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...
mono-repo-docker-compose-setup
by Waterball-Software-AcademyMono-repo Docker compose setup. 偵測 frontend / backend 子資料夾與 stack 特徵後生成 root docker-compose.yml + 兩份 Dockerfile + .dockerignore；接著並行 spawn 兩條 subagent (backend / frontend) 各自 build/up + curl 驗證直到 HTTP 200，否則由 subagent 自行修補（Dockerfile / compose / 程式碼），每條最多 5 次迭代。TRIGGER when user 下 /mono-repo-docker-compose-setup、要把 monorepo 容器化並冒煙、或請求一鍵生成 fullstack docker compose。SKIP when 不是 monorepo（沒有 frontend/backend 子資料夾）、user 只要 single-service Dockerfile、或要做 production deploy spec 而非 dev compose。
aibdd-form-story-spec
by Waterball-Software-Academy從推理包翻譯為「Storybook CSF3 stories + React component implementation 雙產出」。 對 caller 指定的 `target_dir` 寫兩個檔：`<identifier>.tsx`（React component 實作）與 `<identifier>.stories.tsx`（CSF3 stories；boundary I4 binding anchor SSOT）。 目標目錄、props、stories、render hints 由 Planner 透過 DELEGATE 參數指定，本 skill 不自決。 綁定 Storybook 10 + `@storybook/nextjs-vite`；步驟定義從 Story `args` 派生 `getByRole(role, { name })` locator。
sf-eval-starter
by Waterball-Software-AcademyWorker 連線 SF MCP 後接管全自動 RED→GREEN→REFACTOR 循環。每輪呼 mcp__sf__get_next_goal 拿下一個 TDD goal，DELEGATE 對應的 aibdd-{red,green,refactor}-execute sub-skill；組好 test command 後**先在本地 dry-run 一次確認 runner launchable**（環境準備是 worker 責任，evaluator 不會幫忙裝相依），再呼 mcp__sf__verify_goal 拿 job_id（非同步 dispatch），最後用 mcp__sf__verify_goal_status 透過 bash `sleep 20` 每 20 秒 poll 一次直到 completed=true 取出 verdict，再進下一輪 — 直到 evaluator 回 all-done。期間僅以 AssistMessage 單向回報進度，禁止 AskUserQuestion / ExitPlanMode。TRIGGER when /sf-eval-starter, 跑 SF eval, 進入 SF 全自動模式. SKIP when SF MCP 未啟動 / 已在另一個 SF skill 內運行 / user 想要 step-by-step.
aibdd-green-evaluate
by Waterball-Software-AcademyEvaluate a completed AIBDD Green Worker run by checking only the final full acceptance suite test report. Pass only when the suite is truly all green.
aibdd-red-evaluate
by Waterball-Software-AcademyEvaluate a completed AIBDD Red Worker run using runtime-visible feature files, step definitions, and test report evidence. Veto false red and hollow red before Green may consume the run.
aibdd-refactor-evaluate
by Waterball-Software-AcademyEvaluate a completed AIBDD Refactor Worker run by checking strict dev constitution conformance and final full acceptance suite all pass.
aibdd-activity-granularity-rule-docs
by Waterball-Software-Academy撰寫或審閱 Activity 顆粒度專用之規則 Markdown（Actor／Step）：僅收容可判定的不變式條列、可選反例與預期對照，禁止混入 SOP 動作或 Upstream 追溯。於新建或修整 `**/rules/*granularity*.md`、被要求「顆粒度只留規則」、拆分規則檔與執行程序、或複寫 discovery 類顆粒度說明時使用。
aibdd-pen-to-storybook
by Waterball-Software-AcademyAdapter for Pencil `.pen` design files. Reads `.pen` → returns normalized `component_table` + Tailwind 4 `tokens`. Pure read-only — does NOT write files. Pencil-side adapter implementation of the cross-source design adapter contract; future siblings (`aibdd-figma-to-storybook`, `aibdd-penpot-to-storybook`) follow the same `component_table + tokens` return shape so downstream consumers (`/aibdd-form-story-spec`, `/aibdd-plan` Phase 3 component-design merge, `/aibdd-green-execute` Wave 1) stay design-source-agnostic.
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.