browser-testing-with-devtools

Capture DOM state, console output, network activity, and performance data via Chrome DevTools MCP.

3|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/vtgiang-dotcom/Solo-Code-Harness --skill browser-testing-with-devtools-vtgiang-dotcom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-testing-with-devtools
Source: https://github.com/vtgiang-dotcom/Solo-Code-Harness/tree/main/.gemini/antigravity/skills/browser-testing-with-devtools
Command: npx skills add https://github.com/vtgiang-dotcom/Solo-Code-Harness --skill browser-testing-with-devtools-vtgiang-dotcom

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Chrome-based UI testing can be flaky and hard to reproduce without live browser data; this skill enables agents to observe actual rendering, DOM state, console output, network activity, and performance in real browsers via the Chrome DevTools MCP server.

Core Features & Use Cases

  • Observe live DOM structure and render timing to diagnose UI issues.
  • Capture console output, network activity, and performance metrics from real browsers.
  • Use cases include UI debugging, performance profiling, visual validation, and accessibility checks using real runtime data.

Quick Start

Connect to a running Chrome instance via the Chrome DevTools MCP and begin inspecting a loaded page.

Frequently Asked Questions about browser-testing-with-devtools

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

FAQPage Schema
How do I capture DOM state and console output for UI debugging?

To capture DOM state and console output for UI debugging, connect to a running Chrome instance via the Chrome DevTools MCP server to observe live rendering and inspect page elements. This allows agents to diagnose UI issues using real runtime data.

How does browser performance profiling work with DevTools?

Browser performance profiling with DevTools works by connecting to Chrome DevTools MCP to capture network activity and render timing metrics. This enables agents to observe live browser behavior and gather actual performance data from real browsers during development.

What is the best way to automate visual verification in real browsers?

The best way to automate visual verification in real browsers is by using the Chrome DevTools MCP server to observe live DOM structure. This approach captures actual rendering output, ensuring accurate visual validation of UI components without relying on mocked environments.

Do I need a configured Chrome DevTools MCP server to inspect a loaded page?

Yes, you need a configured Chrome DevTools MCP server to inspect a loaded page. The skill requires this active connection to observe live browser behavior safely and capture runtime data like network activity and DOM state without executing untrusted instructions.

Why does Chrome-based UI testing become flaky and hard to reproduce?

Chrome-based UI testing becomes flaky and hard to reproduce without live browser data. By connecting to the Chrome DevTools MCP, agents can observe actual rendering, console output, and network activity to accurately diagnose and replicate UI issues in real time.

Can I use this approach for accessibility checks using real runtime data?

Yes, you can use this approach for accessibility checks using real runtime data. By capturing the live DOM structure and console output via Chrome DevTools MCP, agents can evaluate UI components against accessibility standards within actual development or QA contexts.