skills.rest
h4v1d
h4v1dCOMMUNITY
Explore all skills by this author →
GitHub

browser

Control Chrome via DevTools Protocol to automate browsing, scraping, and screenshots.

Updated Dec 9, 2025
Search Tags:#automation#browser#Chrome#CDP#web-scraping#Puppeteer-core#dom-element-picker
One-click install
npx skills add https://github.com/h4v1d/extension-collection-geminicli --skill browser-h4v1d
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/h4v1d/extension-collection-geminicli/tree/main/browser
Command: npx skills add https://github.com/h4v1d/extension-collection-geminicli --skill browser-h4v1d

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core.

What problem does it solve?

This Skill provides lightweight Chrome DevTools Protocol tools to automate common browser tasks such as starting Chrome with remote debugging, navigating pages, evaluating JavaScript, taking screenshots, and interactively selecting DOM elements, all without heavy dependencies.

Core Features & Use Cases

  • Start Chrome with remote debugging and optional profile sync
  • Navigate to URLs or open new tabs and manage page context
  • Evaluate JavaScript in the active page context
  • Take screenshots of the current viewport for visual validation
  • Interactively pick DOM elements to inspect or reference in automation
  • Use cases include quick web scraping, automated testing, and QA checks on live sites

Quick Start

Use the browser skill to quickly automate common browser tasks:

  • Start Chrome: ~/.factory/skills/browser/start.js
  • Navigate: ~/.factory/skills/browser/nav.js https://example.com
  • Evaluate JS: ~/.factory/skills/browser/eval.js 'document.title'
  • Screenshot: ~/.factory/skills/browser/screenshot.js
  • Pick Elements: ~/.factory/skills/browser/pick.js "Click the submit button"

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate Chrome tasks using the Chrome DevTools Protocol?▼

Automate Chrome tasks by connecting via the Chrome DevTools Protocol to start Chrome with remote debugging, navigate pages, evaluate JavaScript, take screenshots, and interactively pick DOM elements.

How do I start Chrome with remote debugging for web scraping?▼

Start Chrome with remote debugging by executing a launch script that initializes the browser instance with an active debugging port, enabling connections for web scraping and automated testing workflows.

Can I evaluate JavaScript in the active page context during web automation?▼

Yes, you can evaluate JavaScript in the active page context during web automation by executing page-context scripts directly through the connected Puppeteer-core instance to extract data or trigger actions.

Does this browser automation approach work with Puppeteer-core?▼

Yes, this browser automation approach uses Puppeteer-core as its dependency to connect to Chrome via the DevTools Protocol, allowing you to manage page context and execute scripts without heavy browser downloads.

What is the best way to interactively pick DOM elements for automated testing?▼

Interactively pick DOM elements by running a picker script that prompts user selection on the live site, allowing you to capture exact element references for automated testing and QA checks.

How do I take a screenshot of the current viewport for visual validation?▼

Take a screenshot of the current viewport by executing a screenshot script after navigating to the target URL, rendering a visual capture for QA checks and visual validation of the active page.

Related Skills

Explore More Software Engineering Skills→
limaonlimaon

browser

Automate Chrome browser tasks via the Chrome DevTools Protocol.

Community
Advanced
aws-samplesaws-samples
90

file-processing

Process and analyze CSV, JSON, and text data files with automated cleaning and transformation.

Official
Advanced
0xMassi0xMassi
2.1k

webclaw

Extract text, metadata, and structured data from web pages into Markdown and JSON.

Community
Advanced
gyuhagyuha
2

scrapling-official

Scrape and crawl websites with HTTP requests, browser automation, and anti-bot bypass.

Community
Advanced