agent-browser

Automate web browser navigation, interaction, data extraction, and testing workflows.

9|2|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/kompassdev/kompass --skill agent-browser-kompassdev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/kompassdev/kompass/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/kompassdev/kompass --skill agent-browser-kompassdev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables automated control and testing of web browsers, allowing users to perform complex web interactions, extract data, capture screenshots, and test web apps efficiently without manual effort.

Core Features & Use Cases

  • Web Interaction Automation: Navigate, fill forms, click buttons, and simulate user actions on websites.
  • Data Extraction & Validation: Retrieve text, HTML, or attributes from web elements for analysis or verification.
  • Testing & Monitoring: Take screenshots, PDFs, and record videos for debugging, documentation, or visual regression testing. Automate login and data scraping workflows.

Quick Start

Use the agent-browser to open a website, capture the page structure with refs, then automate filling a login form and verifying the homepage.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web browser navigation and form filling for testing?

Automate web interaction by using Chrome DevTools Protocol to navigate pages, fill forms, and simulate user actions for testing. This approach captures page structure with refs to drive automated login and verification workflows accurately.

Can I extract data and capture screenshots during web scraping workflows?

Data extraction and screenshot capture are supported during web scraping workflows to retrieve text, HTML, or attributes. You can capture screenshots, PDFs, and record videos for debugging, documentation, or visual regression testing.

Does browser automation work with iframe handling and session management?

Browser automation supports iframe handling and integrates with authentication and session management. It facilitates comprehensive control over web browsers using Chrome DevTools Protocol and scripting capabilities for complex interaction scenarios.

What is the best way to run automated testing in headless or headed modes?

Running automated testing in headless or headed modes is configured directly through the browser control settings. This flexibility allows seamless execution of QA, data scraping, and automation scenarios without manual effort.

How do I validate web elements and retrieve HTML attributes for analysis?

Validate web elements and retrieve HTML attributes by scripting extraction workflows that target specific page structures. This enables detailed analysis and verification of web app content captured during automated navigation sessions.

Are there limitations when using Chrome DevTools Protocol for web automation?

Web automation limitations depend on Chrome DevTools Protocol scripting capabilities and target website structures. Complex authentication workflows or dynamic iframe handling may require advanced scripting to ensure reliable data extraction and testing.