browser

Name: browser - Agent Skill
Rating: 5.0 (1998 reviews)
Author: cexll

1,998

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

Download Folder View on GitHub

CLI Install

Recommended

Use the skills CLI to install this skill with one command. Auto-detects all installed AI assistants.

Method 1 - skills CLI

npx skills i cexll/myclaude/skills/browser

Method 2 - openskills (supports sync & update)

npx openskills install cexll/myclaude

Auto-detects Claude Code, Cursor, Codex CLI, Gemini CLI, and more. One install, works everywhere.

Installation Path

Download and extract to one of the following locations:

~/.claude/skills/browser/

SKILL.md

scripts

browser.zip

package-lock.json

package.json

Skill Instructions

Back

Run with Cloud Agent

No setup needed. Let our cloud agents run this skill for you.

Select Provider

Select Model

Claude Sonnet 4.5

$0.20/task

Best for coding tasks

Environment setup included

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

Launch Chrome: scripts/start.js --profile for authenticated sessions
Navigate: scripts/nav.js <url>
Inspect: scripts/eval.js 'document.querySelector(...)'
Capture: scripts/screenshot.js or scripts/pick.js
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