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...
use-other-model
by ruan-cat指导主代理如何驱动其他 AI 模型(MiniMax、Gemini)完成任务,实现 50-80% token 节省。提供两种方案:方案 A(MCP 工具,适合简单任务)和方案 B(独立 Claude Code 会话,适合复杂任务)。当用户提及使用其他模型、节省 token、批量操作、多文件处理、或执行时间超过 5 分钟的任务时使用此技能。包含完整的技术实现细节、代码模板和安全最佳实践。
openspec-explore
by ruan-catEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
clone-ruancat-repo
by ruan-cat按固定清单快速克隆 GitHub 用户 ruan-cat 的常用仓库(及 tocque/h5mota-web)到约定目录名, 支持浅克隆与多分支抓取等参数组合。在用户提及「克隆 ruan-cat 仓库」「拉常用仓库」 「clone-ruan-cat」「初始化本地多仓」「同步阮喵喵 GitHub 仓库」或需要一键复现本机仓库存量时使用。 命令清单以 references/clone-commands.md 为唯一真实来源。
pr-ruancat-repo
by ruan-cat用于对 ruan-cat 相关仓库执行批量 Pull Request、跨仓库同步改动、为多个已克隆本地仓库规划 PR 策略、选择本地 git/Bash 与 GitHub API/MCP 混合执行方式的场景。触发关键词包括“批量 PR” “多仓库同步改动”“对 ruan-cat 的仓库发 PR”“pr-ruancat-repo”。
use-wd-form
by ruan-cat使用 wot-design-uni 的 wd-form 组件编写表单页的标准规范 - 提供表单结构、wd-picker 选择器、校验规则、提交处理的完整规范。 触发条件(满足任意一项即触发): - 页面包含 <wd-form> 组件 - 需要实现表单页面(创建、编辑、提交等) - 需要添加选择功能(必须使用 wd-picker 而非 wd-radio-group) - 需要添加表单分区标题(必须使用 FormSectionTitle) - 用户提及"表单"、"wd-form"、"表单校验"、"表单提交"等关键词 - 从 Vue2 迁移表单页面 - 需要实现单选/多选功能(单选用 wd-picker,多选用 wd-checkbox-group) 必须协同的技能: - beautiful-component-design(FormSectionTitle、图标、美化) - api-migration(如果有接口调用) - api-error-handling(如果有接口调用) - code-migration + component-migration(从 Vue2 迁移时) 禁止项: - 禁止使用 wd-radio-group 实现单选(应使用 wd-picker) - 禁止使用 <view class="section-title"> 代替 FormSectionTitle - 禁止 wd-cell 包裹 wd-picker(正确:wd-picker 包裹 wd-cell) - 禁止使用不存在的 #value 插槽 - 禁止单选初始化为数组(应为空字符串) - 禁止多选初始化为字符串(应为空数组) 覆盖场景:维修工单创建、房屋申请、投诉录单、活动报名、用户信息编辑等所有表单页面。
neon-postgres
by ruan-catGuides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.
neon-postgres-zh
by ruan-cat使用 Neon Serverless Postgres 的指南和最佳实践。涵盖入门、使用 Neon 进行本地开发、选择连接方式、Neon 功能、身份验证 (@neondatabase/auth)、PostgREST 风格的数据 API (@neondatabase/neon-js)、Neon CLI 以及 Neon 的平台 API/SDK。用于任何与 Neon 相关的问题。
code-migration
by ruan-cat专注于 Vue2 Options API 到 Vue3 Composition API + TypeScript 的迁移。 触发条件(满足任意一项即触发): - 任务包含"Vue2 到 Vue3"、"Options API"、"Composition API"、"代码迁移"等关键词 - 需要将 Options API(data、methods、computed)转换为 Composition API(ref、reactive、computed) - 需要添加 TypeScript 类型定义 - 需要迁移生命周期钩子(mounted → onMounted) - 需要将 Vuex 迁移到 Pinia - 需要编写组合式函数(Composables) - 需要添加 definePage 页面配置 - 需要处理静态资源导入(@/ 别名 → import) - 从 Vue2 项目迁移页面代码 必须协同的技能: - component-migration(组件迁移)- ColorUI → wot-design-uni - style-migration(样式迁移)- ColorUI 类名 → UnoCSS 原子类 - api-migration(如果有接口)- API 调用 - api-error-handling(如果有接口)- 错误提示 - route-migration(路由迁移)- pages.json → 约定式路由 禁止事项: - 禁止使用 export default {}(必须使用 <script setup lang="ts">) - 禁止使用 this(Composition API 中不存在 this) - 禁止使用 any 类型(必须明确类型) - 禁止在 definePage 中添加 name 或 meta 字段(只使用 style) - 禁止在微信小程序样式中使用 * 通配符选择器 - 禁止在模板中直接使用 @/ 别名字符串(静态资源必须 import) 覆盖场景:几乎所有从 Vue2 迁移到 Vue3 的页面都需要此技能,包括代码结构、响应式数据、生命周期、状态管理等。
route-migration
by ruan-cat专注于 Vue2 传统路由配置到 Vue3 约定式路由的迁移。 触发条件(满足任意一项即触发): - 任务包含"路由迁移"、"pages.json"、"约定式路由"、"路由配置"等关键词 - 需要从 pages.json 迁移到文件系统路由 - 需要添加 definePage 页面配置 - 需要配置强类型路由系统(TypedRouter) - 需要更新路由跳转代码(uni.navigateTo → TypedRouter) - 需要处理多平台路由适配 - 需要查阅路由迁移映射表(docs/prompts/route-migration-map.yml) - 从 Vue2 项目迁移页面路由 必须协同的技能: - code-migration(代码迁移)- Vue2 → Vue3 代码写法 - component-migration(组件迁移)- ColorUI → wot-design-uni - style-migration(样式迁移)- ColorUI 类名 → UnoCSS 原子类 禁止事项: - 禁止自行决定路由路径(必须查阅映射表) - 禁止使用 uni.navigateTo 字符串拼接(必须使用 TypedRouter) - 禁止在 definePage 中添加 name 字段(只使用 style) - 禁止跳过 definePage 配置(会导致标题显示为 "unibest") - 禁止不更新映射表状态(完成后必须添加 ✅ 标记) 覆盖场景:几乎所有从 Vue2 迁移到 Vue3 的页面都需要此技能,包括路由配置、页面跳转、参数传递等。
use-wd-form
by ruan-cat使用 wot-design-uni 的 wd-form 组件编写表单页的标准规范 - 提供表单结构、wd-picker 选择器、校验规则、提交处理的完整规范。 触发条件(满足任意一项即触发): - 页面包含 <wd-form> 组件 - 需要实现表单页面(创建、编辑、提交等) - 需要添加选择功能(必须使用 wd-picker 而非 wd-radio-group) - 需要添加表单分区标题(必须使用 FormSectionTitle) - 用户提及"表单"、"wd-form"、"表单校验"、"表单提交"等关键词 - 从 Vue2 迁移表单页面 - 需要实现单选/多选功能(单选用 wd-picker,多选用 wd-checkbox-group) 必须协同的技能: - beautiful-component-design(FormSectionTitle、图标、美化) - api-migration(如果有接口调用) - api-error-handling(如果有接口调用) - code-migration + component-migration(从 Vue2 迁移时) 禁止项: - 禁止使用 wd-radio-group 实现单选(应使用 wd-picker) - 禁止使用 <view class="section-title"> 代替 FormSectionTitle - 禁止 wd-cell 包裹 wd-picker(正确:wd-picker 包裹 wd-cell) - 禁止使用不存在的 #value 插槽 - 禁止单选初始化为数组(应为空字符串) - 禁止多选初始化为字符串(应为空数组) 覆盖场景:维修工单创建、房屋申请、投诉录单、活动报名、用户信息编辑等所有表单页面。
style-migration
by ruan-cat专注于 ColorUI 到 UnoCSS + wot-design-uni 的样式系统迁移,从传统 CSS 框架到现代化原子 CSS。 触发条件(满足任意一项即触发): - 任务包含"样式迁移"、"ColorUI"、"UnoCSS"、"原子 CSS"等关键词 - 需要将 ColorUI 类名(cu-btn、cu-list、cu-card)迁移到 UnoCSS 原子类 - 需要将 SCSS 变量迁移到 UnoCSS 主题配置 - 需要将固定像素(20px)转换为响应式单位(20rpx) - 需要迁移渐变背景(bg-gradual-* → bg-gradient-to-*) - 需要迁移间距样式(margin-xs → m-10rpx) - 需要迁移圆角样式(radius-sm → rounded-8rpx) - 从 Vue2 项目迁移页面样式 必须协同的技能: - component-migration(组件迁移)- ColorUI → wot-design-uni - code-migration(代码迁移)- Vue2 → Vue3 代码写法 - beautiful-component-design(可选)- 样式美化 禁止事项: - 禁止滥用 UnoCSS shortcuts 功能(不要将业务样式写入 uno.config.ts) - 禁止将 ColorUI 类名直接转为 shortcuts(应展开为原子类) - 禁止在微信小程序样式中使用 * 通配符选择器 - 禁止使用 UnoCSS 的 space-y-* / space-x-* 类(微信小程序不支持) - 禁止使用 UnoCSS 的 divide-y-* / divide-x-* 类(微信小程序不支持) - 禁止使用复杂的 :nth-child() 选择器(如 n+2, 3n+1) - 禁止使用 :not() 伪类选择器(特别是 :not([hidden])) 覆盖场景:几乎所有从 Vue2 迁移到 Vue3 的页面都需要此技能,包括布局、颜色、间距、形状、渐变等样式。
beautiful-component-design
by ruan-cat移动端 uni-app + wot-design-uni 组件美化规范 - 提供图标、文本对齐、响应式设计、表单分区标题、选择器美化、弹框交互的完整规范。 触发条件(满足任意一项即触发): - 需要添加 FormSectionTitle 组件(表单分区标题) - 需要使用 Carbon Icons 图标 - 需要实现响应式设计(rpx 单位、图片网格) - 需要美化选择器组件(wd-picker) - 需要实现弹框交互(wd-message-box、wd-popup) - 需要美化详情页卡片(通栏标题 + 色彩编码) - 用户提及"美化"、"图标"、"对齐"、"响应式"、"FormSectionTitle"等关键词 - 修复组件嵌套顺序错误(wd-picker 和 wd-cell) - 修复插槽使用错误(#value 插槽不存在) 必须协同的技能: - use-wd-form(表单页面必须协同) - api-migration(如果有接口调用) - api-error-handling(如果有接口调用) - z-paging-integration(列表页面美化) 禁止项: - 禁止使用 <view class="section-title"> 代替 FormSectionTitle - 禁止 wd-cell 包裹 wd-picker(正确:wd-picker 包裹 wd-cell) - 禁止使用不存在的 #value 插槽(wd-cell 没有此插槽) - 禁止使用 wd-popup 实现标准交互(应使用 wd-message-box) - 禁止在详情页卡片容器保留 padding(应移除以实现通栏标题) 覆盖场景:表单页面、详情页面、列表页面、选择器页面、弹框交互、图标使用、响应式布局等所有需要美化的场景。
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.