use when the user says or implies: Issueにして, タスクを切って, やることを整理して, Issue候補, GitHub Issue, Projectsに追加, this should be an issue, break this into tasks, capture action items, or organize work into To do/Pending/In progress/Done.
morning-tasks
by 38kta-labLoad the auto-generated morning brief (ideas/task-review/md/morning-YYYY-MM-DD.md) into the current session's TaskCreate list so the user can work through today's tasks with progress tracking. Use when the user says morning-tasks, /morning-tasks, ブリーフを取り込んで, 今日のタスクをTaskにして, brief から task 作って, load brief, ingest morning brief, or wants the morning brief surfaced as trackable TaskCreate entries for this session.
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.