E2E Verify

Core Principle: Visual Verification is Non-Negotiable

Every screenshot you take MUST be read and visually inspected. Taking a screenshot without reading it is useless. The entire point of E2E testing is to verify what the USER sees, not just what the DOM contains.

After every mcp__chrome-devtools-mcp__take_screenshot, you MUST:

1. Read the screenshot using your multimodal vision capabilities
2. Compare it to the spec — read the issue/PR description and verify the screenshot matches what was requested
3. Describe what you see — document the visual state in your results (layout, content, styling, errors)
4. Flag discrepancies — if what you see doesn't match the spec, report it as a finding

DOM checks (console errors, network requests) supplement visual verification — they do NOT replace it. A page can have zero console errors and zero network failures but still look completely wrong.

Parse Arguments