Facilitates local browser automation, including page navigation, DOM inspection, and screenshot capture, via Chrome DevTools Protocol.
Install
mkdir -p .claude/skills/browser && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1144" && unzip -o skill.zip -d .claude/skills/browser && rm skill.zipInstalls to .claude/skills/browser
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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.Key capabilities
- →Launch Chrome with remote debugging
- →Navigate to specific URLs in new or existing tabs
- →Execute custom JavaScript expressions or IIFEs
- →Capture screenshots of browser pages
- →Extract metadata from DOM elements via visual picking
How it works
The skill utilizes Chrome DevTools Protocol (CDP) helpers to interface with a local Chrome instance running on localhost:9222. Scripts are executed via command line to perform navigation, evaluation, and visual inspection.
Inputs & outputs
When to use browser
- →Scrape data from complex web pages
- →Automate repetitive browser tasks
- →Capture screenshots for visual testing
- →Inspect DOM elements via scripts
About this skill
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 --profilefor authenticated sessions - Navigate:
scripts/nav.js <url> - Inspect:
scripts/eval.js 'document.querySelector(...)' - Capture:
scripts/screenshot.jsorscripts/pick.js - Return gathered data
Key Points
- All operations run locally - credentials never leave the machine
- Use
--profileflag to preserve cookies and auth tokens - Scripts return structured JSON for agent consumption
When not to use it
- →When an MCP server is required for the environment
- →When browser automation requires non-local execution
Prerequisites
Limitations
- →Requires Chrome to be running on localhost:9222
- →All operations are restricted to the local machine
How it compares
Unlike manual browser interaction, this skill provides structured JSON outputs for agent consumption and supports automated session persistence via profile flags.
Compared to similar skills
browser side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| browser (this skill) | 3 | 7mo | Review | Intermediate |
| dev-browser | 53 | 4mo | Review | Intermediate |
| agent-browser | 30 | 3mo | Review | Intermediate |
| browser-tools | 6 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by cexll
View all by cexll →You might also like
dev-browser
SawyerHood
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
agent-browser
vercel-labs
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
browser-tools
Whamp
Lightweight Chrome automation toolkit with shared configuration, JSON-first output, and six focused scripts for starting, navigating, inspecting, capturing, evaluating, and cleaning up browser sessions.
agent-browser-skill
MGdaasLab
基于 agent-browser CLI 的浏览器自动化工具。提供快照获取、元素交互、截图等功能。推荐用于需要页面快照分析、通过 ref 引用交互元素的场景。
browserwing-executor
browserwing
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
go-rod-master
rootcastleco
Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns.