chrome-devtools

Automate browser tasks with Puppeteer CLI scripts for testing and data extraction.

Updated Aug 23, 2026

Search Tags:#debugging #browser automation #web scraping #Chrome DevTools #performance testing #Puppeteer #screenshot

One-click install

npx skills add https://github.com/hanthienduc/myprotocol-stack --skill chrome-devtools-hanthienduc

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: chrome-devtools
Source: https://github.com/hanthienduc/myprotocol-stack/tree/main/.claude/skills/chrome-devtools
Command: npx skills add https://github.com/hanthienduc/myprotocol-stack --skill chrome-devtools-hanthienduc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer, debug, yargs, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Manually interacting with browsers for testing, scraping, or performance analysis is repetitive and error-prone. This skill provides a suite of executable Puppeteer CLI scripts to automate browser tasks, offering precise control over web pages for debugging, performance monitoring, and data extraction.

Core Features & Use Cases

Comprehensive Browser Automation: Navigate, click, fill forms, take screenshots (with auto-compression), and execute custom JavaScript directly in the browser context.
Advanced Web Analysis: Monitor console messages, track network requests/responses, and measure Core Web Vitals to diagnose performance bottlenecks and debug client-side issues.
Robust Error Recovery & Troubleshooting: Includes guidelines for verifying working directories, validating outputs, and recovering from script failures, ensuring reliable automation.
Use Case: You need to automate a login process, take a full-page screenshot of a dashboard, and then extract specific data from a table. You can chain navigate.js, fill.js, click.js, screenshot.js, and evaluate.js to perform this entire workflow programmatically.

Quick Start

Navigate to 'https://example.com' and take a full-page screenshot, saving it as 'example.png' in the 'docs/screenshots' directory.