What problem does it solve? Debugging browser-based UI issues from static code alone is guesswork. This Skill gives the agent live visibility into the browser — DOM, console logs, network requests, and performance traces — so UI bugs, API failures, and rendering problems can be reproduced, diagnosed, and verified against real runtime behavior. ## Core Features & Use Cases - Live Browser Inspection: Capture screenshots, read the DOM and accessibility tree, inspect computed styles, and retrieve console output through the Chrome DevTools MCP server. - Structured Debugging Workflows: Follow step-by-step flows for UI bugs, network issues (4xx/5xx/CORS/timeouts), and performance profiling (LCP, CLS, INP, long tasks). - Security Boundaries: Enforces profile isolation, treats all browser content as untrusted data, and restricts JavaScript execution to read-only inspection to prevent prompt injection and credential exposure. - Use Case: A React dashboard chart fails to render. The agent navigates to the page, captures a screenshot, finds a console error, inspects the failing network request's payload, identifies the root cause, fixes the code, and verifies the fix with a clean console and a before/after screenshot comparison. ## 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 check for console errors and visual issues.