Browser Automation

Automate Chrome browser sessions for web scraping and data extraction.

5|Updated Nov 26, 2025

Search Tags:#automation #puppeteer #scraping #browser #headless #Chrome

Ready to run

npx skills add https://github.com/jeffvincent/claude-config --skill browser-automation-jeffvincent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Browser Automation
Source: https://github.com/jeffvincent/claude-config/tree/main/skills/browser-automation
Command: npx skills add https://github.com/jeffvincent/claude-config --skill browser-automation-jeffvincent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core^21.0.0, node>=18.0.0.

What problem does it solve?

Lightweight browser automation for Claude agents to perform web scraping, SEO analysis, and data extraction from JavaScript-heavy sites with a small, focused set of scripts.

Core Features & Use Cases

Launch Chrome with remote debugging, navigate pages, execute scripts, take screenshots, export cookies.

Quick Start

Example prompts:

"Start browser in headless mode"
"Navigate to https://example.com"
"Take a full-page screenshot"

Frequently Asked Questions about Browser Automation

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

FAQPage Schema

How do I scrape data from JavaScript-heavy websites?▼

Web scraping JavaScript-rendered sites requires executing scripts in a real browser environment. Puppeteer Core automates Chrome to render JavaScript, extract DOM content, and return structured data suitable for RAG pipelines and downstream analysis.

Can I automate Chrome for SEO analysis and screenshots?▼

Yes. Browser automation with Puppeteer Core lets you navigate pages, execute custom scripts, capture full-page screenshots, and extract metadata for SEO analysis across multiple pages in headless mode.

How do I handle authenticated sessions during web scraping?▼

Puppeteer Core supports authenticated browser sessions by navigating login flows, managing cookies, and maintaining session state across multi-page scraping tasks, enabling access to content behind authentication.

What's the difference between browser automation and simple HTTP scraping?▼

Browser automation executes JavaScript and renders dynamic content, making it suitable for modern single-page applications. HTTP scraping works only on static HTML. Use browser automation when sites load content via JavaScript.

Do I need Node.js 18 or higher to run browser automation?▼

Yes. This Skill requires Node.js 18.0.0 or newer and Puppeteer Core 21.0.0 or higher to launch Chrome with remote debugging and handle JSON-formatted outputs.

What can I do after extracting data with browser automation?▼

Extracted data outputs as JSON, enabling downstream processing: database ingestion, RAG pipeline enrichment, analytics dashboards, or format conversion for reporting and further analysis.