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...
ywc-agentic
by yongwoon(ywc) Use when the user provides a high-level natural-language goal and wants the existing ywc-* skills orchestrated autonomously through Plan → Execute → Evaluate → Repeat to deliver code implementation. Triggers: "agentic", "autonomous workflow", "goal to code", "ywc-agentic", "자율 실행", "自律実行". Do not use for one-off skill invocations, manual task implementation, or when the user wants explicit control over each phase.
ywc-commit
by yongwoon(ywc) Use when the user says "commit", "커밋", "커밋 해줘", "commit push", "push", "지금까지 한 작업 커밋", or any phrase indicating intent to stage, commit, or push current work. Do not use for PR creation, code review, or making code changes.
ywc-confidence-gate
by yongwoon(ywc) Use before starting any non-trivial implementation, before invoking ywc-code-gen / ywc-sequential-executor / ywc-parallel-executor, or before committing to a design path with material rework cost. Scores readiness across five dimensions (scope clarity, architecture compliance, evidence quality, reuse verified, root cause identified) and gates the decision with PROCEED (≥90) / REVIEW (70–89) / STOP (<70). Triggers: "confidence check", "confidence gate", "ready to implement", "should I proceed", "is this ready", "준비 됐어", "구현 시작해도 돼", "confidence 점검", "착수 준비", "実装着手", "実装に進んで良いか", "確信度チェック", "ywc-confidence-gate". Do not use for completion verification (use ywc-verify-done — that gates the claim, this gates the start), spec quality review (use ywc-spec-validate), implementation review (use ywc-impl-review — that scores findings, this scores readiness), or brainstorming intent (use ywc-brainstorm).
ywc-debug-rootcause
by yongwoon(ywc) Use when encountering a bug, test failure, build failure, or any unexpected behavior, before proposing or applying any fix. Forces root-cause identification through a 4-phase investigation, blocks symptom patching, and questions architecture after 3+ failed fixes on the same surface. Triggers: "왜 안돼", "안 돼요", "디버그", "디버깅", "버그", "고장", "이상해", "원인 찾아줘", "debug", "debug this", "find the bug", "root cause", "what's wrong", "デバッグ", "原因不明", "通らない", "落ちる", "おかしい", "ywc-debug-rootcause". Do not use for ongoing implementation drafting (use ywc-code-gen), incident postmortem after the fact (use ywc-incident-postmortem), security vulnerability triage (use ywc-security-audit), or pre-implementation confidence check (use ywc-confidence-gate).
ywc-finish-branch
by yongwoon(ywc) Use when delivering a single completed feature branch to the base branch — covers mark-PR-ready, CI wait + bot review polling, merge (PR or local), post-merge verification, Mark Task Complete bookkeeping, and local branch cleanup. Triggers: "finish branch", "deliver branch", "finish-branch", "ywc-finish-branch", "merge feature branch", "branch 마무리", "branch 마감", "ブランチ完了", "deliver task", "task 마감". Do not use for branch creation (handled by upstream executor), worktree management (caller of `ywc-parallel-executor` handles), draft PR creation alone (use `ywc-create-pr`), or PR review comment handling (use `ywc-handle-pr-reviews`).
ywc-handle-pr-reviews
by yongwoon(ywc) Use when handling PR review feedback, addressing code review comments, or responding to GitHub PR review threads. Triggers: "handle PR reviews", "address review comments", "respond to PR comments", "리뷰 대응", "리뷰 코멘트 처리", "レビュー対応". Do not use for creating a new PR (use ywc-create-pr), performing a code review yourself (use ywc-impl-review), or for changes outside an open PR context.
ywc-impl-review
by yongwoon(ywc) Use after implementation is complete and before creating a PR, when the user wants to validate code matches the spec, check implementation quality, or run a comprehensive review. Triggers: "구현 검증", "impl review", "implementation review", "사양 적합성", "코드 리뷰", "구현 리뷰", "PR 전 검증", "check my implementation", "実装レビュー". Do not use during active code generation, for spec-only review (use ywc-spec-validate), or for product/business-level review (use ywc-product-review).
ywc-incident-postmortem
by yongwoon(ywc) Use when a production incident has occurred and you need a structured postmortem: timeline reconstruction, root cause analysis (5 Whys), impact assessment, prevention action items, and optionally a sanitized client-facing report. Trigger phrases: "장애 회고", "포스트모텀 작성", "postmortem", "incident report", "장애 보고서", "장애 원인 분석", "사고 회고록", "ポストモーテム", "インシデントレポート", "障害振り返り", "outage report", "incident postmortem", "ywc-incident-postmortem" Do not use for: proactive security vulnerability scanning before an incident (use ywc-security-audit); general code quality review unrelated to an incident (use ywc-impl-review); generating changelog or release notes after a fix (use ywc-changelog-release-notes).
ywc-merge-dependabot
by yongwoon(ywc) Use when the user wants to merge Dependabot PRs, batch-process dependency updates, or clean up accumulated Dependabot PRs. Triggers: "merge dependabot", "dependabot PR", "dependency updates", "security updates merge", "디펜다봇 머지", "依存関係更新マージ". Do not use for non-Dependabot PRs, manual dependency upgrades, or for merging feature PRs (use ywc-create-pr or platform tools).
ywc-onboard-repo
by yongwoon(ywc) Use when entering an existing / unfamiliar repository for the first time, generating a starter CLAUDE.md from detected conventions, or producing an architecture / convention briefing for a new joiner. The output is a printed Onboarding Guide plus a Starter CLAUDE.md written to the repo root (enhancing the existing one in place if present). Triggers: "onboard me", "이 repo 처음이야", "이 codebase 를 이해하게 해줘", "generate CLAUDE.md", "walk me through this repo", "리포 분석해줘", "コー ドベースを案内して", "onboarding 가이드", "ywc-onboard-repo". Do not use for creating a brand-new repository from scratch (use ywc-project-scaffold — that is the inverse direction), for creating a CodeTour `.tour` JSON walkthrough artifact (out of scope — this skill emits Markdown not .tour), for ad-hoc "explain this one file" requests (answer directly), or for incremental codemap refreshes on a repo you already understand (this skill is the cold-start; refreshes belong to a separate hygiene pass).
ywc-parallel-executor
by yongwoon(ywc) Use when multiple independent tasks from tasks/ can run simultaneously and the user wants faster execution via Git Worktree isolation. Triggers: "병렬 실행", "parallel execute", "parallel-executor", "agent executor", "동시 실행", "워크트리 실행", "execute tasks in parallel", "run tasks simultaneously", "並列実行". Do not use for strictly sequential tasks (use ywc-sequential-executor), single-task execution, or when no dependency-graph.md exists.
ywc-plan
by yongwoon(ywc) Use when the user has a rough feature idea or change request and needs a concrete plan before implementation, including scale assessment and routing to the right downstream skill. Triggers: "plan 세워줘", "계획 세워", "어떻게 진행할지", "plan this", "make a plan", "계획", "プラン作成", "計画立てて", "ywc-plan", "task 만들기 전 plan", "before task generator". Do not use for spec quality validation on an existing spec (use ywc-spec-validate), task decomposition from a finalized spec (use ywc-task-generator), product/business reasoning (use ywc-product-review), or architecture-only design without implementation intent (use ywc-tech-research).
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.