Browser Testing with DevTools shows an agent how to use the Chrome DevTools MCP server to see what a page does at runtime. It covers screenshots, DOM and style inspection, console logs, network requests, accessibility tree reads and performance traces.
The skill sets security boundaries around that access: an isolated browser profile, browser content treated as untrusted data and read-only JavaScript execution.
What You Get
- An MCP configuration snippet for chrome-devtools-mcp
- A table of DevTools capabilities and when to use each
- Debugging workflows for UI bugs, network issues and performance
- Security rules for profile isolation, untrusted content and JavaScript execution
Common Use Cases
- Verifying a UI change in a real browser
- Diagnosing console errors and failed requests
- Profiling Core Web Vitals before and after a fix
- Checking the accessibility tree and focus order
What Makes It Unique
Most of the skill’s length goes to safety. It tells the agent to default to a dedicated or temporary browser profile, to treat DOM text, console output and network responses as data and never as instructions, and to keep JavaScript execution read-only and free of credential access.
Under The Hood
The skill is a single SKILL.md of instructions. It asks you to add an npx command to your MCP configuration that downloads and runs chrome-devtools-mcp, which launches Chrome and exposes its pages to the agent. The agent then uses the server’s tools and reaches local dev servers and whatever pages it is pointed at. The skill ships no scripts of its own.