Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 551 files from 1 750 authors, of which 61 898 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Verifies the work plan is implementable end-to-end and resolves verification-lane / fixture / E2E-environment gaps before the build phase begins. Use when "implement-ready/verification readiness/lane setup/E2E environment missing" is mentioned, or before any build phase begins on a work plan whose readiness has not been preflight-checked.
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow
Design Doc compliance and security validation with optional auto-fixes
Execute materialized fullstack task files with layer-aware agent routing
Orchestrate full-cycle implementation across backend and frontend layers
Generate text, images, video, and audio from the terminal using AI models.
Browser automation CLI for AI agents. Requires Node.js with agent-browser. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
A simple calculator that can add, subtract, multiply, and divide numbers. Use when the user needs to perform basic arithmetic operations.
通过 Evotown Database MCP Proxy 对已注册的业务数据库执行只读 SQL 查询。当用户需要查 CRM、订单、报表等结构化数据时使用；禁止直连数据库或写入 SQL。
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
发起 HTTP 网络请求，支持 GET、POST、PUT、DELETE、PATCH 方法。当用户需要调用 API、获取网页内容、发送数据到服务器时使用。
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Report Evotown dispatch job completion after the agent finishes real work.
Queue a cross-agent or cross-team handoff through the Evotown control plane.
A股分析研究助手，提供行情数据获取与技术面/基本面分析框架（仅供研究参考，不构成投资建议）。适用于：(1) 获取A股行情和历史数据，(2) 技术面分析（K线形态、MACD、KDJ、RSI、布林带等），(3) 基本面分析（财务指标、估值分析），(4) 板块热点追踪，(5) 选股策略筛选与量化因子分析，(6) 生成股市分析报告。当用户询问"帮我分析股票"、"今日选股"、"A股行情分析"、"技术分析"、"量化选股"时触发。不用于：预测明日涨跌或给出确定性买卖指令、代客决策、港股美股（数据源不同）、加密货币。
资深高考命题专家助手,提供专业的命题指导和评审服务。适用于创作高考试题、评审试题质量、分析试卷结构、了解命题趋势等场景。结合文档工具提取解压文件,使用网络搜索了解当年最新命题趋势,使用分析工具评估题目质量和试卷结构。涵盖"一核四层四翼"评价体系、题型规范、评分标准、命题流程等多个维度。不用于:大学/考研/中考命题(体系不同,仅可借鉴)、日常作业题编写、直接替考生解题。
用火山引擎 Podcast AI 模型生成中文双人对话播客。当用户要把文章、报告、话题文本转成播客音频、生成对话式音频内容时使用，需要环境具备火山引擎 APP_ID 和 ACCESS_KEY。支持 mp3/ogg_opus/pcm/aac、语速调节、自定义音色、断点续传。不用于：单人朗读式 TTS（用普通语音合成）、英文播客（模型主要优化中文）、播客文稿本身的撰写（先用写作类 skill 产出文本再来）。
用 ByteDance Seedream 4.0 API（经 Segmind）生成 AI 图像。当用户要从文字描述生成营销素材、海报、产品图、概念图、社交媒体配图等高质量图像，且环境配有 SEGMIND_API_KEY 时使用。支持 2K/4K、多比例、单次最多 15 张批量、最多 3 张参考图控风格。不用于：修改/编辑已有图片（用图像编辑类 skill）、视频生成、无 API 环境下的快速配图需求。
大学备考苏格拉底式学习助手，专为应对"面向课本和PPT考试"设计。当用户说"帮我复习"、"准备考试"、"备考"、"期末复习"、"模拟学习"、"突击复习"等时触发。核心特点：(1)强制要求用户上传课本/PPT/考纲等原始材料——没有材料就无法有效辅导；(2)使用苏格拉底式提问法，不直接灌输而是引导思考；(3)专注于应用型和理解型内容，而非纯概念记忆；(4)模拟真实考试场景进行针对性练习；(5)分析材料识别高频考点和重难点。适用于大学各科目期中期末考试备考、突击复习、考前模拟。
| 将天气要素（风速、能见度、降雨量等）单站预报系统的项目文档、模型、报告、评估结果整理成符合省级自然科学基金项目编写规范的专题研究报告。适用于：(1) 基于Claude Code + OpenSpec开发的气象预报系统结题报告编写，(2) 将技术文档转换为学术研究报告格式，(3) 生成符合省级自然科学基金规范的专题研究报告，(4) 整合项目代码、模型、评估指标等技术材料为规范化学术报告。触发关键词："专题研究报告"、"结题报告"、"天气预报系统"、"基金项目报告"、"风速预报"、"能见度预报"、"降雨量预报"、"气象预测"、"单站预报"等。
Build and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/document a codebase, build a code wiki, create project documentation from source, or update an existing .llm-wiki. Triggers on phrases like "build wiki", "analyze this codebase", "document this project", "update wiki", "llm-wiki", or when entering an unfamiliar project that has no .llm-wiki yet.
AI咨询/销售的对话策略助手。当用户需要准备AI方案沟通、跟业务部门聊AI落地、写AI提案、应对客户异议、做AI培训破冰时使用。触发场景："怎么跟老板聊AI"、"客户说AI不靠谱"、"准备一个AI方案汇报"、"帮我想想怎么推AI"、"业务部门不配合"、"AI项目怎么卖"、"demo之后怎么跟进"。也适用于AI咨询师、技术合伙人、CTO做内部AI推广。
Windows C盘清理和磁盘空间管理。当用户说C盘满了、磁盘空间不足、清理临时文件/缓存/回收站/系统日志、查找大文件、分析磁盘占用时使用。仅适用于 Windows 环境。不用于：macOS/Linux 磁盘清理、卸载软件（引导用户走系统卸载）、清理用户个人文件（只报告位置，删除决定权在用户）。
PPT 生产 Agent：理解场景 → 推荐风格 → 先出大纲 → 定义页面 → 双通路交付（PPT 内容稿 / 逐页视觉图 / 信息图组图）。当用户要做汇报、路演、培训课件、提案、咨询报告的演示文稿，或要把大纲/文章做成 slides、deck、PPT、信息图、小红书图文、可视化传播图时使用。支持指定风格或从风格库推荐，支持 image 模型逐页出视觉稿。前身为 notion-infographic（v2）并吸收 ppt-designer 的设计原则。不用于：pptx 文件的纯技术操作（拆分/合并/提取，用宿主 pptx skill）、演讲稿或文章本体的写作（用 wechat-article-writer）、需要先做研究的内容调研（先走 deep-research 再回来）、单张海报或 logo 设计。
> Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need synthesis across multiple external sources, iterative follow-up research, or a reusable written artifact. Do not use for quick factual lookups, single-source summaries, simple Q&A, summarizing one document the user already provided, plan-only requests where the user explicitly defers the actual research, or when the user wants a short answer with no need for cited evidence (a short but evidence-backed conclusion is still a brief "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析".
胥克谦式AI-Native产品开发方法论。适用于：(1) 使用AI Agent（Claude Code、Codex、Cursor等）进行产品级软件开发，(2) 设计和优化Harness/Skill体系，(3) 文档驱动开发(SDD)流程，(4) 构建自动化质量门禁和eval机制，(5) Token成本优化与缓存策略，(6) 产品人转型开发者的AI编程实践。触发场景包括"帮我设计开发流程"、"怎么降低token成本"、"怎么提高AI编码质量"、"文档驱动"、"质量门禁"、"harness设计"、"单agent vs multi-agent"、"自动化迭代"、"AI产品开发"、"SDD"、"eval机制"等。即使用户只是说"帮我用AI写代码"或"怎么让agent干活更靠谱"也应触发。注意：如果产品是行为开放、用户输入不可穷举的AI-native类型，请改用 xuefeng-method skill。不用于：单个bug修复或小改动（无需方法论）、PRD需求文档写作（用product-manager）。
用 MinerU 将复杂PDF文档转换为LLM友好的Markdown/JSON格式。适用于：(1) PDF转Markdown/JSON，(2) 提取PDF中的文本、表格、公式、图像，(3) 解析学术论文、技术文档、商业报告，(4) 为RAG应用准备文档数据，(5) 批量处理PDF。触发关键词："PDF解析"、"PDF转Markdown"、"提取PDF表格/公式"、"MinerU"、"parse PDF"等。不用于：PDF的阅读/填表/签名/拆分合并（用宿主pdf工具）、Word/PPT等非PDF格式解析、只需读几页内容的场景（直接读即可，不必转换）。
结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现"，或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查（正确性/安全/性能/可读性/健壮性五维度），重点捕捉 AI 生成代码的特有缺陷。不用于：对已有 PR 的正式评审（用 code review 流程）、安全专项扫描（用 security-audit）、10 行以内的简单片段。
资深产品经理助手，提供 PRD/MRD/BRD 创作与评审、产品策略、留存增长、竞品分析、功能优先级，以及 grill-me-to-doc 逐轮访谈。用户要求“逐个问我”“先把需求问清楚”“grill me”“把想法变成产品文档”时进入 grill-me-to-doc：先读仓库证据，每轮只问一个决策，给推荐答案与理由，记录决策和未决项，支持 resume，产出结构化 PRODUCT-DOC；文档完成且用户批准前硬停止，任何时候都不写实现代码。即使未提“产品”，讨论 App 功能、增长或商业模式也应触发。不用于：单纯代码实现、系统架构深设（用 solution-architect）、需多源引用的市场调研（用 deep-research）、纯营销文案。
全面的代码安全检查和服务器安全审计skill。适用于：(1) 代码漏洞扫描 - 检测SQL注入、XSS、SSRF等OWASP Top 10漏洞，(2) 依赖安全检查 - 识别过时或有漏洞的第三方库，结合实时搜索确认最新CVE，(3) 服务器配置审计 - 检查SSH、防火墙、权限等安全配置，(4) 敏感信息泄露检测 - API密钥、密码、令牌等硬编码检测，(5) 容器安全扫描 - Docker镜像和Kubernetes配置审计，(6) CI/CD安全检查。触发关键词："安全检查"、"漏洞扫描"、"代码审计"、"security audit"、"vulnerability scan"、"SAST"、"dependency check"、"CVE检测"等。不用于：修复单个已定位的bug、编写新的安全功能代码、对无授权的第三方系统做扫描或渗透测试。
解决方案架构师助手。当用户要设计新系统架构、评审现有架构、做技术选型决策、诊断性能/可扩展性/可用性问题、规划架构演进或重构时使用。覆盖微服务、事件驱动、云原生等架构模式，技术趋势通过实时搜索获取而非依赖内置知识。不用于：具体功能的代码实现、安全漏洞审计（用security-audit）、产品需求分析（用product-manager）、只需一句话回答的技术常识问题。
Three.js 性能优化指南。当 Three.js/React Three Fiber 项目出现掉帧、内存增长、加载缓慢、绘制调用过多，或需要迁移 WebGPU、实现大规模粒子/实例化渲染、配置资源压缩管线时使用。触发关键词："Three.js 优化"、"WebGPU"、"draw calls"、"内存泄漏"、"TSL"、"InstancedMesh"、"R3F 优化"等。不用于：通用 React 性能问题（用 vercel-react-best-practices）、WebGL/Three.js 入门教学、3D 美术资产的制作本身。
专业微信公众号文章助手，支持四个独立且可组合模式：article 写正文；image-prompts 从文章生成版本化、provider-neutral 的图片提示词 manifest 与稳定占位符，但不调用生图；layout 把文章和 manifest 确定性转换为微信安全的内联 HTML；full-pipeline 串联正文、提示词/占位符和排版。用户提到公众号、微信文章、推文、配图提示词、图片 manifest、公众号排版、内联 HTML 或完整图文流水线时触发。支持企业官号、个人技术博客、活动回顾和产品评测。不用于：带引用的研究报告（用 deep-research）、PPT/组图（用 deck-studio）、英文文章、仅润色一小段。永不自动发布，永不把提示词或占位符声称为已生成图片。
雪峰式AI-Native产品开发方法论。适用于：(1) 用户行为开放、不可穷举的AI-native产品（AI日历、AI助手、AI推荐、对话式产品等），(2) 强模型依赖型场景，AI驱动核心决策而非仅辅助，(3) 多专精Agent架构设计与分工，(4) 上线后快速校准、行为审计与漂移检测，(5) 模型选择和智能路由策略，(6) 概率性输出的质量评估。触发场景包括"AI-native产品怎么做"、"用户行为不可预测怎么办"、"多agent怎么分工"、"模型漂移怎么处理"、"校准到95%太难了"、"唯快不破"、"怎么选模型"、"agent并行分工"、"AI产品上线后怎么迭代"。注意：如果产品是场景明确、边界可定义的+AI类型，请改用 keqian-method skill。即使用户没有明确说"AI-native"，但在讨论AI驱动决策、用户行为不可预测、概率性输出等话题时也应触发。
Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+ files), complex multi-step workflows, iterative processing, or mentions efficiency/performance.
Perform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request renaming identifiers, replacing deprecated code patterns, updating method calls, or making consistent changes across multiple locations.
Transfer code between files with line-based precision. Use when users request copying code from one location to another, moving functions or classes between files, extracting code blocks, or inserting code at specific line numbers.
Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.
Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
Sets up new projects or improves existing projects with development best practices, tooling, documentation, and workflow automation. Use when user wants to start a new project, improve project structure, add development tooling, or establish professional workflows.
Create comprehensive HTML architecture diagrams showing data flows, business objectives, features, technical architecture, and deployment. Use when users request system architecture, project documentation, high-level overviews, or technical specifications.
Create HTML dashboards with KPI metric cards, bar/pie/line charts, progress indicators, and data visualizations. Use when users request dashboards, metrics displays, KPI visualizations, data charts, or monitoring interfaces.
Create HTML flowcharts and process diagrams with decision trees, color-coded stages, arrows, and swimlanes. Use when users request flowcharts, process diagrams, workflow visualizations, or decision trees.
Create HTML technical documentation with code blocks, API workflows, system architecture diagrams, and syntax highlighting. Use when users request technical documentation, API docs, API references, code examples, or developer documentation.
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
1:1 rebuild of award-winning creative websites (WebGL / scroll-animation / portfolio sites). Evidence-driven pipeline - mirror-first forensics, line-number-traceable reverse engineering of minified bundles, verbatim porting, quantitative verification gates. Use when user asks to "复刻网站", "重建网站", "1:1 rebuild", "clone this site", or provides a URL of a creative/award site to reproduce.
Build the project, run tests, lint, format, spell check, generate mocks, or verify the build passes for Bitwarden iOS. Use when asked to "build", "run tests", "lint", "format", "verify build", "check if it compiles", "run swiftlint", "run swiftformat", "generate mocks", or to execute any part of the build/test/verify pipeline.
Performs comprehensive code reviews for Bitwarden iOS projects, verifying architecture compliance, style guidelines, compilation safety, test coverage, and security requirements. Use when reviewing pull requests, checking commits, analyzing code changes, verifying Bitwarden coding standards, evaluating unidirectional data flow pattern, checking services container dependency injection usage, reviewing security implementations, or assessing test coverage. Automatically invoked by CI pipeline or manually for interactive code reviews.
Convert an XCTest file to Swift Testing framework. Use when asked to "convert to Swift Testing", "migrate XCTest", "convert test file", "xctest to swift testing", "migrate tests to Swift Testing", or when explicitly asked to convert existing XCTest-based tests.
Convert a hand-written bespoke mock to a Sourcery AutoMockable-generated mock. Use this skill whenever the user says "convert this mock", "migrate mock to AutoMockable", "replace bespoke mock", "use Sourcery for this mock", or mentions wanting to convert a Mock*.swift file to use `// sourcery: AutoMockable`. Also use this skill proactively when you notice a new protocol being created without the annotation, or when an existing bespoke mock is being modified and AutoMockable would be sufficient.
> Diagnose and fix flaky (intermittently failing) tests in Bitwarden iOS. Finds the root cause of non-deterministic test failures (race conditions, timing issues, shared state, order dependence), applies a targeted fix, then stress-tests the fix by running the test 100 times to confirm stability. Use this skill whenever a test is failing intermittently, sometimes passes / sometimes fails, or someone describes a test as flaky, unstable, or non-deterministic — even if the exact "intermittent failure", "test is non-deterministic", "test fails sometimes", "test randomly fails".
Plan implementation, design an approach, or create an architecture plan for a Bitwarden iOS feature. Use when asked to "plan implementation", "design approach", "architecture plan", "how should I implement", "what files do I need", or to create a design doc before writing code.
Refine requirements, analyze a ticket, perform gap analysis, or clarify what a Jira/Confluence ticket is asking before coding in Bitwarden iOS. Use when asked to "refine requirements", "analyze ticket", "gap analysis", "clarify ticket", "what does this ticket mean", or to understand scope before implementation begins.
Claude Skills — questions
Answers built from the skills we actually parsed.