Maintain a verification skill

A feature map rots the moment the app changes. This skill is the upkeep loop for a skill generated by create-verification-skill, or for any project-local verification skill with a feature map. The unit of rigor is the feature, not every sentence: cover every feature file from source and exercise every feature live, without turning every bullet into its own terminal command.

Outcomes

Pick one, and say which:

• clean. Every feature got source and live coverage, and nothing is worth shipping. No branch, no PR.
• changed. One PR ships proven doc, harness, or map corrections.
• blocked. Coverage could not finish, or a proven fix could not ship safely. Say exactly what blocked it.

Edit scope

Only edit the verification skill's own directory: its SKILL.md, its features/, and any harness scripts it owns. Never edit product code during a run. A behavior the map describes that the app no longer does is either doc drift, which you fix in the map, or a product regression, which you report rather than paper over in docs.

Pass

0. Locate the target

Find the verification skill to maintain: the project-local skill whose body has launch and drive sections and a feature map. Look wherever this project keeps its skills, for a directory named for verifying the app. With several candidates, ask which one. With none, stop and call the Skill tool for create-verification-skill instead of inventing a target.

1. Index hygiene

Read the feature map README and glob its sibling files. Fix missing, extra, duplicate, or dead entries. Keep this lightweight. No generated inventory.

2. Source wave

Launch one read-only sub-agent per feature file, concurrently. Each one explains how the user-facing feature works from source, flags likely doc drift with citations, and returns one concise live-verification recipe. Children never drive the app and never edit files.

Return shape: feature summary, source entry points, likely drift or none, one recipe.

3. Reconcile

Every feature file has a returned summary. Merge overlapping recipes into as few app states as practical. Spot-check cited drift and do not re-prove clean claims. Sweep recent churn for user-facing surfaces missing from the map, and require a concrete source path before calling one missing.

4. Live pass

Required even when source looks clean. The coordinator owns all driving. Follow the verification skill's own launch model: one long-lived instance driven serially for servers and UIs, or a fresh isolated session per drive for short-lived CLIs. That skill's Launch section decides, not this one.

Exercise every feature at least once, and hold three invariants for the whole pass, whatever the failure:

1. Never drive an instance you have not health-checked since it last did something surprising. Doctor before the first drive, doctor on each fresh session where sessions are the unit, and doctor again after any failed drive. Where doctor cannot see the failure, such as a wedged UI state on a healthy process, reset to a known state or relaunch rather than hoping.
2. Evidence captured so far survives every cleanup. Check it at its named location rather than assuming it.
3. Nothing a drive started outlives that drive's usefulness. Failed-iteration residue is cleaned whether the session is stuck, exited, or shared. For a shared instance, clean the residue and not the instance.

A doctor failure caused by skill drift is drift. Fix it under edit scope and retry once, restarting whatever the fix invalidated and nothing more, before calling the pass blocked.

A feature that cannot be reached is verified-unreachable only with the concrete prerequisite (auth, entitlement, OS, external state) and the route attempted. If the map omits that prerequisite, that is drift.

Any harness fix from triage gets re-driven live before it ships. Final teardown happens after the last drive of the run, including those re-proofs, so nothing outlives the run. Evidence stays, per the skill.

5. Triage

• A wrong or missing user-POV description is doc drift. Fix it.
• Working behavior the harness cannot drive is a harness gap. Fix it. A harness fix follows the same helpers rule as generation: scripts executable, invocation documented in the skill body.
• App behavior that is actually broken is a product gap. Record it for the user and keep it out of this PR.

6. Ship or stop

For changed, open one PR of proven corrections, re-reading every changed file first. For clean or blocked, open no PR and report the outcome and the coverage honestly.

Keep concise run notes in a scratch location, covering features covered, unreachable prerequisites, confirmed drift, and the outcome. Do not commit them.