Browser

Automate web page navigation, element interaction, and DOM reading via Chrome DevTools Protocol.

6|3|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/lordmacu/nexo-rs --skill browser-lordmacu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Browser
Source: https://github.com/lordmacu/nexo-rs/tree/main/skills/browser
Command: npx skills add https://github.com/lordmacu/nexo-rs --skill browser-lordmacu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for web page interaction and scraping, allowing users to navigate, click, fill forms, read the DOM, take screenshots, and run JavaScript within a managed Chrome session.

Core Features & Use Cases

  • Web Page Interaction: Navigate to URLs, click elements, fill forms, and scroll through pages.
  • DOM Reading: Extract text and element references from the Document Object Model (DOM).
  • Screenshotting: Capture visual content of the web page as a base64 PNG.
  • JavaScript Execution: Run arbitrary JavaScript code for dynamic web page interactions.
  • Use Case: Ideal for tasks like automating web form submissions, scraping structured data, or interacting with web applications that require user input.

Quick Start

Use the browser skill to navigate to 'https://example.com' and take a screenshot.

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 with Chrome sessions?

Automate web scraping by controlling Chrome sessions via the Chrome DevTools Protocol to navigate URLs, interact with elements, and read the DOM. This approach allows you to extract structured data and capture screenshots from live web pages.

Can I execute JavaScript to interact with dynamic web pages?

Yes, you can execute arbitrary JavaScript within the managed Chrome session to interact with dynamic web pages. This allows you to trigger client-side scripts, manipulate the DOM directly, and handle dynamic content rendering.

Do I need a specific browser to automate web page navigation?

Yes, web page automation requires a Chrome or Chromium instance with Chrome DevTools Protocol support. The Skill leverages this protocol to manage sessions, submit forms, and read the Document Object Model.

What is the best way to capture visual content from a web page?

The best way to capture visual content is by taking a screenshot within the Chrome automation session. The Skill captures the visual state of the web page and returns it as a base64 PNG string for immediate use.

How do I fill out and submit web forms automatically?

Fill out and submit web forms automatically by navigating to the target URL and interacting with the page elements. The Skill clicks buttons, inputs text into form fields, and triggers submissions through the Chrome DevTools Protocol.

Why use Chrome DevTools Protocol for DOM interaction instead of other methods?

Using the Chrome DevTools Protocol for DOM interaction provides direct control over a live browser environment. This ensures accurate element reading, JavaScript execution, and form submissions for web applications requiring full user input simulation.