What problem does it solve? Green tests do not prove a feature actually works, and a model reviewing its own code shares its own blind spots. This skill closes both gaps before merge: it drives the real application to prove behavior against the spec, and it runs a senior code review on a different model than wrote the code. ## Core Features & Use Cases - Runtime verification: The verify mode launches the real app, exercises the changed flow (UI, API, CLI, or job), and checks every acceptance criterion and specced surface, with an evidence ledger so no verdict is fabricated. - Cross-model code review: The review mode spawns a reviewer subagent on a contrasting model, ranks findings by severity (blocker, major, minor, nit), and writes them to docs/reviews/. - Use Case: After finishing a feature with /develop, run verify to confirm every acceptance criterion is met in the running app, then run review before opening the PR to get a fresh-model senior read of the diff. ## Quick Start Ask the assistant to run the check skill in verify mode on the current branch to prove the change works against its spec before merging.
