browser-tools

Control web pages via Chrome DevTools Protocol for navigation, JavaScript, and screenshots.

35|1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/jal-co/jalco-pi-mono --skill browser-tools-jal-co
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-tools
Source: https://github.com/jal-co/jalco-pi-mono/tree/main/pi/.pi/agent/skills/browser-tools
Command: npx skills add https://github.com/jal-co/jalco-pi-mono --skill browser-tools-jal-co

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 an AI to interact with web pages programmatically, enabling tasks that require visual understanding or user-like interaction with a browser.

Core Features & Use Cases

  • Navigate: Open and control web pages.
  • Evaluate JavaScript: Execute custom JavaScript code within the browser context.
  • Element Picking: Allow users to visually select DOM elements for interaction or data extraction.
  • Screenshotting: Capture visual state of web pages.
  • Use Case: When a user asks to "fill out the login form on example.com", this skill can be used to navigate to the page, identify the input fields, and fill them with provided credentials.

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 browser interaction and execute JavaScript on web pages?

Automated browser interaction is achieved through the Chrome DevTools Protocol, enabling navigation, custom JavaScript execution, and element selection within a live browser context.

What do I need to run Chrome DevTools Protocol automation for web scraping?

Running DevTools Protocol automation requires a Brave browser instance with remote debugging explicitly enabled on port 9222 to facilitate programmatic web page control.

Can I extract readable content from dynamic web pages using Puppeteer?

Yes, dynamic content scraping is supported by navigating with Puppeteer-core and processing the page DOM using Cheerio, Readability, and Turndown to extract and format text.

How does frontend testing work with web automation via the DevTools Protocol?

Frontend testing leverages the DevTools Protocol to navigate URLs, visually pick DOM elements, execute test scripts, and capture screenshots to verify application state.

What are the limitations of using Puppeteer-core for web automation?

A key limitation is that Puppeteer-core requires a pre-existing browser connection; it cannot download or launch a browser automatically, necessitating a manually configured Brave instance.