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...
auto-dev-mode
by LostSunset為 Buddha-skills 專案執行自動開發迭代。當使用者要求「執行一次迭代」「跑自動開發」「依 CLAUDE-CODE-自動開發指令執行」時使用，或被 cron/workflow 喚醒時觸發。會先偵測模式 A/B/C/D，再依 CLAUDE-CODE-自動開發指令.md 的對應流程執行，並在結束時呼叫 dev-log skill 寫日誌。
auto-iterate
by LostSunset一鍵執行 CLAUDE-CODE-自動開發指令.md 的模式 B（開發中專案）完整迭代。當使用者說「跑一次迭代」「執行下一個 step」「auto iterate」「做下一個 ROADMAP 任務」時使用。會自動走完 B.1 狀態恢復 → B.2 規劃 → B.3 開發 → B.4 自我審查 → B.5 提交合併 → B.6 六項必做更新，並在結尾以 dev-log skill 寫入迭代紀錄。
claude-gh-app-setup
by LostSunset在一個 GitHub repo 上完整設定 Claude Code Action，讓 @claude 在 Issue/PR 能用 Claude Max 訂閱（OAuth，不用付費 API key）自動回應，並以 claude[bot] 身份貼文（不是 github-actions[bot]）。當使用者說「在 repo 加上 @claude」「我用 Claude Max 訂閱怎麼接 GitHub」「@claude 回覆者變成 github-actions[bot] 不好看」「裝 Claude GitHub App」「workflow 要怎麼寫」「branch protection 怎麼設」時使用。
claude-pr-automerge
by LostSunset讓 @claude 在 GitHub Actions workflow 中自動合併 PR，而不只是留言審查。當使用者說「@claude 合併後說沒有權限」「@claude 不會自動 merge」「想讓 claude 自動合併 upstream sync PR」「@claude 只留言不 merge」「讓 bot 自動按 merge」「workflow 自動 merge」時使用。
dev-log
by LostSunset用於在 Buddha-skills 專案撰寫或更新開發日誌 docs/DEV_LOG.md。當使用者要求「寫開發日誌」「記錄本次迭代」「更新 DEV_LOG」「完成一個 step」「準備合併 PR」時使用，也會在 upstream 自動同步 PR 中被 @claude 呼叫。嚴格遵循 docs/DEV_LOG_RULES.md 的七欄位模板與迭代編號規則。
gitnexus-policy
by LostSunset判斷在 Buddha-skills 或任何裝有 gitnexus 的專案中，何時該用 `gitnexus analyze`（輕量增量），何時該用 `gitnexus analyze --embeddings --skills --verbose`（完整重建）。當使用者問「要不要重跑索引」「需要 embeddings 嗎」「為什麼這次要全開」「gitnexus 怎麼跑」「gitnexus 哪些 flag 該加」「indexer 跑出來怪怪的」時使用。也會在 `auto-iterate`、`maintenance-patrol`、`new-project-init`、寫 ARCHITECTURE 文件、跨 repo 語意搜尋、debug 索引異常時被引用。
maintenance-patrol
by LostSunset執行 CLAUDE-CODE-自動開發指令.md 模式 C 的巡檢與持續改善流程。當使用者說「跑維護模式」「mode C 巡檢」「依賴審計」「安全掃描」「技術債清理」「專案已完成要持續維護」時使用。前置條件：ROADMAP.md 所有步驟皆為 ✅。執行 C.1 巡檢、C.2 持續改善、C.3 版本管理（依需要發 patch/minor release）。
milestone-pipeline
by LostSunset把中大型專案（預估超過 30 步）切成 N 個可獨立交付的里程碑，每個里程碑走一次完整的 brainstorm→spec→plan→subagent-driven execute→PR→merge 流水線，再進下一個。當使用者說「做一個完整的 XX 專案」「從零建 WebGUI / 產品」「這個專案太大了怎麼拆」「做完 M2 換 M3」「幫我走完所有 milestone」時使用。與 `new-project-init` 不同：後者專注 Phase 0（需求/設計/ROADMAP），本 skill 接手 Phase 0 之後「實際開發的 N 次迭代」。
new-project-init
by LostSunset從零初始化新專案，執行 CLAUDE-CODE-自動開發指令.md 模式 A 的完整 Phase 0（9 小節）。當使用者說「新專案初始化」「從零開始做 XX 專案」「做 mode A」「拆 ROADMAP 80 步」「專案 kick-off」時使用。前置條件：專案尚無 ROADMAP.md 且原始碼檔少於 5 個。產生 PROJECT_ANALYSIS、ARCHITECTURE、API_DESIGN、DATA_MODEL、ROADMAP（80 步）、CLAUDE.md、MEMORY.md、TEAM_ROLES、DEV_LOG、首次 commit + v0.1.0 tag。
pptx-visual-qa
by LostSunset使用 LibreOffice + PyMuPDF 把 PPTX 轉成 PNG 以便視覺檢查版面、覆蓋、斷句、切齊與字數溢位。當使用者要求「檢查簡報排版」「把 pptx 轉成圖片 preview」「視覺 QA 投影片」「每頁截圖比對」，或在用 python-pptx / pptxgenjs 產生簡報後需要逐頁驗證時使用。提供完整「產生 → 渲染 → 檢視 → 修正」迭代迴圈。
project-takeover
by LostSunset接手既有程式碼的考古與治理建立流程，執行 CLAUDE-CODE-自動開發指令.md 模式 D 的 Phase D0–D2。當使用者說「接手這個專案」「mode D」「做專案考古」「TAKEOVER_REPORT」「既有 codebase 分析」「這是個舊專案」時使用。前置條件：無 ROADMAP.md 但已有大量程式碼或 git history。執行檔案掃描、架構逆向、健康度評估、地雷掃描，建立 CLAUDE/MEMORY/ROADMAP（R1–R4 階段）後切入模式 B。
resilient-image-download
by LostSunset批次下載網頁文章圖片時處理 HTTP 429 限流、User-Agent 阻擋、Wikimedia Commons /thumb/ 路徑限速、以及小圖佔位符的實戰技巧。當使用者要求「下載多篇文章的圖片」「批次抓圖」「Wikimedia 圖片抓不下來」「爬蟲 429」「準備報告素材」時使用。包含 curl flag 組合、重試策略、備援 URL 解析、下載後尺寸檢查等。
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.