Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
Launches Chrome, navigates pages, executes JavaScript, captures screenshots, and picks DOM elements via CDP. Useful for browser automation without MCP server.
How this skill is triggered — by the user, by Claude, or both
Slash command
/stellarlinkco-myclaude:browserThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Minimal Chrome DevTools Protocol (CDP) helpers for browser automation without MCP server setup.
Minimal Chrome DevTools Protocol (CDP) helpers for browser automation without MCP server setup.
Install dependencies before first use:
npm install --prefix ~/.claude/skills/browser/browser ws
All scripts connect to Chrome on localhost:9222.
scripts/start.js # Fresh profile
scripts/start.js --profile # Use persistent profile (keeps cookies/auth)
scripts/nav.js https://example.com # Navigate current tab
scripts/nav.js https://example.com --new # Open in new tab
scripts/eval.js 'document.title'
scripts/eval.js '(() => { const x = 1; return x + 1; })()'
Use single expressions or IIFE for multiple statements.
scripts/screenshot.js
Returns { path, filename } of saved PNG in temp directory.
scripts/pick.js "Click the submit button"
Returns element metadata: tag, id, classes, text, href, selector, rect.
scripts/start.js --profile for authenticated sessionsscripts/nav.js <url>scripts/eval.js 'document.querySelector(...)'scripts/screenshot.js or scripts/pick.js--profile flag to preserve cookies and auth tokensnpx claudepluginhub stellarlinkco/myclaudeAutomates browser tasks via Chrome DevTools Protocol: launch Chrome, navigate pages, extract DOM, take screenshots, and pick elements interactively.
Interacts with a live Chrome browser session via the Chrome DevTools Protocol. Reads page content, clicks elements, executes JS, navigates, and takes screenshots. Requires explicit user approval.
Controls a browser via Chrome DevTools Protocol (CDP) for navigation, DOM manipulation, JavaScript execution, network control, input simulation, and device emulation.