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. 86 961 files from 2 125 authors, of which 68 678 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.
Analyze website SEO - keywords, content, competitors, and improvement opportunities
> Pull real SEO metrics for any domain using Apify scrapers for Semrush and Ahrefs data. Gets domain authority, organic traffic estimates, keyword rankings, backlink profiles, top performing pages, and auto-discovers competitors from keyword overlap. No Semrush/Ahrefs subscription needed — uses Apify actors that scrape public pages.
> Analyze a website's SEO visibility, keyword rankings, traffic estimates, and competitive positioning. Uses web search probes, SimilarWeb (free tier via web), Useful for competitive intel, gap analysis, and reverse-engineering a company's organic acquisition strategy.
> AI sales coach composite. Analyzes all available sales data — email campaigns, call recordings/transcripts, reply patterns, pipeline outcomes — to identify what the user does well, where they struggle, and how to improve. Finds patterns in top-performing emails, winning call techniques, successful objection handles, and deal progression. Produces personalized coaching recommendations based on their specific product, market, and selling style. Tool-agnostic.
> Crawl a website's sitemap and blog index to build a complete content inventory. Lists every page with URL, title, publish date, content type, and topic cluster. Groups content by category and topic. Optionally deep-reads top N pages for quality analysis and funnel stage tagging. Use before SEO audits, content gap analysis, or brand voice extraction.
> Identify programmatic SEO page patterns worth building for your product — vs/ pages, integrations/, for-{industry}/, alternatives-to/, use-cases/ — and design the template structure, data model, and priority order. Outputs a complete pSEO blueprint with URL patterns, title templates, content frameworks, and data sources per variable.
> Reverse-engineer how competitors do programmatic SEO. Detects URL pattern clusters (vs/, integrations/, for-{industry}/), estimates page count per pattern, analyzes template quality, infers which patterns actually drive traffic, and identifies gaps you can exploit. Outputs a competitive pSEO landscape report.
> Comprehensive SEO footprint analysis. Catalogs all content, pulls real SEO metrics (via Apify Semrush/Ahrefs scrapers or free web search probes), runs competitor analysis, builds topic/keyword and content-type gap matrices, and produces a prioritized recommendations report. The complete SEO audit for any company.
> Find quick-win SEO content opportunities by comparing your site's existing content against competitor keyword rankings. Chains site-content-catalog and seo-domain-analyzer to build a content inventory, then identifies gaps — topics competitors rank for that you don't cover yet. Outputs a prioritized list of posts to write or update. Use when a seed/Series A team wants to start winning organic traffic without guessing.
> Map complete topic clusters for any subject area — hub pages, spoke articles, supporting content, internal linking architecture. Identifies content gaps, priority order, and builds a structured content calendar. Produces topic maps that build genuine topical authority, not random blog posts.
> build keyword architecture, generate content calendar, draft content.
Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.
Design and build complete web experiences from scratch — award-level product and marketing pages, cinematic scroll-directed sites where the page is directed like a film, and multi-screen products (app, dashboard, admin, settings, onboarding, docs site) built as one design system with every component, state and route in one style. Use whenever the user wants to create or redesign a landing page, website, hero section, portfolio, promo or product page; wants scroll animations, storytelling pages, or a site that feels like a movie; or says "make it beautiful", "make it wow", "cinematic", or "design system" — even if they name no technique. Generates its own assets via local CLIs (images, video frames, depth maps, 3D), and gates every ship with an executable anti-slop linter and a screenshot verification loop. Not for polishing a UI someone else built, and not for backend-only work.
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript.
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
Iteratively inspect an agent repository and optional user-provided traces, interview the user, and create, run, and audit Harbor evals one at a time. Use for agent evals, Harbor tasks, benchmark cases, verifier design, or controlled agent environments.
Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid composition), agent patterns, install, environment setup, and which skill to load next.
Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.
Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and langgraph.json configuration.
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally.
Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent locally.
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a time. Use specifically for creating online evaluators for use within LangSmith -- use "eval-engineering" for Harbor-style online evaluations.
INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith with the mda CLI. Covers the code-first, file-based project layout; define_deep_agent / defineDeepAgent; authored tools and middleware; MCP connectors; cron schedules; skills; sandboxes; mda init/dev/deploy; Context Hub; and human-in-the-loop interrupts in Python and TypeScript.
>- subagents, aggregate results. One row = one unit of work.
把中文短剧剧本和视觉设定写成有戏剧职责、连续性边界与冻结关键帧提示词的分镜 Markdown。用户提出“拆分镜/设计镜头/做镜头表”“场次视觉计划/调度故事板”“比较导演方案”“写首帧/关键帧提示词”或检查轴线、站位、视线、持物连续性时使用；不生成媒体。
为短剧人物、造型、地点、道具和状态编写或修改可直接复制的图片提示词 Markdown。用户提到角色设定图、三视图、参考图、场景板、道具图、风格帧、Look Development、状态变体或局部编辑提示词时使用；不生成图片，也不调用供应商。
维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链，并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubric 或 synthetic fixture 候选时使用；不用于普通创作、公开运行时取数、媒体生成或粗略数据分析。
在创作者明确确认后，执行短剧项目的图片、视频、TTS/配音或时间线音乐生产任务，并把结果与精简运行记录落回项目。用户说“生成这张图/这段视频/这句配音/这段配乐”“开始跑图/跑视频/合成语音/生成音乐”“把已确认提示词送去生产”，或要求批量执行已确认媒体任务时使用；不负责创作提示词、镜头、台词、歌词或声音身份，也绝不把预览、继续、预算说明或既有接受状态当作本次付费生产确认。
审查短剧项目中的原著分析、故事、剧本、视觉设定、图片提示词、分镜、冻结关键帧、视频提示词和已有媒体。用户提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词”“检查原著分析”“审查模板感”“根据生产观察做项目校准”时使用；只写审查问题、结论和修订要求，不代替 owner 修改来源文件。
从短剧剧本拆出人物/造型、地点/视图、道具/状态和跨场连续性，写成创作者可读的视觉设定。用户说“拆角色/场景/道具”“做资产设定”“判断复用还是新变体”“更新造型/道具状态”，或拿现成剧本直接做视觉资产准备时使用；不写图片提示词，不生成媒体。
把短剧分镜和冻结关键帧写成可直接复制的视频提示词 Markdown，也可按用户要求写时间线配乐/主题曲意图。用户提到文生/图生视频动作、人物表演、运镜、口型、环境运动、镜头时长、起止状态、把分镜转成视频提示词或写配乐提示词时使用；不生成媒体、不创作歌词、不改分镜边界。
编写或修订可拍摄的中文短剧、漫剧单集 Markdown 剧本，也负责保留作者原文地规范化现成剧本。用户提出“写/改一集短剧”“把大纲写成剧本”“优化场景/对白”“去模板感”“去 AI 味润色”“续写下一集”或提供剧本要求进入后续制作时使用；不负责资产、分镜、媒体提示词或终审。
基于文件系统初始化和继续短剧或漫剧项目，提供 creator-first 五文档路由、本地 Dashboard、制作形态与 Look Development 决策。用户提出“创建/继续短剧项目”“看进度/下一步”“做 Look Development”“打开 dashboard/短剧创作台”“导出制作资料”，或任务跨多个创作阶段时使用；明确的写作、资产、提示词、分镜或审查请求由对应子 skill 直接处理。
> (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new developers. Mode is auto-detected based on project markers in CWD.
> (1) Take a diagnostic assessment of their knowledge, (2) Study or review specific sections/topics, (3) Drill weak areas identified in previous sessions, (4) Check their learning progress or dashboard, or says things like "quiz me", "test me", "let's study", "/tutor", "학습", "퀴즈", "평가".
Mounts Git remotes with ArtifactFS as local working trees without a full clone. Use when asked to mount a remote repo, explain committed state versus dirty overlay state, or mount multiple repos under one daemon.
Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM proxies. Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field of generateText/streamText. MUST run two-step preflight before code — see body. Keywords: backend, 云函数, 云托管, serverless, LLM proxy, agent orchestration, generateText, streamText, generateImage, createModel, hunyuan-image, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web) or Mini Program (use ai-model-wechat).
Use this skill when a browser/Web app (React, Vue, Angular, Next, Nuxt, static sites, SPAs, dashboards, AI chat UI) needs AI models via @cloudbase/js-sdk. Default routing for page/页面/Web/前端/frontend/网页/H5 AI — call directly from browser, do NOT propose a Node.js proxy. Covers generateText and streamText. Models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the model field. MUST run two-step preflight before code — see body. Keywords: 页面, Web, 前端, React, Vue, Next, Nuxt, SPA, AI chat UI, generateText, streamText, createModel, hunyuan-exp, Token Credits, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for Node.js backend (use ai-model-nodejs), Mini Program (use ai-model-wechat), or image generation (Node SDK only).
Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2, hunyuan-2.0-instruct-20251111, glm-5, kimi-k2.6) go in the data wrapper model field. API differs from JS/Node SDK — streamText needs data wrapper, generateText returns raw response. MUST run two-step preflight before code — see body. Keywords: Mini Program AI, wx.cloud.extend.AI, 小程序成长计划, ai_miniprogram_inspire_plan, Token Credits 资源包, generateText, streamText, createModel, hunyuan-exp, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, MiniMax. NOT for browser/Web (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (use ai-model-nodejs).
CloudBase Node SDK auth guide for server-side identity, user lookup, and custom login tickets. This skill should be used when Node.js code must read caller identity, inspect end users, or bridge an existing user system into CloudBase; not when configuring providers or building client login UI.
CloudBase auth provider configuration and login-readiness guide. This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readiness before implementing a client or backend auth flow.
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
CloudBase WeChat Mini Program native authentication guide. This skill should be used when users need mini program identity handling, OPENID/UNIONID access, or `wx.cloud` auth behavior in projects where login is native and automatic.
CloudBase function runtime guide for building, deploying, and debugging your own Event Functions or HTTP Functions. This skill should be used when users need application runtime code on CloudBase, not when they are merely calling CloudBase official platform APIs.
Complete guide for CloudBase cloud storage using Web SDK (@cloudbase/js-sdk) - upload, download, temporary URLs, file management, and best practices.
Build and deploy AI agents with CloudBase Agent SDK (TypeScript & Python). Implements the AG-UI protocol for streaming agent-UI communication. Use when deploying agent servers, using LangGraph/LangChain/CrewAI adapters, building custom adapters, understanding AG-UI protocol events, or building web/mini-program UI clients. Supports both TypeScript (@cloudbase/agent-server) and Python (cloudbase-agent-server via FastAPI).
CloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. This skill should be used when users need to deploy cloud functions, manage CloudRun apps, upload files to storage, query NoSQL/MySQL databases, deploy static hosting, set access permissions, or configure CORS/domains/routing via tcb commands. Also use for CI/CD pipeline scripting, batch operations, terminal-based CloudBase management, or when the user prefers CLI over SDK/MCP.
Code review and validation for CloudBase projects. After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill to check for known pitfalls — auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse. Supports automated lint scripts (regex-based) + LLM semantic review.
Use CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.
Claude Skills — questions
Answers built from the skills we actually parsed.