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...
document-writer
by Elian-Studio어떤 내용이든 고정된 하우스 스타일의 자기완결형 HTML 문서(필요 시 Markdown) 한 파일로 만들어 준다. 분석 결과·조사·리서치·리포트/보고서·기술 설계 설명·가이드/튜토리얼·회의 정리·요약 등 "남에게 보여주거나 보관할 문서"가 필요한 모든 경우에 사용한다. 사용자가 "문서로 정리해줘", "리포트/보고서 만들어줘", "HTML로 뽑아줘", "깔끔하게 문서화해줘", "정리해서 파일로 남겨줘", "~ 요약/정리 문서", "이거 문서화" 라고 하거나, 방금 한 분석·조사·구현 결과를 공유 가능한 문서로 남기려 할 때 반드시 이 스킬을 쓴다. 코드 한 줄 메모가 아니라 읽을 사람이 있는 문서면 명시적으로 "문서"라는 단어가 없어도 적용한다. (코드베이스에서 누락된 개발 문서를 자동 생성하는 일은 document-generate, 정해진 JSON을 스키마 기반 템플릿으로 렌더하는 일은 create-document 를 쓴다 — 이 스킬은 임의의 내용을 보기 좋은 문서로 만드는 범용 작성기다.)
fix
by Elian-StudioWhen the user reports a bug, asks to fix something, or runs /fix, drive the work through root-cause analysis → planning → user approval → TDD repair (regression test first) → verification → review → report, with conflict-free file ownership for multi-symptom fixes.
generate-teammate
by Elian-StudioWhen the user explicitly invokes /generate-teammate or says 'create a team', 'build a team', or 'spawn teammates', decompose the work into phases, judge each phase independently (Agent Team / Subagent / direct), and produce a hybrid execution plan with file-conflict-free role assignment. JSON-first spawn prompt rendering via create-document blocks vague language (help build, TODO, ...) before any teammate is spawned.
harness-manager
by Elian-StudioDetect and reconcile drift between the Codex and Claude Code GLOBAL harnesses — the behavioral rules (~/.claude/CLAUDE.md ↔ ~/.codex/AGENTS.md), MCP servers, custom commands/prompts, and skills that should behave consistently across both assistants. Runs scan → drift report (HTML) → user approval → backed-up edits. Reach for this whenever the user says "하네스 동기화", "harness sync", "Codex랑 Claude Code 규칙 맞춰줘", "AGENTS.md랑 CLAUDE.md 갈라진 거 확인", "MCP 양쪽 정합", "두 어시스턴트 설정/규칙 일치", or just edited one tool's global config and wants the other to match — even when they don't say the word "harness", if the concern is "the two tools disagree", this is the skill. It is NOT harness-legacy-scan (cruft audit) or harness-diet (cruft removal); those trim a single harness, this one keeps two harnesses consistent. Global scope only (~/.claude, ~/.codex); project-level AGENTS.md / .claude are out of scope.
implement
by Elian-StudioWhen the user asks to implement a feature, build a new capability, or runs /implement, drive the work through TDD with a parallel-or-sequential plan: gather context, propose a plan, gate user approval, run Red→Green→Refactor with conflict-free file ownership, verify, and report.
improve
by Elian-StudioWhen the user asks to improve an existing feature, optimize behavior, harden edge cases, or runs /improve, drive a BEFORE/AFTER analysis → plan → user approval → TDD improvement protecting existing tests → quantified before/after verification → review → report.
manage-skills
by Elian-StudioWhen verify-* skills drift behind code changes (uncovered files / broken references / missing checks), auto-detect the drift and create or update verify-* skills so the project's verification stays current. Pairs with verify-implementation (orchestrator); this skill is the meta-tool that maintains the skill set.
persona-review
by Elian-StudioWhen a user wants a plan, design, document, PR description, or idea reviewed through Daniel, Evans, Dean, Martin, multiple persona reviewers, or a custom persona, route the target to selected read-only persona reviewer subagent(s) and return each persona's native judgment style without a shared scorecard or fixed output template.
review
by Elian-StudioWhen the user asks for code review, PR review, diff review, or runs /review, perform a read-only engineering review of changed code to find production risks, regressions, broken contracts, missing tests, and verification gaps before merge. Lead with findings, cite file:line evidence, and hand off fixes/QA/ship instead of editing code.
verify-implementation
by Elian-StudioWhen PR is about to ship, dynamically discover and run all verify-* skills in the current project, surface failures with concrete fix suggestions, and (with approval) auto-apply fixes + re-verify. One command instead of remembering which verify-* to run for which change. Pairs with manage-skills (drift maintenance).
pr-writer
by Elian-StudioDrafts high-signal pull request titles and descriptions from git diffs, commits, branch names, issue context, test results, and repository PR templates. Use when the user asks to write, generate, improve, polish, or review a PR title, PR body, pull request description, merge request description, GitHub PR summary, or GitLab MR summary.
vue-nuxt-best-practices
by Elian-StudioUse when writing, reviewing, refactoring, or optimizing Vue 3 and Nuxt 3/4 applications. Applies a rules-based Vue/Nuxt skill pack covering SSR and hydration, data fetching, component architecture, performance, Nitro/server boundaries, state management, accessibility, and testing.
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.