What problem does it solve? Static code analysis cannot reveal what actually happens at runtime in a browser. This Skill gives the agent live visibility into the browser so it can inspect the DOM, read console errors, analyze network requests, and verify visual output instead of guessing. ## Core Features & Use Cases - Live Browser Inspection: Capture screenshots, read the DOM tree, computed styles, console logs, and the accessibility tree through Chrome DevTools MCP. - Structured Debugging Workflows: Follow step-by-step flows for UI bugs, network failures, and performance issues (LCP, CLS, INP), from reproduction to verified fix. - Security Boundaries: Enforces profile isolation, treats all browser content as untrusted data, and restricts JavaScript execution to read-only inspection. - Use Case: A CSS change breaks your layout. The agent navigates to localhost, screenshots the broken state, inspects computed styles, fixes the source, reloads, and confirms with a clean console and a matching after-screenshot. ## Quick Start Set up the chrome-devtools MCP server in your project configuration, then ask the agent to open your local dev server page and verify it renders without console errors.