create-verification-skilllisted

# Create a verification skill Every serious project needs a scripted way to drive the real app and prove behavior: launch it, exercise a feature the way a user would, and capture evidence. This skill generates two coupled artifacts: 1. **`.claude/verify.sh`** — a fast, always-on gate wired to the `Stop` hook. It runs automatically every time an agent tries to finish in this repo and blocks it if the repo is broken. This is the piece that turns "I verified it" from a claim into a mechanism. 2. **`.claude/skills/verify-<app>/`** — the deep, human-and-agent-readable skill that drives the real app, plus a feature map. `verify.sh` is the cheap gate that runs constantly; the skill is the expensive drive you invoke deliberately. Both, or neither is worth much: a gate with no drive only proves the code compiles, and a drive nothing invokes never runs. You write the output for the next agent, not for a human: it will be read cold, mid-task, by an agent that has never seen the app. ## 1. Interview the repo, not the user Answer these from the codebase and only ask the user what you cannot observe. **Fan this out — send all of these as multiple `Agent` tool calls in a single message** so they run concurrently, not one after another: - **Surface:** what does a user actually touch? A web UI, a CLI/TUI, a desktop app, an API, a library? A repo can have several; pick the primary one and note the rest. - **Run:** how does the app start locally? Prefer the repo's own documented dev comm