web-browser

Automate Chrome/Chromium navigation and interaction via the Chrome DevTools Protocol.

10|Updated Dec 15, 2014
One-click install
npx skills add https://github.com/baleen37/dotfiles --skill web-browser-baleen37
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-browser
Source: https://github.com/baleen37/dotfiles/tree/main/users/shared/.config/claude/skills/web-browser
Command: npx skills add https://github.com/baleen37/dotfiles --skill web-browser-baleen37

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, and includes scripts (resource) components.

What problem does it solve?

This Skill eliminates the need for manual web browsing by allowing programmatic control of web pages through automated navigation, interaction, and data extraction.

Core Features & Use Cases

  • Browser Automation: Control Chrome/Chromium browsers remotely using the Chrome DevTools Protocol.
  • Interactive Element Selection: Visually identify and select page elements with an intuitive picker tool.
  • Use Case: Imagine you need to log into a website, fill out a complex form, and download the resulting report - all without touching your mouse or keyboard.

Quick Start

Use the web-browser skill to navigate to example.com and take a screenshot of the homepage.

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 navigation and form filling without manual interaction?

Web browser automation uses the Chrome DevTools Protocol to remotely control Chrome/Chromium, enabling programmatic navigation, form submission, and interaction. Connect via Puppeteer-core to send commands and capture page state without touching the keyboard or mouse.

Can I use Puppeteer-core to control a browser remotely?

Yes, Puppeteer-core connects to Chrome or Chromium running with remote debugging enabled via the Chrome DevTools Protocol. This allows remote browser control for navigation, element selection, JavaScript execution, and screenshot capture across single or multi-tab sessions.

How do I capture screenshots and select elements on a webpage programmatically?

Browser automation with Puppeteer-core lets you take screenshots and visually identify page elements through an interactive picker tool. Evaluate JavaScript to extract data and select elements, then capture the resulting page state as images.

What setup is required to start automating a Chrome browser?

Start Chrome or Chromium with remote debugging enabled, then connect Puppeteer-core to the Chrome DevTools Protocol endpoint. This establishes the connection needed for remote navigation, interaction, and state evaluation.

Can I automate multi-tab browser workflows for data extraction?

Yes, browser automation supports multi-tab sessions through Puppeteer-core, enabling workflows that navigate across tabs, interact with page elements, evaluate JavaScript, and extract data from multiple pages in a single session.