Control a browser using cmux commands from your terminal. Open any website, click buttons, fill in text fields, and submit forms. You can also wait for pages to load fully or for specific text to appear.
Use snapshots to get a fresh list of elements on the page. Each element gets a ref like e1 or e2. Then you can click, fill, or press keys on those elements. After an action, take another snapshot to see the new state.
This skill works inside cmux webviews. It is great for automating tasks like logging in, checking dashboards, or extracting data from websites. The commands are simple and easy to repeat.
Global
mkdir -p ~/.claude/skills/cmux-browserProject
mkdir -p .claude/skills/cmux-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