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...
mk-qa-master
by kao273183Run, generate, debug, and improve software tests through mk-qa-master's MCP tools (pytest / Playwright / Jest / Cypress / Maestro / Schemathesis / Newman) and its v0.7 AI Visual Challenge Solver (reCAPTCHA / hCaptcha) and v0.8 OWASP API Security Top 10 scanner. Use when the user asks to run their test suite, diagnose a failing test, generate new tests from a URL or mobile screen, scan an OpenAPI spec for security findings, solve a CAPTCHA blocking a test, or get a self-improvement plan for their suite. Auto-activates from phrases like "run my tests", "why did this test fail", "generate tests for this URL", "scan this API for OWASP issues", "the test is stuck on a reCAPTCHA".
llm-quality-eval
by kao273183AI / LLM 應用品質評估專屬流程。覆蓋幻覺（hallucination）/ 事實性（groundedness）、相關性、結構化輸出合法性、prompt injection 抵抗、安全/毒性、成本（$/req）、延遲（p95）、token 用量、回歸（eval set）、一致性、拒答校準、RAG 檢索品質。整合 promptfoo / DeepEval / Ragas / LLM-as-judge + golden dataset + deterministic seed。當使用者提到「LLM 測試 / AI 品質 / 幻覺 / hallucination / groundedness / prompt injection / eval / 評估集 / RAG 評估 / LLM-as-judge / 模型回歸 / AI app 品質 / token 成本」時觸發。配套：property-based-test-gen（fuzz prompt）、security-scan（injection 屬安全）、performance-test-gen（LLM API 延遲/壓力）、test-data-factory（eval 資料）、bug-report。
a11y-audit
by kao273183對 Web / iOS / Android App 跑獨立無障礙審查，整合 Lighthouse / axe-core / iOS Accessibility Inspector / Android Accessibility Scanner。產出 WCAG 2.1 AA 評分報告、CVSS-like 嚴重度分級、修復建議含 code snippet。當使用者提到「a11y 審查 / accessibility audit / WCAG / Lighthouse a11y / axe-core / VoiceOver 檢查 / TalkBack 檢查 / 無障礙評分 / 字級放大測試」時觸發。配套：test-master（內建 a11y 必檢，本 skill 是深度補強）、bug-report（追 a11y bug）、regression-test（release 前 a11y 回歸）。
tc-version-diff
by kao273183比對兩個 TC 版本（v0.x → v0.y）的差異，產 changelog + 補測清單 + 自動更新 status sheet 的審查紀錄。當使用者提到「TC 版本 diff / TC 升版 / 比對 v0.2 v0.3 / 哪些 TC 要重跑 / 補測清單」，或剛 review 完一份 TC 升版本（看到「v0.3 補 8 條」這種訊息）時觸發。配套：test-review（升版前審）、test-master（升版時擴張）、tc-to-pytest（API TC 升版同步 pytest）。
tc-to-pytest
by kao273183把 Google Sheet 或 markdown TC（白箱 API 驗證類）轉成 pytest-api-kit 三件套（schemas.py + conftest fixture + tests/test_*.py）。當使用者提到「TC 轉 pytest / Sheet 變測試碼 / 把白箱 TC 變 pytest / generate API tests from TC」，或拿到 speckit-to-tc 草稿 + 要寫 BE 測試碼時觸發。配套：speckit-to-tc（前置）、test-review（驗證）、test-automation（前端自動化）。
qa-signoff
by kao273183Release 上線前的 QA 放行門（go/no-go gate）。彙整各方訊號——測試通過率、未關 P0/P1 bug、回歸結果、security/compliance/a11y/效能/離線各 gate 的 blocker 數、flaky 狀態、跨平台一致性——算出 readiness 分數，套 hard/soft gate 規則產出 go / no-go 決策，並生成可簽核的 sign-off 文件（含風險聲明 + 條件式放行）。當使用者提到「放行 / sign-off / signoff / go no-go / release readiness / 上線檢查 / 出版檢查表 / QA gate / release gate / 可以上線嗎 / 放行決策 / readiness 評分」時觸發。配套：regression-test（前置，產回歸結果）、smoke-test-analyzer（測試分層通過率）、flaky-test-hunter（flaky 不該擋放行）、security-scan / compliance-test / a11y-audit（各 gate 來源）、publish-regression（放行後發報告）。
oauth-flow-test
by kao273183OAuth 2.0 / OIDC / SSO 登入流程測試專屬流程。覆蓋 authorization code + PKCE、token 刷新、access/refresh token 過期、refresh token 輪替、登出/撤銷、多 IdP（Google / Apple / Facebook / 企業 SSO）、deep link 重導、state/nonce CSRF 防護、scope/consent、silent renew、錯誤路徑（拒絕授權 / code 過期）。整合 iOS（ASWebAuthenticationSession）/ Android（Custom Tabs + AppAuth）/ Web（redirect + PKCE）/ BE（token 驗簽）。當使用者提到「OAuth / OIDC / SSO / 登入流程測試 / token 刷新 / refresh token / PKCE / 授權碼 / 第三方登入 / Google 登入 / Apple 登入 / single sign-on / token 過期 / 授權測試」時觸發。配套：security-scan（token 漏洞）、compliance-test（同意/個資）、test-automation（登入 UI test）、offline-mode-test（token 刷新斷線）、bug-report。
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.