Use this skill after making UI changes to visually verify the result, catch console errors, and audit network requests — all without leaving Cursor.
Cursor has a built-in browser (
MCP) that can navigate to URLs, take screenshots, read console messages, inspect network requests, and interact with page elements. This skill uses those tools to do a quick visual QA pass.
-
Ensure the dev server is running — check if there's already a terminal running the dev server. If not, start one in the background:
Wait for the server to be ready (watch for the "ready" or localhost URL in the output).
-
Navigate to the page — use
to open the relevant page:
Tool: browser_navigate
Arguments: { "url": "http://localhost:3000", "take_screenshot_afterwards": true }
If the change is on a specific route, navigate directly to it (e.g.,
,
).
-
Take a screenshot — capture the current state:
Tool: browser_take_screenshot
Arguments: { "fullPage": true }
Review the screenshot for visual issues: layout breaks, missing content, wrong colors, misaligned elements.
-
Check console for errors — look for JavaScript errors or warnings:
Tool: browser_console_messages
Report any errors, especially
,
, failed imports, or React hydration mismatches.
-
Audit network requests — check for failed API calls or unexpected requests:
Tool: browser_network_requests
Look for: 4xx/5xx status codes, CORS errors, excessively large responses, unnecessary duplicate requests.
-
Interact if needed — if the change involves interactive elements (buttons, forms, modals), use
,
, or
to test the interaction, then take another screenshot to verify.
-
Report findings — summarize:
- Screenshot shows the UI looks correct (or what's wrong)
- Console is clean (or list errors found)
- Network requests are healthy (or list failures)