Crawl4AI

Wrappt den Crawl4AI browser scraper für JS-heavy sites, batch crawls und LLM-free schema extraction.

von brettdavies · brettdavies/crawl4ai-skill

Getestet · Funktioniert ★ 10.0/10

Crawl4AI — Wrappt den Crawl4AI browser scraper für JS-heavy sites, batch crawls und LLM-free schema extraction.

Was es kann

Provides CLI (crwl) and Python SDK patterns for Crawl4AI, a Playwright-backed crawler that renders JavaScript-heavy pages and SPAs that plain HTTP fetches can't reach. Covers clean markdown generation, LLM-free CSS/JSON schema extraction, concurrent multi-URL batch crawling, sitemap-driven URL discovery, and login/session handling. Triggers on crawl4ai, crwl, scraping SPAs/JS-heavy sites, and schema-based extraction; explicitly defers to lighter tools (defuddle/fetch-web) for static HTML.

Testbericht

Führte den skill's exact recommended command against a live JS-rendered test page aus: a naive curl+CSS-selector scrape returned zero quotes, while `crwl ... -c wait_until=networkidle` returned all ten quotes with authors and tags cleanly formatted in markdown.

Getestet am: 2026-07-14 · Claude Code 2.x (agent harness)

Installation

git clone https://github.com/brettdavies/crawl4ai-skill
cd crawl4ai-skill
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/crawl4ai

Befehle & Beispiel-Prompts

  • /crawl4aiWrappt den Crawl4AI browser scraper für JS-heavy sites, batch crawls und LLM-free schema extraction.

Skills reagieren auf normale Anfragen — keine Slash-Befehle nötig. Nach der Installation aktivieren Prompts wie diese den Skill (auf Englisch):

  • Scrape this SPA's product listings, it's all client-rendered React.
  • Crawl 500 URLs from this sitemap into clean markdown for me.
  • Extract price and name from these product pages with a CSS schema.