Автоматизация браузера с захватом данных и скриншотов

★ 7.1 · automation

browser-act is a Claude Code skill that gives AI agents full browser automation capabilities through the browser-act CLI (version 2.0.2). It handles page navigation and interaction, JavaScript-rendered content extraction, form filling, file uploads, screenshots, XHR/fetch/HAR capture, and parallel operation across multiple isolated browser profiles. All cookies, sessions, and profile data stay local — the only outbound data is a captcha challenge image when solve-captcha is invoked. Install with `uv tool install browser-act-cli --python 3.12` (requires Python 3.12+); well-suited for scraping dynamic sites, automating authenticated workflows, and running multi-step browser tasks inside Claude Code, Cursor, Codex, or Windsurf.