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. 79 870 files from 1 769 authors, of which 62 217 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.
Research products across the web with Firecrawl and produce a shopping recommendation or cart-ready summary. Use when the user wants to compare products, find the best option, evaluate reviews, respect budget/preferences, or shop with a saved browser session.
Extract market, financial, earnings, industry, and company metrics with Firecrawl. Use when the user asks for market research, industry trends, public company data, financial comparisons, earnings research, or structured market reports.
QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.
Audit a website's SEO with Firecrawl. Use when the user asks for an SEO audit, metadata and heading review, sitemap/site-structure analysis, keyword opportunities, competitor SERP comparison, or prioritized search optimization recommendations.
Run outcome-focused Firecrawl workflows that produce deliverables such as research reports, SEO audits, QA reports, lead lists, knowledge bases, website design systems, and other structured web-data artifacts. Use when the user wants Firecrawl to complete a business, marketing, product, or creative workflow rather than merely scrape a page or integrate API calls into code.
Evidence-grounded AI research workflow for turning supplied economics, finance, management, and social-science papers or structured records into versioned PaperReading artifacts. Use when Codex must ingest text or Markdown, separate source-grounded claims from researcher analysis, bind findings to evidence IDs and locators, migrate v0.2 PaperRecord JSON, validate or verify a v0.3 PaperPackage, generate research extensions, export reviewable JSON or Markdown, or safely update a compatible 13-field literature workbook.
带 AI 精读大型开源仓库，产出每句话都能回溯到源码具体行的书稿、课程或技术文档。核心是零幻觉：每一处引用逐字节核实、行号实读、静默删行由脚本抓出。覆盖锁版本锚点、写逐章大纲、八段结构写章节、编成带封面封底的 HTML 书、机器校验、并行子 Agent 生产六件事。当用户要读懂一个陌生的大型仓库、精读某个开源项目源码、把源码整理成一本书、整理成课程或系列文章、做源码解读、写架构分析、或者要派多个 Agent 并行写技术内容时使用。触发词：精读源码、读源码、源码解读、源码分析、拆解这个项目、这个仓库怎么读、把源码写成课、把源码写成书、写源码精读、架构分析、code walkthrough、带我读代码。
Academic paper AI content detection, rewriting, and thesis writing assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions, and generates full thesis drafts. Supports .docx files, outputs reports and rewritten/formatted documents. Bilingual: Chinese & English.
Formats unstructured meeting notes into a structured project report. Use this when the user provides raw notes or requests a summary of a meeting.
Inspect a workspace, identify temporary files, and perform only approved cleanup or organization steps.
Guide for working with Next.js App Router (Next.js 13+). Use when migrating from Pages Router to App Router, creating layouts, implementing routing, handling metadata, or building Next.js 13+ applications. Activates for App Router migration, layout creation, routing patterns, or Next.js 13+ development tasks.
Guide for advanced Next.js App Router patterns including Route Handlers, Parallel Routes, Intercepting Routes, Server Actions, error boundaries, draft mode, and streaming with Suspense. CRITICAL for server actions (action.ts, actions.ts files, 'use server' directive), setting cookies from client components, and form handling. Use when requirements involve server actions, form submissions, cookies, mutations, API routes, `route.ts`, parallel routes, intercepting routes, or streaming. Essential for separating server actions from client components.
Guide for choosing between Server Components and Client Components in Next.js App Router. CRITICAL for useSearchParams (requires Suspense + 'use client'), navigation (Link, redirect, useRouter), cookies/headers access, and 'use client' directive. Activates when prompt mentions useSearchParams, Suspense, navigation, routing, Link component, redirect, pathname, searchParams, cookies, headers, async components, or 'use client'. Essential for avoiding mixing server/client APIs.
Identify and fix common Next.js App Router anti-patterns and mistakes. Use when reviewing code for Next.js best practices, debugging performance issues, migrating from Pages Router patterns, or preventing common pitfalls. Activates for code review, performance optimization, or detecting inappropriate useEffect/useState usage. CRITICAL: For browser detection, keep the logic in the user-facing component (or a composed helper that it renders) rather than isolating it in unused files.
Focused pattern for fetching data using URL parameters in Next.js. Covers creating dynamic routes ([id], [slug]) and accessing route parameters in server components to fetch data from APIs. Use when building pages that display individual items (product pages, blog posts, user profiles) based on a URL parameter. Complements nextjs-dynamic-routes-params with a simplified, common-case pattern.
Pattern for client components calling server actions to set cookies in Next.js. Covers the two-file pattern of a client component with user interaction (onClick, form submission) that calls a server action to modify cookies. Use when building features like authentication, preferences, or session management where client-side triggers need to set/modify server-side cookies.
Guide for implementing navigation in Next.js Server Components using Link component and redirect() function. Covers the difference between server and client navigation methods. Use when adding links, redirects, or navigation logic in server components without converting them to client components unnecessarily.
Guide for Next.js App Router dynamic routes and pathname parameters. Use when building pages that depend on URL segments (IDs, slugs, nested paths), accessing the `params` prop, or fetching resources by identifier. Helps avoid over-nesting by defaulting to the simplest route structure (e.g., `app/[id]` instead of `app/products/[id]` unless the URL calls for it).
Pattern for using useSearchParams hook with Suspense boundary in Next.js. Covers the required combination of 'use client' directive and Suspense wrapper when accessing URL query parameters in client components. Use when building search interfaces, filters, pagination, or any feature that needs to read/manipulate URL query parameters client-side.
Guide for Vercel AI SDK v5 implementation patterns including generateText, streamText, useChat hook, tool calling, embeddings, and MCP integration. Use when implementing AI chat interfaces, streaming responses, tool/function calling, text embeddings, or working with convertToModelMessages and toUIMessageStreamResponse. Activates for AI SDK integration, useChat hook usage, message streaming, or tool calling tasks.
Use when auditing iOS/Android app submissions for compliance with Apple App Store Review Guidelines or Google Play Developer Policies. Scan .ipa, .apk, or .zip files against official store policies, generate structured compliance reports, and identify violations with remediation steps.
Prepares a jmxfetch release by bumping the version in pom.xml, README.md, and test.yml, and populating the CHANGELOG.md entry. Pass the new version as the argument (e.g. /prepare-release 0.52.0).
Add integration tests to TestGCMetrics.java for new GC collector support added to new-gc-default-jmx-metrics.yaml. Use when a PR adds a new garbage collector to the metrics YAML without a corresponding test.
Starts a new jmxfetch development cycle by bumping to the next SNAPSHOT version in pom.xml, README.md, and test.yml, and adding a new CHANGELOG.md placeholder. Pass the next snapshot version as the argument (e.g. /start-dev-cycle 0.52.1-SNAPSHOT).
Turn a real coding or technical setup task into just-in-time, project-grounded learning while still completing the work. Use when a user asks to learn while building, be guided through a project, understand what concepts a completed task used, see how knowledge appears in files, commands, tests, or design decisions, receive a learning receipt, or verify what they can now do. Do not use for ordinary delegated coding without learning intent, isolated factual explanations, or course creation.
Open Analytics' design language, extracted from the shipped product: an ink-derived neutral system, squircle surface anatomy, one small spring vocabulary, pixel-matched skeletons, and a plain-spoken copy voice, with type-checked component recipes. Use this whenever you build or restyle a dashboard, SaaS app, analytics UI, settings screen, onboarding flow, or marketing/landing page that should feel calm, dense and native, and whenever the user mentions Open Analytics' look, 'clean SaaS design', cards, dropdowns, tab bars, empty states, skeletons, or UI animation quality, even if they never say the words 'design system'.
Core Plain Language standard (ISO 24495-1:2023). Governs all user-facing responses to ensure clear, structured, findable, understandable, and actionable output.
Audit user-selected Markdown or text files for deterministic plain-language findings. Use only when the user explicitly invokes this skill.
Sector-specific Plain Language standard for science and technical writing (ISO 24495-3:2026). Applied during software documentation, architecture specs, and technical analysis.
Plain language applied to source code (ISO 24495-1:2023 principles). Governs the parts of code a person reads: the order units appear in, their names, comments, and error messages. Applied when writing or restructuring code, not when explaining it.
Hold every response to the ISO 24495 plain-language rules, and route to the sector skills. Codex has no output style, so these rules are a skill.
Sector-specific Plain Language standard for legal communication (ISO 24495-2:2025). Applied during contract drafting, license review, and legal/compliance writing.
Provisional task skill for organisational plain language implementation (based on ISO/CD 24495-4, committee draft). Activates for plain language gap analysis, policy drafting, review workflow design, and organisational readiness for the future published standard. Does not activate for ordinary writing, rewriting, or reviewing of individual documents.
Provisional sector-specific Plain Language standard for document design (based on ISO/WD 24495-5, under development). Applied when structuring complex documents so readers can find and navigate content through layout, visual hierarchy, and navigation aids.
Use the Appllama MCP (mcp.appllama.io) well — research real top-grossing mobile apps, their screens, flows, and UI elements, then build from what you learn. Load when the Appllama MCP is connected and the task involves building a mobile app or screen, researching app design patterns, studying onboarding/paywall/feature flows, improving an existing screen, or whenever an appllama_* / search_apps / list_app_screens tool is available. Covers the tool map, pagination, expiring media, and the full build-from-research playbooks.
Build native-feeling, benchmark-quality mobile app screens (Expo / React Native). Use when designing or implementing any mobile UI — screens, flows, onboarding, paywalls, tab bars, sheets, settings, empty states — or when polishing motion, gestures, navigation, typography, dark mode, or perceived performance. Enforces Apple HIG fidelity, semantic colors, native controls, anti-slop discipline, navigation semantics (push vs replace, modal vs sheet vs overlay, the one-way doors where back must not exist), a strict motion bar (frequency gate, exact springs/curves/durations, UI-thread discipline, haptics), a full-motion simulator-verified iteration loop, and a study-real-apps-first workflow (pairs with the Appllama MCP). Trigger on "build a screen", "make this screen better", "design the onboarding", "wire up this flow", "add a bottom sheet", "polish the UI", "make it feel native", "review the animations", or any mobile design/implementation task.
Audit or apply evidence-backed, test-first subtractive cleanup for accumulated agent-created test bloat, verification theater, and defensive or fallback bloat while preserving independent external behavior. Invoke explicitly for semantic simplification, not generic refactoring.
Check whether a Playwright, Puppeteer, Selenium or CDP-driven browser presents a coherent fingerprint, using liarjs as a library against a Page you already have - navigator.webdriver, HeadlessChrome tokens, worker versus main-thread identity, patched-API integrity, WebGL versus WebGPU GPU identity. Use when asked whether an automated browser looks like a normal one, when a headless setup or a stealth plugin's effect needs measuring rather than assuming, or when an assertion on fingerprint quality belongs in a test suite.
Gate a build on browser fingerprint regressions with liarjs - save a baseline scan as JSON, diff later runs against it, and fail the job when the consistency score falls below a floor. Use when asked to add a fingerprint or headless-detection check to GitHub Actions, GitLab CI or another pipeline, to catch a regression in a Chromium build or scraping harness before it ships, or to track how a fingerprint score changes across commits.
Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. Use when asked to run a browser fingerprint test, see what a fingerprint looks like, check canvas or WebGL fingerprint stability, compare a spoofed profile against a real browser, or find out whether a browser profile is self-consistent.
Read a liarjs fingerprint report and attribute each failing check to the component that produced it - what the check id measures, whether the signal comes from the launch configuration, the page-modifying layer, the network path or the machine image, and which failures are inherent to headless or datacenter environments. Use when a fingerprint scan came back with a low score, or when a check id such as webdriver, worker-consistency, gpu-triad, native-integrity or tz needs explaining.
照片拍摄地点定位（看图找地点 / 网络迷踪 / 图寻 / 推拍摄时间）。给一张或几张照片，先一条命令做完元数据、OCR、以图搜图（intake.py），把线索和候选记到候选盘（board.py）上由脚本排名、给下一步；查表线索用 clues.py；卫星图和街景都是"机器先排序、人只看前几名"（sat_scan.py、match.py）；每个结论都用真实数据核对，输出坐标 + 误差半径、证据图和分档置信度。Geolocate or chronolocate a photo with tool-verified reasoning — EXIF, OCR, reverse image search (Baidu/Yandex), lookup tables (plates, area codes, calling codes, driving side, territories), candidate board with likelihood ranking, sun and shadow math, OSM Overpass, CLIP-ranked satellite scan, DINOv2+SIFT-ranked street view matching, DEM skyline rendering. Use when the user shares a photo and asks 这是哪 / 在哪拍的 / 帮我定位这张照片 / 网络迷踪 / 几点拍的 / where was this taken / geolocate this.
Turn B2B marketing work into evidence-aware outputs using market, positioning, demand, account-program, lifecycle, and tool-selection guidance. Use when the user needs a concrete plan, checklist, template, software shortlist, or next action; do not use for generic inspiration or legal advice.
> Build a data-backed client onboarding proposal for an agency starting a new engagement, combining an SE Ranking SEO + AI-search audit with a Planable analysis of the client's current social performance. Use this skill whenever an agency wants to show a new (or about-to-sign) client where they stand and what the plan is, or says things like "build an onboarding proposal for [client]", "we're starting with [client], put together the SEO + social analysis", "create a client proposal with audit and social baseline", "scope a SEO + AI + social engagement", or "show the client their opportunities and our plan". Assumes the client's social accounts are already connected in Planable. Always activate for new-engagement proposals that pair SE Ranking analysis with Planable social data.
> Generate one unified performance report that brings together SEO rankings, AI-search visibility (SE Ranking) and social engagement (Planable) — delivered as a short text summary in chat plus a self-contained interactive HTML report. Use this skill whenever the user wants a combined cross-channel report, or says things like "give me a full report across SEO and social", "how did we do this month across search and social", "combined SEO + AI + social report for [client]", "build a cross-channel dashboard", or "one report that covers rankings, AI visibility and social". Always activate when the request spans both search (SE Ranking) and social (Planable) in a single report.
Generate a demand-gen landing page for an SEO agency, complete with pain-point hook, proof, a free-audit lead magnet flow, and CTAs tuned for cold traffic. Pulls real competitive and AI-search data for the agency's target niche to make the copy specific and credible. Use when the user asks for an SEO agency landing page, lead-gen page for an SEO agency, demand-gen page, free-audit landing page, or wants to convert cold traffic into discovery calls.
> Build and track local search visibility with SE Ranking city-level rank tracking and turn it into local social content in Planable, including Google Business Profile posts. Use this skill whenever the user wants to grow a business's presence in a specific city or cities and pair it with local social, or says things like "track our rankings in [city]", "set up local rank tracking", "we want to show up in local search", "create Google Business Profile posts", "local SEO plus social for our locations", or "how are we ranking city by city and what should we post locally". Always activate for local/multi-location visibility work that combines SE Ranking rankings with Planable local/GMB content.
Paid-search competitive landscape for a domain or keyword. Pulls SE Ranking's PPC data — domain ad keyword footprint, ad copy patterns, who else bids on the same keywords, SERP shopping/ad-pack visibility — and produces a competitive ads brief plus a recommended bid-keyword shortlist. Use when the user asks "paid search analysis", "competitor ads", "PPC competitive", "ad copy intelligence", "shopping pack", "who bids on this keyword", or "paid keyword footprint".
Measure AI Search share of voice for a target domain versus competitors across ChatGPT, Perplexity, Gemini, Google AI Overview, and AI Mode. Pulls the AIO leaderboard, then samples prompts where each domain appears as a source or brand mention, and analyses topic clusters each brand owns. Use when the user asks for AI Search share of voice, LLM visibility tracking, AEO/GEO analysis, AI Overview competitive analysis, or wants to know which brands LLMs cite in their category.
SE Ranking API integration architect. Covers the whole SE Ranking surface — the Data API (keyword research, backlinks, domain & competitor analysis, SERP, website audit, AI Search) and the Project API (rank tracking, project/keyword/backlink management, marketing plan, sub-accounts, AIRT prompts). Answers any "how do I…" question about endpoints, parameters, JSON schemas, credit cost, rate limits, or auth, and produces ready-to-paste cURL / Python / TypeScript / MCP-tool-call recipes. With explicit confirmation it also wires up Project API state — creating projects, adding keywords, configuring audits, setting up AIRT prompt groups. Pulls live tool schemas from the connected MCP. Unlike the analysis skills (briefs, audits, reports), seo-api produces integration recipes and wired-up state. Use when the user asks how to use the SE Ranking API, which endpoint returns a metric, how to build a rank tracker, for Postman / cURL / Python recipes, or how to integrate with Looker / n8n / Make.
> Find the AI-search prompts and topics where a brand is invisible (or losing to competitors) in SE Ranking, then turn those gaps into a social campaign in Planable and set up before/after tracking. Use this skill whenever the user wants to improve how their brand shows up in AI answers (ChatGPT, Perplexity, Gemini, Google AI Overview, AI Mode) through content, or says things like "what should we post to get cited by AI", "where are competitors winning in AI answers and we're not", "create content for the prompts we're missing", "improve our AI visibility with social", "AEO/GEO content plan", or "turn our AI search gaps into posts". Always activate when AI-search visibility is the goal and Planable is where the content will be made.
Generate a writer-ready SEO content brief from a target domain and topic. Pulls domain overview, competitors, keyword gaps, SERP analysis, related and question keywords, AI Search citations, and existing internal-link sources, then synthesises a complete editorial brief a freelance writer can start from immediately. Use when the user asks for a content brief, blog brief, article outline, editor brief, or wants to capture organic traffic their competitors have.
Full backlink profile for a domain — referring domains, anchor text distribution, authority distribution, IP and subnet diversity, growth/decay trend, toxic-candidate flagging. Distinct from `seo-backlink-gap` (which is gap-vs-competitor only). Produces a profile health score and reviewable disavow candidate list (never auto-disavow). Use when the user asks "backlink profile", "link profile audit", "anchor distribution", "toxic links", "disavow candidates", or "backlink health".
Find referring domains that link to multiple competitors but not to your site, then enrich with authority, anchor samples, and outreach angle per row. Produces a prospect list an outreach team can start emailing tomorrow. Use when the user asks for backlink gap analysis, link building opportunities, competitor backlink intersection, link prospecting, or wants referring domains they are missing.
Capture an SEO baseline snapshot for a domain or URL, then on later runs compare the current state and surface regressions. Tracks authority, traffic, keywords, backlinks, and on-page content. Three subcommands — `baseline`, `compare`, `history`. Use when the user asks for "SEO drift", "baseline this site", "did anything break", "SEO regression check", "compare before and after", "deployment check", or "monthly SEO snapshot".
Ad-hoc web scraping, site mapping, and full-site crawling via Firecrawl MCP. Returns raw HTML, parsed metadata (og:*, twitter:*, JSON-LD, canonical, robots), JS-rendered DOM, and screenshots that WebFetch cannot. Distinct from the SE Ranking skills (which give keyword/traffic/SERP data) and from WebFetch (which gives markdown prose only). Use when the user says "scrape this page", "crawl this site", "map this site", "find all pages on", "get the OG tags", "get the JSON-LD", "render this JS-heavy page", or any task where raw HTML head metadata, structured-data scripts, or post-JS DOM are the actual deliverable. Also invoked as a sub-step from other skills that need raw HTML.
E-E-A-T + CITE quality audit for an EXISTING piece of content. Scores Experience, Expertise, Authoritativeness, Trustworthiness, and citation-readiness for AI search; surfaces veto items that block publication; produces a publish / publish-with-fixes / no-publish verdict. Distinct from `seo-content-brief` (produces a NEW article from a topic) and from `seo-page` (URL-level keyword/traffic intelligence). Use when the user asks "content quality audit", "E-E-A-T check", "is this content good", "review this article", "content audit", "citation readiness", or "AI search readiness".
Compare a target domain to its top organic competitors and surface keywords the competitors rank for that the target does not, filtered by intent, volume, and difficulty. Use when the user asks for a competitor gap analysis, keyword gap, organic content gap, missing keyword opportunities, or wants to see what their competitors are ranking for that they are not.
Generate SEO-optimized "X vs Y" comparison and "alternatives to X" landing pages targeting comparative-intent keywords. Pulls competitor data, comparative-intent SERPs, and existing comparison pages to produce a balanced, structured page draft with feature matrix, schema, and conversion blocks. Distinct from `seo-agency-landing-page` (top-of-funnel demand-gen). Use when the user asks for "comparison page", "vs page", "alternatives page", "X vs Y", "alternative to X", or "competitor comparison page".
Claude Skills — questions
Answers built from the skills we actually parsed.