crawl4ai-skill

Run `npx skills add brettdavies/crawl4ai-skill --all -g -y` in your terminal to install the skill globally. You also need the Crawl4AI Python library installed via `pip install crawl4ai` followed by `crawl4ai-setup`.

This skill renders pages in a headless browser with network-idle waiting, so content loaded by JavaScript is fully captured. A single command like `crwl <url> -o markdown` returns clean markdown.

Generate a reusable CSS schema once with the bundled script, then apply it to any number of pages for fast, deterministic extraction with zero per-request LLM cost.

Yes. It follows the universal SKILL.md standard and loads in Claude Code, Codex, Cursor, OpenCode, Cline, and other compatible hosts.

Yes. Batch scripts crawl multiple URLs concurrently, and session templates support authenticated, multi-step flows with proxies and anti-detection options.