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...
apply
by Ting-s515當使用者指定 propose 產出的功能資料夾路徑,並要求開始或繼續實作時,必須載入此技能。 從路徑自動推斷根路徑,讀取資料夾下的三份文檔,依 TDD 流程先逐一撰寫測試,再實作未完成任務並更新 checkbox 狀態。 觸發情境包含但不限於:「apply」、「開始實作」、「繼續實作」、「apply frontend/docs/propose/feature-name」、 「apply backend/docs/propose/feature-name」、「apply docs/propose/feature-name」、「按照任務清單實作」。 使用者通常會在新 session 中指定功能路徑來呼叫此技能,不依賴 propose 的對話 context。
bdd-unit-test
by Ting-s515指定一或多個檔案並要求撰寫單元測試時,必須載入此技能。 根據 BDD(行為驅動開發)原則,分析指定檔案的公開方法與邏輯分支,產出涵蓋 Happy Path、Edge Cases、Error Cases 的測試。 觸發情境包含但不限於:「幫這個檔案寫單測」、「write unit test」、「add unit test」。 即使只說「寫測試」或「補測試」,只要有指定目標檔案或貼上程式碼片段,也應載入此技能。
clarify-flow
by Ting-s515當使用者提供已有的業務流程描述、需求、會議紀錄或需求規格文檔,需要重寫成精確結構化格式,讓每個步驟、if/else 判斷分支、遍歷邏輯都清晰可見時,載入此技能。 觸發信號:描述散亂看不出判斷點、分支條件混在句子裡、if/else 不明顯、遍歷邏輯難追蹤、需要讓步驟和條件明確分離。 典型觸發詞:「流程說明很亂幫我整理」、「把這段描述結構化」、「clarify flow」、「整理需求規格文檔」。 排除:畫 Mermaid 圖、解釋程式碼邏輯、整理 API 文件、翻譯文檔、撰寫全新文件、壓縮精簡文件、或轉換格式。
code-reviewer
by Ting-s515當使用者提供業務邏輯文檔(需求規格、User Story、API 文件、流程說明等),並要求審查程式碼實作時,必須載入此技能。 使用 git diff 比對業務邏輯與程式碼變更,確認功能是否正確實作、找出邏輯衝突、潛在問題與副作用,並檢視是否符合最佳實踐。 觸發情境包含但不限於:「對照文件幫我 review」、「幫我審查這次的實作」、「這個 PR 符合需求嗎」、 「依照業務邏輯檢查程式碼」、「根據規格審查這次變更」。 即使使用者只說「幫我 review」或「有沒有符合需求」,只要上下文中有提供業務邏輯文檔,也應載入此技能。 此技能也適用於 subagent 情境:當 prompt 中包含規格文檔路徑時,自動讀取並對照審查。
explaining-code
by Ting-s515當使用者在對話中詢問程式碼、工具或技術概念的運作原理、流程邏輯或架構設計時,必須載入此技能。 根據對話紀錄理解問題,在使用者需要時才輸出結構化的 Markdown 說明文件, 搭配 ASCII art 與 Mermaid 圖表(流程圖、時序圖、類別圖)進行視覺化說明。 觸發情境包含但不限於:「這段程式怎麼運作的」、「幫我解釋這個邏輯」、「這個架構是什麼」、 「畫個流程圖說明」、「這個 function 在做什麼」、「explain this code」、「how does this work」。 即使使用者只說「解釋一下」或「這是什麼意思」,只要對話中已有相關程式碼或技術討論,也應載入此技能。
export-conversation
by Ting-s515將本次對話的完整內容整理並匯出為結構化的 Markdown 檔案,方便其他 AI model 或下一個對話視窗接續任務。 當使用者說以下任何一種情境時必須載入此技能:「匯出對話」、「輸出對話紀錄」、「把這次對話存成 md」、 、「export conversation」,或任何需要保留本次對話內容、切換 AI 模型、跨對話傳遞任務進度的情境。
export-feature-file
by Ting-s515當使用者提供 Gherkin 文檔、業務邏輯說明或需求規格,並要求產出可被測試框架執行的 Feature File 時,必須載入此技能。 支援 .NET (Reqnroll)、Java (Cucumber-JVM)、JavaScript/TypeScript (Cucumber.js)、Python (Behave)、Flutter/Dart (flutter_gherkin) 等框架;清單外的框架以 LLM 通用知識產出 Step Definitions, 產出符合框架規範的 .feature 檔案,包含 Scenario、Scenario Outline、Examples 等結構。 觸發情境包含但不限於:「幫我產出 feature file」、「把這個轉成 .feature」、「export feature file」、 「根據業務邏輯寫 feature」、「建立測試案例檔」。 即使使用者只說「輸出 feature」或「新增 .feature 檔」,只要有提供業務邏輯或 Gherkin 內容,也應載入此技能。
export-gherkin
by Ting-s515當使用者提供程式碼、業務邏輯說明或需求文檔,並要求將行為或需求轉換為 Gherkin(Given / When / Then)格式時,必須載入此技能。 目的是產出人類可讀的規格文件,用於與 PM、QA、客戶等非技術人員對齊需求、確認驗收條件,而非直接執行的測試框架檔案。 觸發情境包含但不限於:「幫我轉成 Gherkin」、「把這個邏輯寫成 Given When Then」、「export gherkin」、「把需求整理成 Gherkin 格式」、「幫我對齊需求規格」。 即使使用者只說「幫我寫 Given When Then」或「用 BDD 格式描述這個功能」,只要有提供程式碼或業務邏輯,也應載入此技能。 注意:若使用者要求產出「可被測試框架執行的 .feature 檔案」,應使用 export-feature-file 技能而非此技能。
fleet-review
by Ting-s515當使用者明確說出「fleet-review」關鍵字時,才觸發此技能。並行啟動 Claude + Codex 子代理從不同角度審查程式碼,透過跨模型交叉驗證消除誤報。接受一個參數:規格文檔路徑(例如:/fleet-review path/to/spec.md)。不得與 code-reviewer 技能混用,兩者功能不同:fleet-review 需明確呼叫,code-reviewer 則依業務邏輯文檔自動觸發。
llm-repo-raw-capture
by Ting-s515將已完成的深度網路搜尋結果整理到本地 llm-repo 的 raw 資料層,供使用者之後手動 ingest 到 wiki。當任一 AI 工具已完成深度網路搜尋並需要保存可追蹤來源筆記時使用;也適用於 AGENTS.md 或 CLAUDE.md 的深度搜尋委派、「整理到 raw」、「寫入 llm-repo raw」、「保存搜尋結果」,或任何需要在最終回覆前保存已搜尋來源的流程。
llm-repo
by Ting-s515此技能需要時才手動呼叫,在當前 context 中載入本地知識庫(位於 `wiki/` 資料夾)的相關頁面內容,並以此為基礎回答使用者問題。
pff
by Ting-s515Use only when the user's message explicitly contains the "pff" keyword. Scan the current project's docs directory, including tracked files and workspace-only docs that are untracked or uncommitted, to identify what Theon contributed to the project. Consolidate those contribution materials into a standalone Markdown file under the user's .claude/pff directory. Convert the collected evidence into performance review materials and draft narratives aligned with PFF evaluation criteria. Highlight measurable impact, professional growth, ownership, teamwork, and problem-solving contributions.
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.