skills.rest
winsorllc
winsorllcCOMMUNITY
Explore all skills by this author →
GitHub

browser-tools

Automate Chrome browser interactions via the Chrome DevTools Protocol.

1|Updated Feb 25, 2026
Search Tags:#automation#testing#web scraping#devtools#chrome#browser
One-click install
npx skills add https://github.com/winsorllc/upgraded-carnival --skill browser-tools-winsorllc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-tools
Source: https://github.com/winsorllc/upgraded-carnival/tree/main/.pi/skills/browser-tools
Command: npx skills add https://github.com/winsorllc/upgraded-carnival --skill browser-tools-winsorllc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires puppeteer-core, jsdom, @mozilla/readability, turndown, turndown-plugin-gfm, cheerio, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows for programmatic interaction with web pages, enabling tasks like testing frontends, automating user interactions, and extracting dynamic content.

Core Features & Use Cases

  • Browser Automation: Control a Chrome browser instance via the Chrome DevTools Protocol.
  • Navigation: Open URLs, navigate tabs, and reload pages.
  • Content Extraction: Extract readable content from web pages as Markdown.
  • Element Picking: Interactively select DOM elements for automation.
  • Use Case: Automatically fill out a web form by first picking the input fields and then providing the data to be entered.

Quick Start

Navigate to https://example.com in the browser.

Frequently Asked Questions about browser-tools

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

FAQPage Schema
How do I automate web page interaction using Chrome DevTools Protocol?▼

Browser automation via Chrome DevTools Protocol requires a running Chrome instance with remote debugging enabled on port 9222, enabling script-driven URL navigation, JavaScript evaluation, and DOM element interaction.

How can I extract readable content from a web page as Markdown?▼

Extract readable web page content as Markdown by utilizing Readability and Turndown dependencies to parse HTML documents and convert extracted text into structured Markdown format.

What do I need to run Puppeteer-core for browser automation?▼

Running Puppeteer-core for browser automation requires launching a local Chrome browser instance with remote debugging enabled on port 9222 to establish the DevTools Protocol connection.

Can I interactively select DOM elements for web scraping?▼

Interactively select DOM elements for web scraping by utilizing the element picking feature, enabling targeted extraction of specific page components and dynamic content structures.

What is the best way to capture screenshots of dynamic web pages?▼

Capture screenshots of dynamic web pages by connecting to Chrome via DevTools Protocol, navigating to the target URL, and executing the screenshot command after page rendering completes.

Does this browser automation approach work with Cheerio for content extraction?▼

This browser automation approach integrates Cheerio for HTML parsing and DOM element selection, streamlining the extraction of specific page components during web scraping workflows.

Related Skills

Explore More Software Engineering Skills→
mksglumksglu
43

browsirai

Connect AI agents to a running Chrome instance via the Chrome DevTools Protocol.

Community
Advanced
mupengi-botmupengi-bot
11

data-scraper

Fetch HTML from URLs and extract structured data into JSON or Markdown.

Community
Intermediate
hheydaroffhheydaroff

browser-tools

Automate web browsing, DOM interaction, and page content extraction.

Community
Intermediate
josorio7122josorio7122

browser-tools

Automates web page interaction and data extraction through Chrome DevTools Protocol.

Community
Intermediate