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...
feishu-cli-api
by riba2534飞书 OpenAPI 裸调。api GET/POST/PUT/DELETE/PATCH <path> 直接调用任意飞书 OpenAPI 接口， 覆盖 feishu-cli 尚未封装的接口（对齐 lark-cli 的 api 能力）。支持 --params(query)/--data(body JSON)/--data-file(从文件读 body)/ --as auto|user|bot 身份/--dry-run 预览/-o 二进制下载/--format/--jq。 当用户请求"调用 X API"、"裸调飞书接口"、"feishu-cli 没封装的接口怎么调"、"raw api"、 "用 api 命令发请求"、"下载飞书媒体/文件 binary"时使用。 不适用：仅查 schema 不调用（用 feishu-cli schema）；已有专用命令的高频场景（用对应 feishu-cli <模块>）。
feishu-cli-approval
by riba2534飞书审批操作（查询 + 写入）。读：definition detail / instance get / task query。 写：instance {create,cancel,cc} + task {approve,reject,transfer}。 instance get、task query、instance cancel/cc、task approve/reject/transfer 需要 User Token； instance create 使用 tenant_access_token。 当用户请求"提交审批"、"审批通过/拒绝"、"撤回审批"、"转交审批"、"抄送"、"审批查询"时使用。
feishu-cli-attendance
by riba2534飞书考勤数据查询（user-task / user-stats）。user-task 查打卡任务/班次； user-stats 查考勤统计（出勤/迟到/早退/请假）。 注意：仅支持 Tenant Token，SDK v3.5.3 限制不接受 User Token； 单次查询跨度上限 31 天，超出会拒绝。 当用户请求"查考勤"、"查打卡记录"、"出勤统计"、"考勤明细"时使用。
feishu-cli-auth
by riba2534飞书 OAuth 认证和 User Access Token 管理（Device Flow，RFC 8628）。 支持一键创建飞书应用、按域申请推荐权限、auth check 预检 scope、auth login 登录、Token 自动刷新。 覆盖 AI Agent 两步授权（--no-wait 拿链接 → --device-code 续轮询）、JSON 事件流解析、部分 scope 未授予（missing_scopes）的判读与补授。 当用户请求登录飞书、获取 Token、OAuth 授权、用户身份授权、device flow、权限缺失、Token 过期、create-app、99991672、99991679， 或其他飞书技能遇到 User Access Token 问题时使用。 本技能同时承载两个相关子命令：doctor 做配置/网络/代理体检（错误信息不指向 scope/token 时用）， profile 管理多 App / 多账号独立配置（多租户切换）。 注意：profile 指 CLI 配置切换，与邮箱 mailbox profile（feishu-cli-mail）无关。
feishu-cli-bitable
by riba2534飞书多维表格（Bitable/Base）操作。底层使用 base/v3 新 API，支持视图完整配置写入、 记录 upsert、记录批量获取、记录附件上传下载、记录修改历史、角色 CRUD + 协作者增删、 多维表格本体重命名/高级权限开关、数据聚合查询、 仪表盘 + 仪表盘块 CRUD、表单 + 表单问题 CRUD、工作流 CRUD 等。 当用户请求"创建多维表格"、"操作数据表"、"添加记录"、"查询记录"、"管理字段"、 "多维表格"、"base"、"bitable"、"数据表"、"视图排序"、"视图过滤"、"视图分组"、 "角色"、"role"、"高级权限"、"advperm"、"数据聚合"、"data query"、 "仪表盘"、"dashboard"、"表单"、"form"、"工作流"、"workflow"、"记录附件"、 "复制多维表格"时使用。 支持 --as bot|user|auto 身份切换：默认 auto（User 优先、Tenant 兜底）， --as bot 用 App Token 操作多维表格，无需 auth login、永不过期， 适合 cron / 无人值守 / 脚本自动抓取多维表格内容。 凡涉及"App Token 读写 bitable"、"不登录抓多维表格"、"cron 定时同步多维表格"、 "bitable 报需要 User Token / 91403 没权限"时也应使用本技能。
feishu-cli-board
by riba2534飞书画板全能操作 · 5 种画图路径任选其一： (A) Mermaid/PlantUML 服务端渲染（思维导图/时序图/类图/饼图/流程图/甘特图，整图作为一个节点，飞书自动排版） (B) Mermaid 本地引擎 whiteboard-cli（绕开 par/参与方数等服务端限制，每个节点可点击编辑） (C) SVG 自由作图（任意视觉：飞轮/鱼骨/Dashboard/海报/插画/架构图等，每个 SVG 元素 → 1 个原生节点可单独编辑） → 使用 scripts/svg_to_board.py 把 SVG 翻译为飞书原生节点 (D) 简单 SVG 单节点装饰（图标/印章/小元素，2KB 以内 SVG） (E) 精排架构图（手写节点 JSON，绝对坐标 + 配色 + 连线 ID 引用） 当用户请求"画图/画板/whiteboard/画架构图/画流程图/画飞轮/画鱼骨/画路线图/画 Dashboard/画插画/画海报/ AI 自由作图/SVG 落画板/克隆画板/上传图片到画板/可视化/节点图/精排"时使用。 特别地，当用户反馈"右下角半截楼""z_index 错乱""节点翻倍""复杂图渲染不全""mermaid 服务端失败" 务必读 references/pitfalls.md 排障。 写类（add-board/create-notes/update/delete/clone/svg-import/upload-image/import）使用 App Token（默认 Bot 身份）， 无需登录；即使用户已 auth login，写类命令仍保持 App 身份不切换。 读类（image/nodes/export-code/lint）登录后自动用 User Token，未登录回落 App Token。
feishu-cli-calendar
by riba2534飞书智能日历。calendar suggestion 找参会人共同空闲时段； calendar room-find 按容量/时段筛会议室；calendar rsvp 接受/拒绝邀请。 HTTP 直调 freebusy/suggestion + freebusy/room_find（SDK v3.5.3 未暴露）， 自动 429 退避（DoWithRetry）。 当用户请求"找开会时间"、"找空闲时段"、"找会议室"、"接受/拒绝会议邀请"、 "freebusy"、"日程冲突检测"时使用。
feishu-cli-card
by riba2534构造美观、元素丰富的飞书 V2.0 交互式卡片（interactive card）。支持折叠面板、 多栏布局、图表、彩色标签、按钮组、人员卡、流式更新等 20+ 组件，内置 7 个场景模板 （通知 / 成功报告 / 告警 / 审批 / 数据大屏 / 文章摘要 / AI 流式）和配色布局规范。 当用户请求"发卡片"、"发通知"、"做告警"、"发报告"、"做审批"、"做 dashboard"、 "美化消息"、"interactive 卡片"、"v2 卡片"、"带图表的消息"、"带按钮的消息"、 "带折叠面板的消息"、"飞书卡片"、"Lark card"、"构造卡片"时使用。 即使用户只说"发个消息告诉 XX"，只要内容有结构（多字段 / 多链接 / 图表 / 状态）， 都应优先用本技能构造卡片而非纯文本。 构造出的 JSON 写入 /tmp/<name>-card.json，随后交给 feishu-cli-msg 用 --msg-type interactive 发送（msg 使用 App Token，无需 auth login）。
feishu-cli-chat
by riba2534飞书会话浏览、消息互动与群聊管理。看聊天记录（单聊/群聊/话题群）、搜群、获取消息详情、 Reaction 表情回应、Pin 置顶/取消置顶、删除消息，以及群聊信息管理（获取/更新/解散/成员）。 当用户请求"看群消息记录 / 拉群聊天记录 / 导出聊天记录 / 获取群历史 / 看话题回复 / 搜群 / 看私聊记录 / dump 飞书消息"时使用本技能；包括话题群（chat_mode=thread）的整线程展开。 读类（msg history/list/get/mget/thread-messages）登录后默认 User Token、未登录回落 Bot； 互动类（reaction/pin/search-chats/chat get/update/delete/member）必需 User Token； msg delete 默认 App Token 用于 Bot 自撤回，可显式 User Token 给管理员撤回场景； chat create/link 默认 Bot 身份创建群/获取群链接。
feishu-cli-drive
by riba2534飞书云盘增强命令组。分块上传大文件（≥20MB 自动 3 段式）、流式下载、 文档异步导出（markdown 快捷路径 / sheet+bitable csv / sub-id / 有界轮询 + resume）、 文档异步导入、文件/文件夹移动（folder 自动轮询）、富文本评论（text/mention_user/link + wiki URL 解析 + 局部评论）、通用异步任务查询、本地 ↔ 云盘单向镜像 （pull/push/status，SHA-256 内容 diff + --delete-* --yes 双确认）、 v2 doc_wiki/search 扁平 filter 搜索（folder-tokens / space-ids / creator-ids / only-title）。 当用户请求"上传大文件"、"下载云盘文件"、"导出为 pdf/markdown/xlsx"、"导入 docx 到云文档"、"移动文件夹"、"添加文档评论"、"@某人评论文档"、"从 wiki 链接评论"、 "查询异步任务状态"、"drive 任务 resume"、"分块上传"、"云盘镜像"、"目录同步"、 "本地与云盘对照"、"SHA 比对"、"按文件夹搜文档"、"feishu drive"、"lark drive"时使用。 本 skill 与老的 file/media/comment 命令组并存，提供更强能力（User Token 支持、 异步 resume、富文本评论），基础场景仍可用 file/media。
feishu-cli-event
by riba2534飞书实时事件订阅（WebSocket）。event list 看支持的 EventKey；event schema 看事件 payload/scope； event consume 启动长连接订阅，事件流以 NDJSON 写到 stdout（阻塞，一个进程订阅一个 EventKey）； event status 看本机活跃 consume 进程；event stop 按 PID / EventKey / --all 停止 consume。 支持 22+ EventKey（im 消息接收/已读/撤回/reaction、群成员变动、contact 员工变更、 日历变更、云盘标题/协作者、审批实例与任务、VC 会议起止）。 支持断线重连和多 EventKey 并行订阅。 当用户请求"监听飞书事件"、"实时接收消息事件"、"订阅审批回调"、"event 流"、 "WebSocket 长连接监听"、"event consume"、"event list / schema / status / stop"、 "AI Agent bot 实时响应"时使用。 注意：本技能只负责订阅；处理事件 webhook 业务逻辑（push 到飞书消息/写多维表格） 请配合 feishu-cli-msg / feishu-cli-bitable。
feishu-cli-export
by riba2534将飞书文档、知识库文档或电子表格导出到本地。支持 docx/wiki/sheet 导出 Markdown， doc export 内嵌电子表格自动展开，图片/画板素材下载，以及 doc export-file 异步导出 PDF/Word/Excel。当用户请求导出文档、保存为 Markdown、导出 PDF/Word/Excel、下载文档图片、 导出表格或表格转 Markdown 时使用。本地导入请用 feishu-cli-import 或 feishu-cli-drive。
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.