skills.rest
goncalossilva
goncalossilvaCOMMUNITY
Explore all skills by this author →
𝕏@goncalossilvaGitHub

browser-tools

Interact with web pages programmatically via the Chrome DevTools Protocol.

24|3|Updated Jan 4, 2026
Search Tags:#automation#javascript#web scraping#devtools#frontend testing#browser
One-click install
npx skills add https://github.com/goncalossilva/.agents --skill browser-tools-goncalossilva
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-tools
Source: https://github.com/goncalossilva/.agents/tree/main/skills/browser-tools
Command: npx skills add https://github.com/goncalossilva/.agents --skill browser-tools-goncalossilva

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill allows agents to interact with web pages programmatically, enabling tasks that require visual understanding, dynamic content interaction, or user-like actions.

Core Features & Use Cases

  • Browser Automation: Navigate, evaluate JavaScript, take screenshots, and extract content from web pages.
  • Interactive Element Selection: Pick specific elements on a page for interaction or data extraction.
  • Cookie Management: Accept or reject cookie banners to clear the way for interaction.
  • Use Case: An agent needs to find the price of a product on an e-commerce site. It can use browser-tools to navigate to the product page, evaluate JavaScript to get the price, and then extract that information.

Quick Start

Use the browser-tools skill to navigate to https://example.com.

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 scraping of dynamic content rendered with JavaScript?▼

Web scraping of dynamic content is automated by using the Chrome DevTools Protocol to interact with web pages programmatically. This approach evaluates JavaScript and extracts data from fully rendered pages, mimicking human-like user actions.

What's the best way to run automated frontend testing for dynamic web elements?▼

Browser automation for frontend testing is achieved by navigating web pages and evaluating JavaScript via the Chrome DevTools Protocol. It allows agents to take screenshots, interact with specific elements, and verify dynamic visual output.

Do I need a running Chromium-based browser instance to use browser automation tools?▼

A running Chromium-based browser instance with remote debugging enabled is required. This prerequisite allows the automation scripts to connect directly to the browser and execute programmatic interactions like element selection.

Can I extract readable text from web pages after navigating past cookie banners?▼

Extracting readable text is possible by managing cookie banners programmatically to clear the way for interaction. Once accessible, the tool evaluates page content and extracts the required data from the target elements.

How does browser automation handle interactive element selection on complex pages?▼

Interactive element selection is handled by picking specific elements on a page for data extraction or interaction. The Chrome DevTools Protocol evaluates the page structure to target and interact with visual elements precisely.

Why does web scraping fail when extracting prices from e-commerce sites without JavaScript execution?▼

Scraping fails because dynamic content like e-commerce prices requires JavaScript execution to render. Using the Chrome DevTools Protocol evaluates JavaScript directly on the product page, successfully extracting the dynamically loaded price information.

Related Skills

Explore More Software Engineering Skills→
adampetrovicadampetrovic
2

web-browser

Control Chrome/Chromium via the Chrome DevTools Protocol to navigate, execute JavaScript, and capture screenshots.

Community
Intermediate
shoji-swsshoji-sws

hatena-blog-markdown-extractor

Extract Hatena Blog articles into Markdown with frontmatter and absolute image URLs.

Community
Intermediate
ThrookieThrookie
2

playwright-scraper

Automate stealth web scraping of protected sites using Playwright and stealth plugins.

Community
Intermediate
appautomatonappautomaton
18

html-to-markdown

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

Official
Intermediate