Loading...
Loading...
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
npx skill4agent add mitsuhiko/agent-stuff web-browser./scripts/start.js # Fresh profile
./scripts/start.js --profile # Copy your profile (cookies, logins):9222./scripts/nav.js https://example.com
./scripts/nav.js https://example.com --new./scripts/eval.js 'document.title'
./scripts/eval.js 'document.querySelectorAll("a").length'
./scripts/eval.js 'JSON.stringify(Array.from(document.querySelectorAll("a")).map(a => ({ text: a.textContent.trim(), href: a.href })).filter(link => !link.href.startsWith("https://")))'./scripts/screenshot.js./scripts/pick.js "Click the submit button"./scripts/dismiss-cookies.js # Accept cookies
./scripts/dismiss-cookies.js --reject # Reject cookies (where possible)./scripts/nav.js https://example.com && ./scripts/dismiss-cookies.jsstart.js~/.cache/agent-web/logs/YYYY-MM-DD/<targetId>.jsonl./scripts/watch.js./scripts/logs-tail.js # dump current log and exit
./scripts/logs-tail.js --follow # keep following./scripts/net-summary.js