web-browser

Automate Chrome browsing via Chrome DevTools Protocol with Node.js CLI tools.

3|1|Updated Jul 16, 2025
One-click install
npx skills add https://github.com/MykalMachon/llm-config --skill web-browser-mykalmachon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-browser
Source: https://github.com/MykalMachon/llm-config/tree/main/skills/web-browser
Command: npx skills add https://github.com/MykalMachon/llm-config --skill web-browser-mykalmachon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables Claude to interact with web pages by controlling Chrome/Chromium via the Chrome DevTools Protocol to perform actions like clicking, filling out forms, and navigating links, saving you time on repetitive web tasks.

Core Features & Use Cases

  • Navigate: Open pages or switch tabs in a controlled browser session.
  • Interact: Click elements, fill forms, and extract data.
  • Examples: Automate a login, collect data from a page, or capture a screenshot for quick validation.

Quick Start

Start Chrome in remote-debugging mode and use the provided tools (nav.js, eval.js, pick.js, screenshot.js) to automate a simple task such as navigating to https://example.com and taking a screenshot.

Frequently Asked Questions about web-browser

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

FAQPage Schema
How do I automate web browser tasks with Chrome DevTools Protocol?

Chrome DevTools Protocol (CDP) enables remote control of Chrome/Chromium to automate web tasks. This Skill uses Puppeteer-core in Node.js to remotely command a browser instance for navigation, form interaction, and content extraction without manual intervention.

Can I use Puppeteer to automate clicking, form filling, and data extraction?

Yes. Puppeteer-core allows you to click elements, fill forms, navigate pages, and extract data from web content. This Skill provides CLI tools (nav.js, eval.js, pick.js, screenshot.js) to execute these interactions against a Chrome instance running with remote debugging enabled.

What setup do I need to start automating web tasks with a headless browser?

You need Chrome or Chromium running with remote debugging enabled on port 9222, Node.js with Puppeteer-core installed, and the provided CLI tools. Start Chrome in remote-debugging mode, then use the tools to automate navigation, interaction, and screenshots.

How do I take screenshots and validate web page state programmatically?

The screenshot.js tool captures page snapshots after navigation and interaction. This enables quick validation of web state, page rendering, or form completion without manual inspection, useful for QA and testing workflows.

What are the limitations of browser automation via Chrome DevTools Protocol?

CDP-based automation requires Chrome/Chromium with remote debugging enabled; it works best for headless testing and scraping. Performance scales with browser instance capacity, and complex JavaScript interactions may need explicit waits or script evaluation via eval.js.

Can I use this for web scraping and testing workflows?

Yes. This Skill supports automated site exploration, form interaction, and content extraction across testing, scraping, and QA workflows. Use it to navigate pages, interact with elements, and extract data at scale without manual browsing.