maintain-verification-skill
Audit a verification skill and its feature map against the live app, and prove the corrections.
How do I install this agent skill?
npx skills add https://github.com/christofferbergj/agent-skills --skill maintain-verification-skillIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill is a maintenance tool for auditing and updating verification feature maps against a live application. It uses agent swarming to analyze source code and executes local harness scripts to verify functionality. The skill follows best practices for environment health and cleanup, and its external references point to well-known development resources.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Invoke /domain-modeling to resolve and read the invoking project's configured artifacts. Read-only investigations and reviews report documentation drift without edits; creation or implementation reconciles accepted model changes through that owner.
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 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 terminalising every bullet.
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 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. 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-skillinstead of inventing a target. Complete when one source-owned target is resolved, or the missing or ambiguous prerequisite is reported. -
Index hygiene. Read the feature map README and glob its sibling files. Fix missing, extra, duplicate, or dead entries. Lightweight; no generated inventory. Complete when the feature index matches its live files.
-
Source wave. Use /swarm for one read-only source reader per feature file, launched within host capacity. Each explains "how does this user-facing feature work?" 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. Complete when each feature has a source report or a named gap.
-
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 for user-facing surfaces missing from the map — require a concrete source path before calling one missing. Complete when the live pass covers all documented and newly discovered features.
-
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 (the skill's Launch section decides, not this one). Exercise every feature at least once, and hold three invariants the whole pass, whatever the failure: (1) never drive an instance you haven't health-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 (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, 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 isverified-unreachableonly 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). Complete when each feature is exercised or its concrete unreachable prerequisite is recorded, fixes are re-driven, and owned runtime residue is cleaned. -
Triage. Wrong or missing user-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). App behavior that's actually broken → product gap; record it for the user, keep it out of this PR. Complete when each correction has evidence and product regressions remain separately reported.
-
Ship or stop. For changed: one draft PR of proven corrections, re-read every changed file first. For clean or blocked: no PR, report the outcome and the coverage honestly. Complete when the draft PR or clean or blocked outcome matches the completed coverage.
Keep concise run notes (features covered, unreachable prerequisites, confirmed drift, outcome) in a scratch location; don't commit them.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/christofferbergj/agent-skills/maintain-verification-skill">View maintain-verification-skill on skillZs</a>