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...
mr-review
by 94wogus-quantitPerform context-aware comprehensive code review on GitLab MR changes. Validates architecture consistency, business logic accuracy, historical issue patterns, JIRA requirements, security, and test coverage. Generates INLINE_DISCUSSION.json for GitLab inline comments and SUMMARY_COMMENT.md for overall summary. Korean triggers: MR 리뷰, 코드 리뷰, 머지 리퀘스트, PR 리뷰, 코드 검토, 리뷰해줘, 코드 봐줘, MR 확인해줘.
record
by 94wogus-quantitConsolidate workflow artifacts (analysis reports, plans, implementation results) into comprehensive project documentation. Updates README, CHANGELOG, CLAUDE docs and stores technical insights in Serena memory. Use after completing implementation to finalize and document completed work with optional git commit/push. Korean triggers: 문서화, 문서 작성, 문서 업데이트, README 작성, CHANGELOG 작성, 변경사항 기록, 릴리즈 노트, 정리해줘, 문서 정리, 커밋해줘, 푸시해줘, 마무리해줘, 완료 처리.
ask-yt
by 94wogus-quantitAsk YouTube's built-in Gemini AI about video content using CDP automation. Use when user provides a YouTube URL and wants to ask questions about the video. Supports multi-turn questioning: open the panel once, ask multiple questions. Triggers on: "YouTube 영상에 대해 질문해줘" + URL, "이 유튜브 영상 요약해줘" + URL, "/ask-yt [URL] [question]", User wants to query YouTube's Ask/질문하기 built-in AI feature
analyze
by 94wogus-quantitSystematically analyze the root cause of bugs and issues using multi-perspective investigation with First Principles Thinking. Use when analyzing JIRA issues, Sentry errors, or investigating bug reports. Generates [ISSUE_ID]_REPORT.md with root cause analysis, code locations, reproduction steps, and fix recommendations.
choo-choo
by 94wogus-quantitThis skill should be used when the user asks to "run ralph", "랄프 실행", "랄프 돌려", "ralph loop 실행", "ralph로 해줘", "랄프로 돌려", "run-ralph", "choo choo", "랄프 출발", or wants to execute ANY iterative work — code changes, design documents, skill/workflow integrations, architectural decisions, documentation, or refactoring — through a multi-agent team. Choo-choo is a general iterative framework, not a code-only tool: anything expressible as "work + acceptance criteria + per-iteration verification" fits. Transforms the request into a Ralph Loop prompt with a multi-agent team (mandatory Reviewer + QA), 3-level acceptance criteria, and an iteration workflow that gates completion-promise emission on independent verdicts. Anchors all sentinel/prompt files to the project root so a Worker that `cd`s into a sub-directory mid-loop does not break the gate. Then invokes /ralph-loop.
wikify
by 94wogus-quantitarkraft-wiki repo에 지식 문서를 생성/업데이트하는 thin wrapper skill. "지식화하자", "지식화", "wiki에 추가해줘", "wiki 문서로 남겨줘", "wikify", "wiki 정리", "wiki에 정리" 같은 요청에 사용. 사용자가 wiki_root를 settings로 지정하면 그 경로로 작업. 컨텍스트 수집 + 섹션 결정 + Acceptance Criteria 도출은 직접 처리하지 않고 run-ralph:choo-choo에 위임 — 이 skill은 wiki-specific 컨텍스트(섹션 구조, lifecycle, harness 검사 항목, scan 대상 repo 목록)를 묶어 choo-choo에 깨끗한 task 명세로 전달하는 것이 전부.
fix-discussion
by 94wogus-quantitFix GitLab MR discussions by modifying code, posting a reply explaining the fix, and resolving the discussion. Supports single or batch processing. Korean triggers: discussion 수정, 디스커션 해결, 코멘트 반영, 리뷰 반영, discussion resolve, 피드백 반영.
execute
by 94wogus-quantitExecute approved implementation plans with TaskList tracking, test verification, and success criteria validation. Use when you have an approved *_PLAN.md file and need step-by-step implementation with comprehensive tracking. Outputs implemented code, test results, and execution summary. Documentation handled by record skill. Korean triggers: 계획 실행, 플랜 실행, 구현 시작, 개발 시작, 코딩 시작, 작업 시작, 실행해줘, 구현해줘, 만들어줘, 개발해줘, 코드 작성, 기능 구현, 태스크 실행.
plan
by 94wogus-quantitCreate high-quality implementation plans through iterative refinement until all quality standards are met. Use when creating implementation plans from analysis reports or requirements, especially for complex features or critical bug fixes. Generates [FEATURE]_PLAN.md with task breakdown, dependencies, and success criteria. Korean triggers: 구현 계획, 실행 계획, 개발 계획, 플랜 작성, 계획 수립, 작업 계획, 태스크 분해, 계획 세워줘, 플랜 만들어줘, 어떻게 구현할지, 작업 분해해줘.
qa
by 94wogus-quantitIndependent acceptance verification skill. Run after execute completes to validate the implementation against the original REPORT's reproduction scenarios and the PLAN's success criteria — using actual environment verification (test runs, API calls, UI checks via agent-browser, DB state inspection), not just self-reported "tests pass". Generates [ISSUE_ID]_QA.md with PASS/FAIL verdict and evidence. Korean triggers: QA 검증, 품질 검증, qa 실행, 인수 검증, 시나리오 검증, qa 돌려, 검증해줘, 인수 테스트, 수용 검증.
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.