mcpField
B
browser

browser

github.com/stellarlinkcoDevelopment2.8k199 installsUpdated 27w ago
Repository

About browser

A browser automation skill that uses lightweight Chrome DevTools Protocol helpers instead of requiring MCP server setup. It provides scripts to launch Chrome, navigate, run JavaScript, capture screenshots, and inspect elements; operations run locally.

Key features

  1. 01Launch Chrome with optional persistent profile
  2. 02Navigate current or new tabs
  3. 03Execute JavaScript expressions
  4. 04Capture screenshots
  5. 05Pick elements and return metadata
  6. 06Return structured JSON

Use cases

  1. 01Automating local Chrome navigation
  2. 02Inspecting page content with JavaScript
  3. 03Capturing screenshots for an agent

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/stellarlinkco/myclaude --skill browser

After installing, type/browserin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

package-lock.json
package.json
scripts/
eval.cjs
nav.cjs
pick.cjs
screenshot.cjs
start.cjs

Details

From the project README

Browser Automation

Minimal Chrome DevTools Protocol (CDP) helpers for browser automation without MCP server setup.

Setup

Install dependencies before first use:

npm install --prefix ~/.claude/skills/browser/browser ws

Scripts

All scripts connect to Chrome on localhost:9222.

start.js - Launch Chrome
scripts/start.js              # Fresh profile
scripts/start.js --profile    # Use persistent profile (keeps cookies/auth)
nav.js - Navigate
scripts/nav.js https://example.com        # Navigate current tab
scripts/nav.js https://example.com --new  # Open in new tab
eval.js - Execute JavaScript
scripts/eval.js 'document.title'
scripts/eval.js '(() => { const x = 1; return x + 1; })()'

Use single expressions or IIFE for multiple statements.

screenshot.js - Capture Screenshot
scripts/screenshot.js

Returns { path, filename } of saved PNG in temp directory.

pick.js - Visual Element Picker
scripts/pick.js "Click the submit button"

Returns element metadata: tag, id, classes, text, href, selector, rect.

Workflow

  1. Launch Chrome: scripts/start.js --profile for authenticated sessions
  2. Navigate: scripts/nav.js <url>
  3. Inspect: scripts/eval.js 'document.querySelector(...)'
  4. Capture: scripts/screenshot.js or scripts/pick.js
  5. Return gathered data

Key Points

  • All operations run locally - credentials never leave the machine
  • Use --profile flag to preserve cookies and auth tokens
  • Scripts return structured JSON for agent consumption

Comments

Markdown supported