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...
pm-competitor-deconstructor
by zephyrwang6按策略/功能/体验/增长四个维度结构化拆解竞品，输出可借鉴点、不可抄点与差异化建议。当用户说"竞品分析"、"竞品拆解"、"帮我分析竞品"、"看看这几个竞品"、"competitor analysis"、"和竞品比一下"、"对标分析"、"差异化怎么做"， 或者用户给出了一份竞品名单并要求系统化分析时，使用这个 Skill。 也适用于：用户上传了竞品截图/链接/体验报告并要求结构化拆解；用户要求对比自己产品与竞品的差距；用户想找差异化切入点。 不适用于：纯需求文档撰写（用 prd-writer）、纯优先级排序（用 prioritization-engine）、纯用户调研设计（用 survey-designer）。
pm-postmortem-writer
by zephyrwang6生成结构化的上线复盘报告，包含目标达成、偏差原因、经验沉淀和后续行动项（含责任归因和改进 owner）。当用户说"写复盘""上线复盘""项目复盘""复盘报告""postmortem""版本回顾""迭代总结""上线总结"， 或者用户提供了上线数据/过程记录/问题清单并要求结构化总结时，使用这个 Skill。 也适用于：事故复盘（P0/P1 事故后的 RCA 报告）、OKR 复盘、季度复盘、A/B 实验复盘。 不适用于：纯需求撰写（用 prd-writer）、纯优先级排序（用 prioritization-engine）、周报日报（用 status-report）。
space-prd-writer
by zephyrwang6把模糊需求转化为可评审的产品需求文档（PRD）。当用户说"写个需求文档"、"帮我出PRD"、"这个功能怎么写需求"、"我有个想法想落地"、"把这个需求整理成文档"、"需求评审要用的PRD"，或者用户描述了一段功能但没有结构化时，使用这个 Skill。 也适用于：用户上传了原始需求描述/会议纪要/聊天截图并要求整理成PRD；用户说"PRD"、"产品需求"、"需求文档"、"功能说明书"等关键词；用户要求对已有PRD进行补全、优化、查漏补缺。 不适用于：纯技术方案设计（用 architecture）、纯 UI 稿标注（用 design-handoff）、项目管理类文档（用 status-report）。
space-prioritization-engine
by zephyrwang6对需求/功能/项目进行多维度优先级排序，输出版本排期建议。当用户说"帮我排优先级"、"这些需求怎么排"、"用 RICE 打分"、"ICE 评分"、"Kano 分析"、"成本收益分析"、"功能排期"、"路线图规划"、"哪些先做哪些后做"、"版本规划"， 或者用户列出了一批需求/功能/项目并需要决策顺序时，使用这个 Skill。 也适用于：用户想比较多个优先级模型的结果；用户对当前路线图有疑问想重新评估；资源有限需要砍需求；用户提到"RICE"、"ICE"、"Kano"、"优先级矩阵"等专业术语。 不适用于：纯项目管理（排期甘特图）、纯需求文档撰写（用 prd-writer）、纯用户调研设计（用 survey-designer）。
space-review-board
by zephyrwang6模拟多角色 PRD/原型评审会，从产品、研发、测试、设计、运营、法务六大视角给出评审结论。当用户说"帮我评审一下这个 PRD"、"看看这个需求有没有问题"、"模拟评审会"、"review 一下这个文档"、"这个需求能不能过评审"、"帮我查漏补缺"时触发。 也适用于：用户上传了 PRD、需求文档、原型截图、功能说明并要求检查；用户提到"评审"、"review"、"过会"、"需求评审"、"方案评审"等关键词；用户要求从研发或测试视角看需求是否可行。 不适用于：写 PRD（用 SPACE-prd-writer）、纯代码审查（用 code-review）、纯设计走查（用 design-critique）。
space-roadmap-planner
by zephyrwang6版本规划与路线图设计 Skill。从季度目标、团队产能、依赖方信息出发，输出可执行的版本路线图（里程碑、依赖风险、缓冲策略、每阶段成功指标）。 触发条件：用户提到"路线图"、"版本规划"、"roadmap"、"里程碑"、"季度计划"、"迭代规划"、"版本排期"、"项目排期"、"依赖梳理"、"风险预案"、"缓冲方案"、"迭代计划"、"sprint规划"、"release plan"、"OKR拆解"等关键词。 也适用于：用户提供季度目标/团队产能/依赖信息要求排期；用户要求将战略目标拆解为可执行的里程碑；用户要求评估项目风险和缓冲方案；用户要求制定跨团队协作的版本计划。 典型输入：季度目标 + 团队产能 + 依赖方信息 + 约束条件。 不适用于：每日站会（直接沟通）、单个需求设计（用 SPACE-prd-writer）、数据分析（用 SPACE-analytics）。
space-survey-designer
by zephyrwang6设计高质量调研问卷。当用户说"设计问卷"、"做个调研"、"帮我出份问卷"、"用户调研"、"满意度调查"、"NPS问卷"、"市场调研"、"需求调研"、"问卷设计"、"survey design"， 或者用户描述了一个调研目标但还没有结构化的问卷时，使用这个 Skill。 也适用于：用户上传了已有问卷要求优化/查偏差/补充题目；用户说"帮我检查这份问卷有没有问题"；用户需要设计 A/B 测试问卷、焦点小组访谈提纲、NPS/CSAT/CES 调查； 用户提到"诱导题"、"双重问题"、"问卷偏差"等专业术语。 不适用于：纯数据分析（用 data-analysis）、纯用户访谈记录整理（用 content-digest）、纯产品需求文档（用 prd-writer）。
tracking-spec-writer
by zephyrwang6埋点与指标设计方案生成器。从产品需求/核心链路出发，输出完整的埋点方案文档（事件、字段、触发时机、口径说明、QA 校验清单）。 触发条件：用户提到"埋点"、"tracking"、"事件设计"、"数据采集"、"上报方案"、"埋点方案"、"事件规范"、"字段设计"、"指标口径"、"数据验收"、"QA校验"等关键词。 也适用于：用户提供产品PRD/需求文档要求产出埋点方案；用户提供核心用户链路要求拆解事件；用户要求规范化事件命名或字段定义；用户要求设计数据验收方案。 典型输入：事件命名规范 + 字段字典 + 核心链路描述/流程图。 不适用于：纯数据分析（用 SPACE-analytics）、纯BI看板搭建、纯SQL查询编写。
space-analytics
by zephyrwang6从数据现象出发，生成可执行的产品决策建议，并以可视化 HTML 报告输出。当用户说"分析一下这组数据"、"这个指标为什么跌了"、"帮我做个留存分析"、"用户流失原因是什么"、"看看漏斗哪一步掉了"、"给我出个数据分析报告"时触发。 也适用于：用户上传了 CSV/Excel 数据文件并要求分析洞察；用户提供了 SQL 查询结果要求解读；用户要求做指标拆解、归因分析、分群对比、A/B 实验分析；用户提到"指标树"、"漏斗"、"留存"、"转化率"、"DAU 下降"、"分群"、"归因"等数据分析关键词。 不适用于：纯 BI 看板搭建（用 xlsx）、纯 SQL 编写（直接写）、纯数据清洗（直接写脚本）。
space-experiment-designer
by zephyrwang6A/B 实验设计 Skill。从实验目标出发，输出完整的实验方案（假设、分组、指标体系、样本量估算、止损规则、判定规则）。 触发条件：用户提到"A/B 测试"、"AB 实验"、"实验设计"、"对照实验"、"分流实验"、"灰度方案"、"实验方案"、"样本量计算"、"显著性检验"、"实验评估"、"p值"、"置信区间"、"MDE"、"统计功效"、"实验周期"、"止损规则"等关键词。 也适用于：用户提供了实验目标/可改动点/数据量级/周期限制要求产出实验方案；用户要求评估现有实验设计是否合理；用户要求制定实验判定标准和决策规则。 典型输入：实验目标 + 可改动点 + 当前数据量级 + 可接受实验周期。 不适用于：纯数据分析（用 SPACE-analytics）、纯埋点设计（用 tracking-spec-writer）、纯PRD写作（用 SPACE-prd-writer）。
image2pencil
by zephyrwang6将截图/设计稿复刻为 Pencil .pen 设计，并在同一画布旁输出结构化设计文档。用户提到“按图复刻”“照着截图画页面”“image to pencil”“做一个一模一样的页面”“根据这张图做设计稿”“输出设计图和文档”时使用本 Skill。 也适用于：用户要求修改已有 .pen 页面、追加右侧设计文档、做像素级对齐、根据多张截图整合一套页面。 本 Skill 必须调用 pencil MCP 工具完成读取、绘制和截图校验；若信息不全，先向用户索取缺失信息再开始绘制。
space-image2proto
by zephyrwang6Screenshot-to-HTML prototype generator with iterative refinement and learning memory. Use this skill whenever the user provides a screenshot, mockup, wireframe, or image of any UI and wants it reproduced as a working HTML prototype — or when they want to modify an existing prototype they previously generated. Also triggers on: "照这个做原型", "参考这个图", "把这个页面画出来", "this UI needs to be prototyped", "replicate this design", "convert this mockup to HTML", "帮我出个原型", "根据截图输出 HTML", or any image attachment combined with requests like "输出 HTML", "做成页面", "帮我实现". Even if the user just sends a screenshot with a brief instruction like "加一个字段" or "这个也一样", this skill applies — it means they want you to modify or replicate the UI shown. When in doubt, if there's a UI screenshot in the conversation, use this skill.
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.