agent-browser

Automate browser navigation, form filling, element inspection, and media capture via Chrome DevTools Protocol.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/del-zhenwu/chaos-agent --skill agent-browser-del-zhenwu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/del-zhenwu/chaos-agent/tree/main/agent-core/.agents/skills/agent-browser
Command: npx skills add https://github.com/del-zhenwu/chaos-agent --skill agent-browser-del-zhenwu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of automating complex web browser interactions, enabling users to navigate, inspect, and manipulate web pages programmatically for testing, data extraction, and UI validation.

Core Features & Use Cases

  • Web automation: Programmatically navigate, interact with, and analyze web pages for testing or data collection.
  • Form filling and submission: Automate filling forms, clicking buttons, and submitting inputs across websites.
  • Screenshot and recording: Capture screenshots, generate PDFs, and record videos of browser sessions to document workflows.
  • Use Case: For QA teams automating regression tests or content specialists extracting data from web portals, this tool simplifies repetitive tasks and enhances productivity.

Quick Start

Use agent-browser to open a webpage, interact with elements via refs, take screenshots, and close the browser session.

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 interactions for UI testing and data extraction?

Automate web interactions by programmatically navigating pages, filling forms, and inspecting elements using Chrome DevTools Protocol. This approach controls browser behavior for web QA, data extraction, and UI testing workflows.

What is the best way to capture screenshots and record browser sessions programmatically?

Capture screenshots, generate PDFs, and record videos of browser sessions programmatically to document workflows. This media capture leverages Chrome DevTools Protocol to control browser behavior and validate UI changes.

Can I use Chrome DevTools Protocol to fill and submit forms automatically?

Yes, you can automate filling forms, clicking buttons, and submitting inputs across websites using Chrome DevTools Protocol. This programmatic manipulation streamlines repetitive web automation tasks for content specialists.

Does this browser automation approach work for QA teams automating regression tests?

Yes, this browser automation approach is specifically suitable for QA teams automating regression tests. It simplifies repetitive web interactions, element inspection, and UI validation workflows programmatically.

How do I inspect web elements via refs during an automated browser session?

Inspect web elements via refs by opening a webpage, interacting with targeted elements, and capturing screenshots before closing the browser session. This programmatic element inspection leverages Chrome DevTools Protocol.