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...
wk-gh-pr-review-fix
by YuXilong-LabsUse when working on a GitHub pull request and the task is to inspect unresolved review threads, act on actionable feedback, and close the loop by verifying, pushing, replying, and resolving the threads.
wk-instinct
by YuXilong-Labs会话学习系统 — 从 Claude Code 对话中提取可复用模式，保存为原子 instinct 文件（含置信度评分），积累后演化为正式 Skill 或全局规则。
wk-ios-component-reuse
by YuXilong-LabsiOS 组件库复用工作流 — 选型、实现、审查、迁移阶段强制执行"先检索组件再行动"， 输出证据驱动的决策。依赖 MCP ios-components server。 支持 4 种模式：selection / implementation / review / migration。
wk-lark-wiki-batch
by YuXilong-LabsUse when batch-generating, Haiku-polishing, or uploading multiple iOS base component API docs to Lark Wiki. Triggers: in mcp-ios-components project with pods_dir, need main-branch base components only, need batch wiki sync. Symptoms: need all base components docs at once, want default Haiku whole-document polish, need branch auto-pull + update-or-create upload, need hash-based incremental skip.
wk-lark-wiki
by YuXilong-LabsUse when generating, polishing, or uploading iOS component API documentation to Lark Wiki. Triggers: in mcp-ios-components project or any CocoaPods component directory (has .podspec). Symptoms: need API docs from source code, docs need AI polish, docs need Lark Wiki sync.
wk-review
by YuXilong-Labs本地代码修改 Review 工具 — 以资深 iOS/移动端开发视角审查 git diff， 关注逻辑 bug、crash 风险、内存泄漏、性能问题、线程安全、资源管理。 采用 Agent 并行审查架构，每个文件/模块由独立 Agent 子进程审查， 确保上下文隔离、审查专注、大 diff 不挤占主对话空间。 所有结论附带准确行号和代码证据，分级输出，只读不改。
wk-scan-clean-code
by YuXilong-LabsiOS/macOS 代码清理审计工具 — 识别 ObjC/Swift 工程中可安全删除的字段、方法、文件。 支持 4 种扫描模式：Model 字段审计、死代码检测、无用文件检测、全量扫描。 所有结论附带证据链，分级输出，宁可保守不误删。
wk-skill-create
by YuXilong-LabsSkill 生成工具 — 分析 git 历史和现有代码提取编码模式，生成符合本仓库规范的 SKILL.md 草稿；也用于从现有 instinct 集合演化为完整 Skill。
wk-symbol-reference-scan
by YuXilong-LabsiOS 工程全局符号引用扫描工具 — 覆盖源码、Framework Headers、二进制 strings 三条路径。 支持 single/batch/related 三种模式，输出结构化 Markdown 表格报告。 证据驱动、只读不修改、多源并行搜索。
wk-sync-pb
by YuXilong-Labs同步上游 proto submodule 并重新生成 ObjC Protobuf 代码的完整自动化工作流。 TRIGGER: 用户执行 /wk-sync-pb 命令时触发。 流程：拉取上游 proto → 生成 ObjC 代码 → 敏感词检查 → 用户确认 → 提交推送。
wk-tdd
by YuXilong-LabsiOS/macOS TDD 工作流引导 — 强制先写测试（RED→GREEN→REFACTOR）， 覆盖 Swift Testing / XCTest / OCMock，内置覆盖率验证。 每个阶段产出可直接运行的代码，不允许跳过 RED 阶段。
wk-xcodebuild
by YuXilong-LabsiOS/macOS 工程编译与测试的 xcodebuild / swift(SwiftPM) 智能包装工作流。 当需要执行 xcodebuild 编译（build）、测试（test/build-for-testing）、归档（archive）、 分析（analyze），或 swift build / swift test（Swift Package Manager）时使用本 Skill， 而非直接运行裸 xcodebuild / swift build/test。 xcodebuild 路径会自动检测本机 USB 真机并设为目标（无真机回退 My Mac）； swift 路径为本机构建、不选设备。两者都参考 rtk 的方式精简海量输出，只把关键信息 （结果、error、链接/签名错误、测试失败用例、warning 去重计数）返回给 agent， 完整日志落盘，显著减少上下文填充、节省 token。 test 类动作自动注入 -resultBundlePath 并在摘要追加 xcresult 权威分区 （xcresulttool 计数对 XCTest / Swift Testing 统一）；另提供 xcb result（xcresult 测试结果摘要，替代裸 xcresulttool get test-results）与 xcb cov（覆盖率摘要， 替代裸 xccov view --report）子命令。 CocoaPods 路径（xcb pod …）覆盖 pod install / update / repo update / lib|spec lint， 摘要只保留依赖变更、[!] 警告/错误块、lint ERROR/WARN。 TRIGGER：用户要求编译/构建/跑测试/build/test/run on device/真机调试/swift build/swift test， 或要查看测试结果/xcresult/覆盖率，或要装/更新 Pods（pod install/update）， 或 agent 准备调用 xcodebuild、swift build/test、pod install/update/lint、 xcresulttool get test-results、xccov view --report 时。
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.