抓取
网页抓取与数据提取
requirements
ddaanet
Capture and document requirements for implementation. Triggers on "capture requirements", "document requirements", "what do I want to build", or feature discussions without clear documentation. Produces requirements.md artifact for design and planning phases.
pix-storybook
CoRLab-Tech
Autonomous pixel-perfect Stencil component implementation using Figma MCP, Storybook, and Playwright MCP for visual testing and fixing.
jq
zhongjis
Extract specific fields from JSON files efficiently using jq instead of reading entire files, saving 80-95% context.
browser-automation-parity
terryjyu
Enforce parity between interactive Browser Subagent sessions and headless Python+Playwright automation in Google Antigravity. Use this skill whenever browser automation fails silently in run mode, a click/navigation/paste works under subagent guidance but breaks in replay, you need CI-grade reproducibility with rich diagnostics, or you're building any Playwright automation that must be observable and self-checking. Also trigger when the user mentions "trace", "flaky test", "missed click", "run mode fails", "subagent works but script doesn't", or wants to debug browser automation discrepancies.
e2e-qa-tester
AgustinAlbonico
"Ejecuta pruebas E2E y QA manual usando Playwright MCP para verificar la ultima tarea completada en la conversacion. Usar cuando se necesite: (1) Probar un flujo recien implementado, (2) Verificar que una funcionalidad funciona correctamente, (3) Hacer QA manual de una nueva feature, (4) Testear formularios, flujos de autenticacion, o cualquier interaccion de usuario. El skill busca credenciales en CREDENTIALS.md, intenta conectar al puerto 5173 por defecto, y pide confirmacion antes de ejecutar las pruebas."
website-cloning
ocholasupernet-debug
Clone any website as a deployable React + Vite web app with real scraped content (images, text, structure, colors, fonts). Use when the user asks to clone, replicate, copy, or rebuild an existing website.
map-docs
davidosemwegie
This skill should be used when the user asks to "map documentation links", "extract docs navigation", "get documentation structure", "scrape docs sidebar", or wants to understand the structure of a documentation website before creating skills.
audit-site
Crawlio-app
Use this skill when the user asks to "audit a site", "analyze a website", "review a site", "site health check", or wants a comprehensive analysis including technology stack, issues, and recommendations. Orchestrates a full crawl, enrichment capture, observation analysis, and findings report.
playwright
devinschumacher
Canonical Playwright hub for E2E tests and ad-hoc browser automation. Use when the user explicitly mentions "Playwright", "@playwright/test", "npx playwright", "playwright.config.ts", "PWDEBUG", "trace viewer", or "toHaveScreenshot". Avoid using for generic browser automation unless Playwright is requested, and avoid using for pure web scraping.
extract-and-export
Crawlio-app
Use this skill when the user asks to "download and export a site", "crawl and extract content", "archive a website", "export as WARC/ZIP/PDF", or wants a complete crawl-extract-export pipeline. Crawls the site, extracts structured content, and exports in the requested format.
cloudflare-browser-rendering
brixtonpham
Guide for implementing Cloudflare Browser Rendering - a headless browser automation API for screenshots, PDFs, web scraping, and testing. Use when automating browsers, taking screenshots, generating PDFs, scraping dynamic content, extracting structured data, or testing web applications. Supports REST API, Workers Bindings (Puppeteer/Playwright), MCP servers, and AI-powered automation. (project)
bouncer
timmyg
"Name's not on the list. Scans every skill, plugin, and MCP server you've got installed, checks their IDs at the door, and walks you through setting up anyone who showed up without credentials."
setup-scheduled-scraper
sawyerh
Set up a local Playwright + Next.js scraper project with scheduled runs and an optional web viewer. Use when asked to build a project that scrapes specific URLs on a schedule, stores results locally (JSON), and optionally provides a Next.js App Router + Tailwind + Shadcn data viewer. Assumes macOS launchd automation by default.
cendoj-scraper
cjescudero
Buscar resoluciones judiciales en CENDOJ mediante automatizacion con Playwright e interceptacion de red (sin extraer resultados del DOM). Usar cuando se necesite consultar sentencias por texto libre, tribunal, identificador ROJ o identificador ECLI, y devolver resultados estructurados en JSON desde scripts/scraper.py.
extract
Alexu0317-FATHER
"Scan the current session for cognition/thinking/preference signals and write to extract-buffer.md. Run in the target session (current or --resume'd). Manual invocation only."
nextfriday-types
next-friday
Next Friday TypeScript patterns for props, interfaces, and return types. Use when defining types or writing function signatures.
complexity
zhongjis
Use when reducing cognitive complexity, flattening nested code, or simplifying functions. Triggers on "reduce complexity", "simplify", "too nested".
playwright
zhongjis
Browser automation via Playwright MCP tools. Use when AI Agent needs to interact with web browsers for: (1) Web scraping and data extraction, (2) Form interaction and submission, (3) Browser testing and validation, (4) Taking screenshots of web pages, or any browser automation tasks.
skill-learn
rxdaozhang
Consolidate actionable lessons after another skill is used and required multiple correction rounds. Use this skill at task closure to extract concrete failures from the current conversation, propose safe incremental updates to the original skill files, show a diff first, and only apply changes after explicit user confirmation. Works for Claude and Codex skill workflows.
firecrawl
edxeth
Scrapes and crawls web pages, converting them to clean markdown or structured JSON for LLM consumption. Use when needing to extract content from URLs, crawl entire websites, map site structure, search the web with scraping, or extract structured data from pages. Best for web scraping, site crawling, URL discovery, and converting web content to LLM-ready formats.
extracting-keywords
arielperez82
Extract keywords from documents using YAKE algorithm with support for
CodingHeader
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
qa
AgustinAlbonico
"Alias corto para ejecutar pruebas E2E y QA manual. Usar cuando quieras probar la ultima funcionalidad implementada con /qa."
personal-context-agent
Cursedpotential
"Extract and structure personal context from AI chat transcripts into themed markdown files. Use when (1) Processing Claude, Claude Code, or other AI conversation exports, (2) Building personalized AI assistants from chat history, (3) Creating context files for Claude Projects, GPTs, or Gems, (4) Consolidating scattered knowledge from multiple conversations. Optimized for Claude Haiku."