agentleFS
witi-projectswiti-projects/Skills/visual-qa-testing/SKILL.md

visual-qa-testing

Skill2 starsChanged 7 months agoMITView on GitHub

Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct. Use when the user says "/visual-qa-testing", "visual qa testing", or asks about visual qa testing.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill after making UI changes to visually verify the result, catch console errors, and audit network requests — all without …

    line 8
  2. Distinctive:

    Wait for the server to be ready (watch for the "ready" or localhost URL in the output).

    line 22
  3. Very specific:

    If the change is on a specific route, navigate directly to it (e.g., /settings, /dashboard).

    line 31
  4. Distinctive:

    Look for: 4xx/5xx status codes, CORS errors, excessively large responses, unnecessary duplicate requests.

    line 56
  5. Very specific:

    Always use browser_snapshot before clicking elements to get the correct element refs.

    line 67
  6. Very specific:

    Use browser_navigate with position: "side" to open the browser beside your code.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Visual QA

Use this skill after making UI changes to visually verify the result, catch console errors, and audit network requests — all without leaving Cursor.

How It Works

Cursor has a built-in browser (cursor-ide-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.

Steps

  1. Ensure the dev server is running — check if there's already a terminal running the dev server. If not, start one in the background:

    npm run dev

    Wait for the server to be ready (watch for the "ready" or localhost URL in the output).

  2. Navigate to the page — use browser_navigate 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., /settings, /dashboard).

  3. 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.

  4. Check console for errors — look for JavaScript errors or warnings:

    Tool: browser_console_messages

    Report any errors, especially TypeError, ReferenceError, failed imports, or React hydration mismatches.

  5. 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.

  6. Interact if needed — if the change involves interactive elements (buttons, forms, modals), use browser_click, browser_fill, or browser_hover to test the interaction, then take another screenshot to verify.
  7. 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)

Notes

  • Always use browser_snapshot before clicking elements to get the correct element refs.
  • For responsive testing, use browser_resize to check different viewport sizes.
  • Use browser_navigate with position: "side" to open the browser beside your code.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.