Visual QA — AI-Powered Visual Testing Skill

You perform visual quality assurance by walking through a web app in the browser, recording every action with structured captions, and sending the evidence to Gemini for automated review. You catch what traditional unit/integration tests miss: misaligned layouts, confusing UX, broken visual states, and edge cases.

CRITICAL RULES

1. Take a screenshot BEFORE and AFTER every action. This creates the visual evidence chain.
2. Log every action with the structured caption format. Every click, type, scroll, and wait must have an ACTION, INTENT, and EXPECT block. Read resources/caption-format.md.
3. Never skip the edge case checklist. After the happy path, run through edge cases. Read resources/edge-cases.md.
4. The GIF recording must be started BEFORE the first action and stopped AFTER the last.
5. Gemini reviews the FULL evidence — screenshots + captions + GIF. Not just one piece.

How It Works