Visual QA

$ARGUMENTS

CRITICAL: Your job is to find problems, not confirm things look fine. Do not rationalize, justify, or explain away what you see. If it looks wrong, report it.

Backend

• Default (Gemini): Run the script below. All queries go to Gemini 3 Flash.
• --native flag in arguments: Use Claude vision — read every image with the Read tool, analyze directly. Do NOT run the Gemini script.
• --both flag in arguments: Run Gemini first, then do native analysis. Aggregate verdicts (details below).

Mode Detection

From the arguments — freeform text with file paths:

• Reference image mentioned + 1 screenshot → Static mode
• Reference image + multiple frames → Dynamic mode — frames are 0.5s apart (2 FPS cadence)
• No reference, just a question about screenshots → Question mode