agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/maintain-verification-skill/SKILL.md

maintain-verification-skill

Skill4 starsChanged 11 days agoMITView on GitHub

Audit a project-local verifier and feature map against source and live behavior. Use when either may be stale or hiding regressions.

68 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-pstack, ketchup-video and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 25 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 13 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 14 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 19 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 27 projects that use this

  • drafaelSkill

    in-your-own-words

    Restate the user's goals and the problem they are trying to solve to check understanding. Manual invocation only; use when the user explicitly invokes in-your-own-words or requests this understanding check. Do not solve the task or rewrite the assistant's last answer.

    Also in 26 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Live coverage: Run the verifier's doctor, then drive every feature at least once.

    line 19
  2. Distinctive:

    Recover safely: Check replay packets for fixture/schema drift and feature fidelity.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 68 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

For behavior/verifier checks, read Poteto.

Cover each mapped feature in source and live behavior. Return clean, changed or blocked.

Fence

Edit only the verification skill directory: its SKILL.md, feature map, and owned helpers. Never edit product code. A behavior the app no longer provides is documentation drift or a product regression; repair the former and report the latter.

Pass

  1. Locate. Resolve the project-local verifier by capability, not a verify-* prefix. T3 Code's app/mobile skills follow native verification. Use actual launch, readiness, drive, evidence and cleanup instructions. Uncovered flows route to /create-verification-skill. Map each affected surface to its owner; ask only when ownership remains ambiguous.
  2. Reconcile the index. Compare features/README.md with sibling feature files. Remove dead entries and add missing concrete user surfaces found in routes, commands, menus, or public docs.
  3. Source coverage. For every feature, trace current entrypoints, stable handles, prerequisites, and observable outcomes. Record likely drift with source pointers and one live recipe. Inspect sequentially unless the user explicitly authorizes delegation.
  4. Live coverage. Run the verifier's doctor, then drive every feature at least once. Use one isolated long-lived instance for UI/services or a fresh isolated session per short-lived CLI, as the verifier specifies. Capture evidence before cleanup.
  5. Recover safely. Check replay packets for fixture/schema drift and feature fidelity. After a surprising drive, doctor again; when doctor cannot see a wedged state, reset or relaunch. Clean failed-iteration residue without deleting evidence. Re-run every harness repair live.
  6. Triage. Wrong user description is doc drift. Working behavior the harness cannot drive is a harness gap. Broken product behavior is a product gap: report it and leave product code unchanged.
  7. Finish. Tear down what the run created and confirm evidence remains. Re-read changed verifier files. Deliver through the caller's requested endpoint.

Receipt

  • Outcome: clean | changed | blocked.
  • Coverage: each feature with source and live evidence.
  • Corrections: map, instructions, or helper fixes plus replay result.
  • Product gaps: concrete behavior defect and reproduction, not papered over in the verifier.
  • Limits: unreachable prerequisite, route attempted, and remaining risk.

clean requires source and live coverage for every mapped feature. changed requires a successful replay of every correction. blocked names the exact missing prerequisite.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free