Control your Chrome browser directly from an AI agent. This skill lets the agent see what you see and interact with your open tabs. It uses the Chrome DevTools Protocol to connect to your live Chrome session. That means the AI can work with your logged-in accounts, cookies, and the current page state without launching a fresh browser.
You can ask the AI to take a screenshot of a webpage, click elements, read content from a tab, or navigate to a URL. It even works inside cross-origin iframes. No extra software is needed beyond Node.js 22 or higher. Just enable remote debugging in Chrome once, and the skill handles the rest.
This tool is great for anyone who wants an AI assistant to automate tasks on websites they are already logged into. It supports over 100 open tabs and works with Chrome, Brave, Edge, and Vivaldi on any operating system.
Global
mkdir -p ~/.claude/skills/chrome-cdp-live-browserProject
mkdir -p .claude/skills/chrome-cdp-live-browserSource Repository
Agent Browservercel-labs/agent-browser
Fast browser automation tool for AI agents to control any website
Develop Userscriptsxixu-me/skills
Build and debug browser userscripts for Tampermonkey and ScriptCat
Just Scrapescrapegraphai/just-scrape
Search, scrape, crawl, and monitor web pages with an easy command line tool
Browser Actbrowser-act/skills
AI agents use browser-act to automate web tasks like fetch forms screenshots and complex workflows
Firecrawlfirecrawl/cli
Search, scrape, and crawl websites with one simple command line tool
Playwright Climicrosoft/playwright-cli
Automate browser tasks and test web pages with simple terminal commands
Browser Usebrowser-use/browser-use
Automate web testing, form filling, and screenshots with simple CLI commands
Browser Act Skill Forgebrowser-act/skills
Explore any website once and create reusable skill packages forever