chrome-devtools

Debug and automate web page interactions using Chrome DevTools via MCP.

2|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/pure-golang/level85 --skill chrome-devtools-pure-golang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chrome-devtools
Source: https://github.com/pure-golang/level85/tree/main/.agents/skills/chrome-devtools
Command: npx skills add https://github.com/pure-golang/level85 --skill chrome-devtools-pure-golang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of slow, manual debugging of web pages by enabling efficient inspection of DOM state, network behavior, and performance details through Chrome DevTools.

Core Features & Use Cases

  • Browser automation via MCP: Automates browser interactions by driving Chrome DevTools through an MCP server with a persistent profile.
  • Reliable page-state workflow: Uses a structured sequence (navigate/new page → wait → take snapshot → interact using element uids) to handle dynamic pages.
  • Actionable diagnostics: Supports both text-based structural inspection and visual verification for troubleshooting and web automation.

Quick Start

Use the chrome-devtools skill to navigate to a page, take a snapshot, then click or fill elements using their snapshot uids to reproduce and debug the issue.

Frequently Asked Questions about chrome-devtools

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

FAQPage Schema
How do I debug web UI issues using Chrome DevTools during browser automation?

To debug web UI issues during browser automation, use the chrome-devtools Skill via MCP to navigate pages, take DOM snapshots, and interact with elements using their uids. This structured workflow ensures reliable inspection of dynamic page states and efficient troubleshooting of UI problems.

Can I inspect network requests and DOM snapshots while automating Chrome?

Yes, you can inspect network requests and DOM snapshots while automating Chrome. The Skill drives Chrome DevTools through an MCP server to review network behavior and capture accessibility tree snapshots, enabling actionable diagnostics for web automation workflows.

What is the correct workflow for automating web page interactions with MCP?

The correct workflow for automating web page interactions with MCP involves a structured sequence: navigate to a new page, wait for the page to load, take a snapshot, and then interact with elements using their snapshot uids for precise clicking or filling.

How do I extract web data not visible in the accessibility tree during browser automation?

To extract web data not visible in the accessibility tree during browser automation, use the evaluate_script function. This allows you to run custom JavaScript for data extraction, alongside filePath, pagination, and filtering options for handling complex page content.

Does browser automation with Chrome DevTools require a persistent profile?

Yes, browser automation with Chrome DevTools via MCP uses a persistent profile. This setup enables reliable page-state workflows and consistent session management for troubleshooting UI issues and automating browser tasks efficiently.

Can I analyze web performance and review network behavior through Chrome DevTools?

Yes, you can analyze web performance and review network behavior through Chrome DevTools. The Skill applies Chrome DevTools via MCP to inspect network requests, analyze performance details, and troubleshoot dynamic web pages during automation.