kiranvkulkarni/QA_Intelli-Gen_V3 — reverse-engineered prompt
Reverse engineered prompt
Build me a Python tool that can turn smartphone app requirement screens into Gherkin test cases. I want it to work best when it can pull frames straight from Figma using an API token, but it should also accept locally exported images if Figma is not set up. The goal is to understand screen flows, navigation, default states, selections, previews, capture behavior, restrictions, toast messages, and persistence, then write clean feature files for each app.
Please make it feel mostly automatic. I want an inbox style flow where it can scan incoming app folders, process them, move finished inputs to a processed area, and write the latest feature files to an output folder. A watch mode would be great too.
Also include an optional QA review flow where scenarios can be approved, rejected, or corrected, and keep those decisions saved. I also want version comparison so I can see what scenarios were added, removed, or changed between requirement updates.
Use the README as the source of truth, and look up current docs online if you need to.
Want more depth? Deep Reverse