Maintain a verification skill

A feature map drifts as the framework, language and toolchain change. This skill is the upkeep loop for a skill generated by /create-verification-skill (or 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 through its actual compiler, library, CLI or runtime entrypoint, without turning every bullet into a separate proof obligation.

When a mapped feature uses shared test, regression, consumer or benchmark tooling, follow that owning skill's entrypoint and keep one copy of the helper. Use Validate skills after changing metadata, resource paths or cross-skill links.

Outcomes

Pick one, and say which:

• clean — every feature got source and live coverage; nothing 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, features/, and any harness scripts it owns). Never edit framework or toolchain implementation during a run: a behavior the map describes that the target no longer provides is either doc drift (fix the map) or a product regression (report it, don't paper over it in docs).

Pass

0. Locate the target. Find the verification skill to maintain: the project-local skill whose body has launch/drive sections and a feature map (usually .agents/skills/verify-*/). Several candidates → ask which one; none → stop and point at /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. Lightweight; no generated inventory.

2. Source wave. One read-only delegated source reviewer per feature file, following AGENTS.md. Launch concurrently where capacity permits; otherwise batch without dropping any feature or its summary. Each explains "how does this caller-visible framework or language contract work?" from source, flags likely doc drift with citations, and returns one concise live-verification recipe. Children never execute verification drives 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 compatible fixture/runtime states as practical. Spot-check cited drift; don't re-prove clean claims. Sweep recent churn for caller-visible framework, language or toolchain surfaces missing from the map — 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 Launch procedure — actual consumer/compiler fixture work for compile-time claims, demanded or executed library/decision/Task behavior for runtime claims, one long-lived instance driven serially for servers, or a fresh isolated session per drive for short-lived CLIs. The target skill decides the procedure. For an indirect-interaction feature, observe every specified downstream outcome; originating acceptance, query readiness or one projection cannot substitute for another required result. Exercise every feature at least once, and hold three invariants the whole pass, whatever the failure: (1) never drive a target whose prerequisites you haven't checked since it last did something surprising — doctor before first drive, doctor on each fresh session where sessions are the unit, doctor again after any failed drive, and where doctor can't see the failure (stalled fixture or projection state behind an otherwise healthy process), reset to a known state or relaunch rather than hoping; (2) evidence captured so far survives every cleanup, checked at its named location, not assumed; (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, not the instance). A doctor failure caused by skill drift is drift: fix it under edit scope and retry once — restart whatever the fix invalidated, nothing more — before calling the pass blocked. A feature that can't 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's 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. Wrong or missing developer/caller-POV description → doc drift, fix it. Working behavior the harness can't drive → harness gap, fix it; a harness fix follows the same helpers rule as generation (scripts executable, invocation documented in the skill body). Framework or toolchain behavior that's actually broken → product gap; record it for the user, keep it out of this PR.

6. Ship or stop. For changed: one PR of proven corrections, re-read every changed file first. For clean or blocked: no PR, report the outcome and the coverage honestly.

Keep concise run notes (features covered, unreachable prerequisites, confirmed drift, outcome) under .agents-state; don't commit them. Retain proof artifacts separately from scratch state, following the target verification skill.