Maintain a verification skill
A feature map rots the moment the app changes. This is the upkeep loop for a skill generated by /skill: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 live.
Outcomes
Pick one and say which:
- clean: every feature got source and live coverage; nothing worth changing.
- changed: one change set of 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 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 (fix the map) or a product regression (report it; don't paper over it in docs).
Pass
Locate the target. Glob .omp/skills/verify-*/SKILL.md, .claude/skills/verify-*/SKILL.md, and .agents/skills/verify-*/SKILL.md from the repo root (omp, Claude Code, and Codex and most other harnesses read those folders). Several candidates → pick the one whose app the change touches, and log why. None → stop and point at the create-verification-skill skill instead of inventing a target.
Index hygiene. Read features/README.md and glob its sibling files. Fix missing, extra, duplicate, or dead entries.
Source wave. One read-only scout task per feature file, in a single task batch. Each explains "how does this user-facing feature work?" from source, flags likely doc drift with file:line 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.
Reconcile. Every feature file has a returned summary. Merge overlapping recipes into as few app states as practical. Spot-check cited drift; don't re-prove clean claims. Sweep recent churn (git log --since) for user-facing surfaces missing from the map; require a concrete source path before calling one missing.
Live pass. Required even when source looks clean. You (the coordinator) own all driving. Follow the 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. Exercise every feature at least once. Hold three invariants whatever fails:
- Never drive an instance you haven't doctored since it last did something surprising: doctor before the first drive, on each fresh session, and after any failed drive. Where doctor can't see the failure (a wedged UI on a healthy process), reset or relaunch rather than hoping.
- Evidence captured so far survives every cleanup, checked at its named location, not assumed.
- Nothing a drive started outlives its usefulness. 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, restarting only what the fix invalidated, before calling the pass blocked. A feature 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. Re-drive every harness fix live before it ships. Final teardown happens after the last drive, re-proofs included; evidence stays.
Triage.
- Wrong or missing user-POV description → doc drift; fix it.
- Working behavior the harness can't drive → harness gap; fix it (scripts executable, invocation documented in the skill body).
- App behavior that's actually broken → product gap; record it for the user, keep it out of this change.
Ship or stop. For changed: re-read every changed file, then present one change set. Commit it and open a PR per deepmodebot's Opening a PR playbook (skill://deepmodebot/references/playbooks/opening-a-pr.md). For clean or blocked: no changes; report the outcome and coverage honestly.
Keep run notes (features covered, unreachable prerequisites, confirmed drift, outcome) in a scratch location; don't commit them.
1---2name: maintain-verification-skill3description: "Periodic pass that keeps a project's verify-<app> skill and feature map honest: parallel read-only source readers per feature, one live session driving every feature, at most one change set of proven corrections. Use for /skill:maintain-verification-skill or \"audit the verify skill\"."4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/timothyvang/maintain-verification-skill7---89# Maintain a verification skill1011A feature map rots the moment the app changes. This is the upkeep loop for a skill generated by `/skill: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 live.1213## Outcomes1415Pick one and say which:1617- **clean**: every feature got source and live coverage; nothing worth changing.18- **changed**: one change set of proven doc, harness, or map corrections.19- **blocked**: coverage could not finish, or a proven fix could not ship safely. Say exactly what blocked it.2021## Edit scope2223Only edit the verification skill's own directory (its `SKILL.md`, `features/`, and 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 (fix the map) or a product regression (report it; don't paper over it in docs).2425## Pass26270. **Locate the target.** Glob `.omp/skills/verify-*/SKILL.md`, `.claude/skills/verify-*/SKILL.md`, and `.agents/skills/verify-*/SKILL.md` from the repo root (omp, Claude Code, and Codex and most other harnesses read those folders). Several candidates → pick the one whose app the change touches, and log why. None → stop and point at the **create-verification-skill** skill instead of inventing a target.28291. **Index hygiene.** Read `features/README.md` and glob its sibling files. Fix missing, extra, duplicate, or dead entries.30312. **Source wave.** One read-only `scout` task per feature file, in a single `task` batch. Each explains "how does this user-facing feature work?" from source, flags likely doc drift with file:line 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.32333. **Reconcile.** Every feature file has a returned summary. Merge overlapping recipes into as few app states as practical. Spot-check cited drift; don't re-prove clean claims. Sweep recent churn (`git log --since`) for user-facing surfaces missing from the map; require a concrete source path before calling one missing.34354. **Live pass.** Required even when source looks clean. You (the coordinator) own all driving. Follow the 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. Exercise every feature at least once. Hold three invariants whatever fails:36 - Never drive an instance you haven't doctored since it last did something surprising: doctor before the first drive, on each fresh session, and after any failed drive. Where doctor can't see the failure (a wedged UI on a healthy process), reset or relaunch rather than hoping.37 - Evidence captured so far survives every cleanup, checked at its named location, not assumed.38 - Nothing a drive started outlives its usefulness. For a shared instance, clean the residue, not the instance.3940 A doctor failure caused by skill drift is drift: fix it under edit scope and retry once, restarting only what the fix invalidated, before calling the pass `blocked`. A feature 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. Re-drive every harness fix live before it ships. Final teardown happens after the last drive, re-proofs included; evidence stays.41425. **Triage.**43 - Wrong or missing user-POV description → doc drift; fix it.44 - Working behavior the harness can't drive → harness gap; fix it (scripts executable, invocation documented in the skill body).45 - App behavior that's actually broken → product gap; record it for the user, keep it out of this change.46476. **Ship or stop.** For **changed**: re-read every changed file, then present one change set. Commit it and open a PR per deepmodebot's Opening a PR playbook (`skill://deepmodebot/references/playbooks/opening-a-pr.md`). For **clean** or **blocked**: no changes; report the outcome and coverage honestly.4849Keep run notes (features covered, unreachable prerequisites, confirmed drift, outcome) in a scratch location; don't commit them.