skills.rest
xxih
xxihCOMMUNITY
Explore all skills by this author →
GitHub

browser

Automate Chrome navigation, JavaScript execution, screenshots, and DOM selection via the Chrome DevTools Protocol on port 9222.

1|Updated Mar 18, 2026
Search Tags:#automation#cdp#chrome#browser#screenshot#web-scraping#dom
One-click install
npx skills add https://github.com/xxih/ai-harness-zh --skill browser-xxih
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/xxih/ai-harness-zh/tree/main/references/translations/happy-claude-skills/skills/browser
Command: npx skills add https://github.com/xxih/ai-harness-zh --skill browser-xxih

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill removes repetitive manual browser interactions by providing a minimal Chrome DevTools Protocol toolset to start Chrome, navigate pages, run page JavaScript, capture screenshots, and interactively select DOM elements for scraping or testing.

Core Features & Use Cases

  • Start Chrome with profile: launch Chrome with or without your existing profile to preserve login state.
  • Navigate and control pages: open URLs in the current or a new tab and drive page navigation programmatically.
  • Evaluate JavaScript in-page: run single-expression or IIFE JavaScript in the page's async context to extract data or inspect the DOM.
  • Visual evidence and selection: capture viewport screenshots and use an interactive element picker to obtain precise selectors.
  • Use Case: efficiently scrape dynamic content, verify UI states for automated testing, or collect screenshots and DOM snapshots for bug reports.

Quick Start

Start a Chrome instance with your profile, navigate to the target site, evaluate a page expression to inspect the DOM, and capture a screenshot using the browser skill's scripts.

Frequently Asked Questions about browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Chrome browsing and web scraping using the Chrome DevTools Protocol?▼

You can automate Chrome browsing and web scraping using the Chrome DevTools Protocol by running scripts to start Chrome, navigate pages, execute in-page JavaScript, capture screenshots, and interactively select DOM elements for data extraction.

How do I extract dynamic content from a web page using CDP?▼

To extract dynamic content using CDP, you evaluate JavaScript in the page's async context. This allows you to run single expressions or IIFEs to inspect the DOM and programmatically extract data from dynamically loaded elements.

Do I need a specific Chrome configuration to automate browser control?▼

Yes, automating browser control requires a Chrome instance with remote debugging enabled on port 9222. The Skill provides specific scripts to launch Chrome with your existing profile to preserve login state.

Can I capture screenshots and pick DOM elements interactively for automated testing?▼

Yes, you can capture viewport screenshots and use an interactive element picker to obtain precise CSS selectors. This visual evidence and DOM selection is useful for verifying UI states or collecting bug report snapshots.

What is the best way to scrape dynamic content without manual browser interactions?▼

The best way to scrape dynamic content without manual interactions is using a minimal Chrome DevTools Protocol toolset. It programmatically drives page navigation and runs in-page JavaScript to bypass repetitive manual extraction.

Are there limitations when using a Chrome profile for web scraping automation?▼

When using a Chrome profile for web scraping, you must launch Chrome with remote debugging enabled. Using your existing profile preserves login state, but the automation relies strictly on CDP commands rather than visual GUI interactions.

Related Skills

Explore More Software Engineering Skills→
YeomanYeYeomanYe

cdp-browser-control

Connect to Chrome via CDP to automate browsers while preserving login state.

Community
Intermediate
Runchuan-BURunchuan-BU
401

agent-browser

Automate web browsing to navigate pages, click elements, fill forms, and extract data.

Community
Advanced
MemTensorMemTensor
10.7k

browserwing-executor

Automate browser interactions via HTTP API for navigation, element manipulation, and data extraction.

Official
Advanced
appautomatonappautomaton
18

playwright-cli

Automate complex web interactions and stateful sessions via a Playwright-backed shell interface.

Official
Advanced