What problem does it solve?
Projects often lack a scripted way to prove that real user-facing behavior works. This Skill interviews the repository, then generates a project-local verification skill (.cursor/skills/verify-<app>/) that launches the app, drives it the way a user would, and captures evidence.
Core Features & Use Cases
- Repo Interview: Identifies the app's surface (web UI, CLI/TUI, API, desktop), launch command, driving harness (Playwright, CDP, tmux/PTY, HTTP), and observable evidence sources directly from the codebase.
- Skill Generation: Writes a complete
SKILL.md with Launch, Doctor, Drive, Evidence, Cleanup, and Helpers sections grounded in real selectors and commands from the repo.
- Feature Map Seeding: Creates a
features/ directory with one file per user-facing feature, following a strict four-section contract (Sub-features, user POV entry points, harness driving steps, Gotchas).
- Self-Proof: Runs the generated skill end to end once — launch, doctor, drive one feature, capture evidence, clean up — before handing it over.
- Use Case: A repo with a web app and CLI has no scripted verification. Run this Skill to produce a
verify-<app> skill that any future agent can execute cold to prove features work.
Quick Start
Ask the agent to create a verification skill for this repository so the app can be launched, driven, and proven with captured evidence.