skills.rest
ajianaz
ajianazCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

browser

Automate Chrome browser control for site exploration and scraping via CDP.

4|Updated Dec 4, 2025
Search Tags:#browser automation#web scraping#puppeteer#JavaScript execution#Chrome DevTools#screenshot#DOM interaction
One-click install
npx skills add https://github.com/ajianaz/skills-collection --skill browser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/ajianaz/skills-collection/tree/main/skills/browser
Command: npx skills add https://github.com/ajianaz/skills-collection --skill browser

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill provides minimal Chrome DevTools Protocol (CDP) tools to automate browser tasks, making web scraping, interactive DOM element picking, and page navigation simple and efficient. It eliminates the need for complex manual browser interactions for repetitive tasks, saving you time and effort.

Core Features & Use Cases

  • Browser Automation: Start Chrome, navigate to URLs, and execute JavaScript directly in the browser.
  • Web Scraping: Extract data from web pages by evaluating JavaScript or taking screenshots.
  • Interactive Element Picking: Visually select DOM elements on a page for targeted interactions or data extraction.
  • Use Case: "I need to scrape the titles of all articles on a news website. This skill can start Chrome, navigate to the site, and then execute JavaScript to extract all document.title elements."

Quick Start

Use the browser skill to start Chrome with my existing profile, then navigate to 'https://www.example.com'.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate web scraping and data extraction from websites?▼

Web scraping with browser automation extracts data by programmatically navigating to pages, executing JavaScript, and selecting DOM elements. This skill uses Chrome DevTools Protocol to start Chrome, evaluate in-page scripts, and capture targeted content without manual browser interaction.

Can I use Puppeteer to control Chrome and extract page content?▼

Puppeteer-core enables remote control of Chrome via the Chrome DevTools Protocol for JavaScript execution, screenshot capture, and DOM interaction. This skill wraps those capabilities for site exploration, data extraction, and interactive element selection in a streamlined workflow.

What's the best way to take screenshots and pick DOM elements from live web pages?▼

Browser automation with interactive element picking lets you visually select DOM nodes on a rendered page for targeted data extraction or interaction. This skill provides Chrome DevTools Protocol tools to navigate, screenshot, and interactively identify elements without writing complex selectors.

Do I need Chrome with remote debugging enabled to automate browser tasks?▼

Yes, remote debugging is required. This skill requires Chrome started with remote debugging enabled and access to the Chrome DevTools Protocol, plus Puppeteer-core and Node.js to execute browser automation scripts and interact with pages programmatically.

How do I execute JavaScript directly in a browser during automation?▼

JavaScript execution within browser automation evaluates code in the page context to extract data or interact with elements. This skill uses Chrome DevTools Protocol to evaluate scripts on live pages, returning results for parsing or further processing.

What are the limitations of browser automation for web scraping?▼

Browser automation requires Chrome with remote debugging, full-path script invocation, and Node.js runtime. It handles JavaScript-heavy sites and interactive content better than static parsing but needs adequate system resources and may face rate-limiting on target sites.

Related Skills

Explore More Software Engineering Skills→
neo-unicornneo-unicorn
2

neo-xiaohongshu-push

Save prepared posts to Xiaohongshu drafts via Chrome DevTools Protocol.

Community
Intermediate
verrio1verrio1

Documents

Extract text and tables from DOCX, PDF, PPTX, and XLSX into JSON/CSV.

Community
Advanced
jackandkingjackandking

pagination-handler

Automate paginated web data extraction across multiple navigation patterns.

Community
Advanced
appautomatonappautomaton
18

html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

Official
Intermediate