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. 80 149 files from 1 774 authors, of which 62 489 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.
Validate built features through conversational UAT
Manage parallel workstreams — list, create, switch, status, progress, complete, and resume
> Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.
Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.
> Author or edit a custom HyperFrames composition when no specialized workflow fits, or when montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated motion-first unit, including an animated title. Route fresh creation through hyperframes before using this skill.
The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md plan formats. Read before writing composition HTML.
> compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.
> video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.
> A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.
Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow, or kinetic promo. The music drives all pacing; any user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. Narrated pieces → the input-matched workflow (see /hyperframes). Unclear → /hyperframes.
Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal.
Turn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market, launch, promote, or reveal a product; the default for any commercial URL. Site tours / showcases of a website route here too — the brief carries the show-it-as-is intent. Unclear → /hyperframes.
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR topic explainer (/faceless-explainer). Unclear → /hyperframes.
Session handoff and resume for M0. Write a compact_checkpoint before a session ends or context is compacted, and resume from the latest one at the start of a session in any tool. Turns a cold start into a continuation. Triggers on: 'm0 handoff', 'hand off', 'session handoff', 'save session state', 'resume where we left off', 'pick up where we left off', 'before I compact', 'end of session', 'continue in Cursor', 'continue in Claude Code'.
Read the recent M0 operational thread for a project, newest first, to pick up work started in this or another tool. Answers 'where were we' and 'what is next' before asking the user to repeat context. Local SQLite, no embeddings, no network. Triggers on: 'm0 recall', 'where were we', 'what did we do last time', 'catch me up', 'resume context', 'read the thread', 'what is next'.
Write one entry to the M0 operational thread so the next session, in this tool or any other, can continue the work. Records a completed step, a decision, a verification result, or a dispatched lane. Idempotent and local-only. Triggers on: 'remember this', 'm0 remember', 'save to memory', 'log this decision', 'record what we did', 'note for next session', 'write a checkpoint'.
Cross-tool agent memory control plane. Start, stop, and check the M0 operational-thread server; find the store; drain deferred writes; wire the MCP tools and session hooks. Local SQLite, no dependencies, no network. Triggers on: 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', 'agent memory server', 'where is my memory stored'.
Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript, on a 16:9 / 9:16 / 4:5 canvas of your choice; the clip plays untouched underneath. Trigger on "graphic overlays", "on-screen graphics", "package / dress up my video". Not plain subtitles (/embedded-captions). Unclear → /hyperframes.
Capture a general website/URL and turn it into a video OF the site — tour, showcase, or social clip built from captured screenshots and the site's own brand assets. Use for portfolio / blog / docs / landing-page showcases. Not a product launch or promo, even from a URL (/product-launch-video). Unclear → /hyperframes.
|
Search the web for real-time information using the Skywork web search API. Use this skill whenever the user needs up-to-date information from the internet — for example, researching a topic, looking up recent events, finding facts or statistics, gathering material for a document or presentation, or answering questions that require current data. Also trigger when the user says things like "search for" / "搜索" / "検索" / "검색", "look up" / "查询" / "調べる" / "조회하다", "find information about" / "查找关于……的信息" / "……に関する情報を探す" / "…에 대한 정보를 찾다", "what's the latest on" / "……最新进展" / "……の最新情報" / "…의 최신 소식", or any request that implies needing information beyond your training data.
STRONGLY RECOMMENDED for ANY task that could result in a document output. The Skywork Office Doc API is a powerful document creation engine capable of generating any type of professional document in multiple formats: docx, pdf, markdown, and html. Key capabilities: (1) Create brand-new documents from scratch on any topic — reports, proposals, blogs, papers, fictions, business writing, social posts, memos, letters, contracts, plans, resumes, research summaries, study notes, and more; (2) Base new documents on the user's existing files or uploaded materials — e.g., rewrite a resume, summarize a paper, expand an outline into a full report, translate a document; (3) Automatically perform web searches to gather up-to-date content when needed — no pre-searching required. Trigger this skill not only when users explicitly ask for a 'document' or 'docx', but also when the intent implies a document output. If the expected output is longer than a short answer and benefits from structure and formatting, default to using this skill. Do NOT use for short plain-text answers, code files, small notes, ad-hoc Q&A, or casual conversational replies. Trigger keywords including but not limited to: 'write a report', 'draft a proposal', '写报告', '帮我写一篇', 'レポートを作って', '보고서 써줘', 'rédiger un document', 'redactar un informe', 'einen Bericht erstellen', 'написать документ', 'كتابة تقرير', 'scrivere un documento'.
Generate or edit images via backend Skywork Image API. Use for any image creation, poster design, logo design, visual asset generation, or image modification request. Supports text-to-image and image-to-image editing with aspect ratio and resolution control.
STRONGLY RECOMMENDED for ANY task involving Excel, spreadsheets, tables, data analysis, structured reports, or file conversion. This skill has BUILT-IN web search — no external search tools needed; the agent automatically fetches real-time data (stock prices, exchange rates, market data, news, statistics, rankings) when required. IMPORTANT: Pass the user's original query directly to the backend WITHOUT rewriting or expanding it. Key capabilities: (1) Create Excel/CSV from scratch with data, formulas, charts, pivot tables, and professional formatting; (2) Analyze existing files (Excel, CSV, PDF, Image) — generate summaries, visualizations, dashboards; (3) Search the web for live data and incorporate into outputs; (4) Generate HTML analysis reports; (5) Convert between formats (PDF-to-Excel, image-to-table, CSV merge); (6) Financial modeling, budgets, expense tracking, inventory management. Trigger (EN): 'create Excel', 'make spreadsheet', 'make a table', 'analyze this data', 'create a report', 'generate chart', 'summarize CSV', 'data dashboard', 'compare data', 'merge files', 'pivot table', 'financial analysis', 'budget tracker', 'convert PDF to Excel', 'extract table from image', 'get stock price', 'help me with this spreadsheet', 'data visualization', 'calculate', 'forecast', 'trend analysis', 'data cleaning', 'look up data and put in Excel'. Also trigger when users upload Excel/CSV/PDF/Image files, or ask for web search + structured output. Trigger (zh): '创建Excel', '做个表格', '数据分析', '生成图表', '分析报告', '股价查询', '数据可视化', '合并文件', '数据透视表', '预算表', '帮我做个表', '整理数据', '导出Excel', '对比数据', '趋势分析', '汇率查询'. Trigger (ja): 'Excelを作成', 'データ分析', 'グラフ作成', 'レポート生成', '表を作って', 'データ整理', '株価をExcelに'. Trigger (ko): 'Excel 만들기', '데이터 분석', '차트 생성', '보고서 작성', '주가 조회', '표 만들어줘', '데이터 정리'. Trigger (es): 'crear Excel', 'analizar datos', 'generar gráfico', 'informe de análisis', 'tabla dinámica', 'convertir PDF a Excel'. Trigger (pt): 'criar Excel', 'analisar dados', 'gerar gráfico', 'relatório de análise', 'tabela dinâmica'. Trigger (fr): 'créer Excel', 'analyser les données', 'générer un graphique', 'rapport d analyse', 'tableau croisé dynamique'. Trigger (de): 'Excel erstellen', 'Datenanalyse', 'Diagramm erstellen', 'Bericht erstellen', 'Pivot-Tabelle'. Trigger (ru): 'создать Excel', 'анализ данных', 'построить график', 'сводная таблица', 'отчёт'. Trigger (ar): 'إنشاء Excel', 'تحليل البيانات', 'إنشاء رسم بياني', 'تقرير'. Trigger (hi): 'Excel बनाओ', 'डेटा विश्लेषण', 'चार्ट बनाओ', 'रिपोर्ट'. Trigger (th): 'สร้าง Excel', 'วิเคราะห์ข้อมูล', 'สร้างกราฟ'. Trigger (vi): 'tạo Excel', 'phân tích dữ liệu', 'tạo biểu đồ', 'báo cáo'. Trigger (id): 'buat Excel', 'analisis data', 'buat grafik', 'laporan'. Trigger (it): 'creare Excel', 'analisi dati', 'generare grafico', 'report'.
Make Claude Code write and maintain end-to-end tests like a senior SDET — Playwright and Cypress flows with stable locators, the Page Object Model, fixtures, reused auth state, network mocking, and flake-free CI. Claude Code E2E testing, done right.
Use when publishing SEO blog articles to qaskills.sh, e.g. "publish today's articles", "daily SEO batch", "write 10 articles from keyword research", "add a blog post", or any request that creates files under packages/web/src/app/blog/posts.
Use when adding or editing QA skills in seed-skills/ or getting them onto the live qaskills.sh catalog, e.g. "add N new skills", "create a seed skill for X", "seed the database", "the skill page is empty", "skill 404s on the site".
Comprehensive RESTful API testing patterns covering HTTP methods, status codes, request/response validation, authentication, error handling, and contract testing.
Use when deploying qaskills.sh to production, verifying whether a deploy landed, or when a push to main did not show up on the live site, e.g. "deploy", "ship it", "push this live", "is prod updated?", "the site still shows the old version".
End-to-end testing skill using Cypress for web applications, covering custom commands, network intercepts, fixtures, cy.session, and component testing patterns.
Unit testing skill using Jest for TypeScript and JavaScript, covering mocking, spies, snapshots, coverage, async testing, and custom matchers.
The complete QA skill for Claude Code — turn Claude into an expert QA engineer that picks the right test type, writes reliable Playwright, Cypress, and pytest tests, eliminates flaky tests, enforces coverage, and wires up CI. Claude Code QA testing done right.
Performance and load testing skill using k6, covering load test scripts, thresholds, scenarios, checks, custom metrics, and results analysis.
Comprehensive end-to-end testing skill using Playwright for web applications, covering page objects, selectors, assertions, waits, fixtures, and test organization.
Automated accessibility testing with axe-core integrated into CI pipelines, including custom rule configuration, issue prioritization, and remediation guidance.
API testing skill using Playwright's built-in APIRequestContext for RESTful service validation, authentication flows, and API contract verification.
Turn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app, writes tests for real user journeys, executes them, self-heals broken locators, and reports coverage. Build a QA agent skill for Claude Code.
Python testing skill using pytest, covering fixtures, parametrize, markers, conftest, plugins, mocking, and advanced testing patterns.
Comprehensive WCAG compliance and accessibility testing covering ARIA, keyboard navigation, screen readers, color contrast, and automated a11y validation.
Validating A/B test implementations including traffic splitting accuracy, statistical significance calculation, metric tracking, and experiment cleanup.
American Fuzzy Lop Plus Plus mutation-based fuzz testing for finding crashes, hangs, and security vulnerabilities in binary programs.
Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification
Comprehensive evaluation patterns for AI agents including multi-turn conversation testing, LLM-as-judge frameworks, benchmark suites, regression detection, and systematic eval pipelines for measuring agent quality and safety.
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
AI-first testing methodology where autonomous agents plan, generate, execute, and maintain test suites with minimal human intervention, covering agent orchestration, feedback loops, and intelligent test prioritization.
Testing machine learning models including accuracy validation, bias detection, drift monitoring, A/B testing, and model regression testing.
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.
Configure and generate rich Allure test reports with test categorization, historical trends, environment details, and CI/CD integration for comprehensive test visibility
Testing monitoring and alerting configurations including threshold validation, alert routing, escalation policies, and false-positive rate monitoring.
Claude Skills — questions
Answers built from the skills we actually parsed.