Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user mentions deep crawl website, recursive crawl, crawl a whole site, scrape entire website, scrape docs site, scrape documentation, scrape knowledge base, scrape blog, build RAG corpus, build vector…
Install
npx skills add browser-act/skills --skill webcrawler-deep-crawlnpx skills add browser-act/skills --skill webcrawler-deep-crawl -a claude-code -gnpx skills add browser-act/skills --skill webcrawler-deep-crawl -a codex -ggemini skills install https://github.com/browser-act/skills.git --path solutions/search-research/webcrawler-deep-crawlgh skill install browser-act/skills webcrawler-deep-crawlgit clone --depth 1 https://github.com/browser-act/skills /tmp/browser-act__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/browser-act__skills/solutions/search-research/webcrawler-deep-crawl ~/.claude/skills/webcrawler-deep-crawl # Claude Code
cp -R /tmp/browser-act__skills/solutions/search-research/webcrawler-deep-crawl ~/.agents/skills/webcrawler-deep-crawl # Codex, Cursor, Gemini CLI, Copilot, OpenCode