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

maintain-verification-skill

Skill2 starsChanged 17 days agoMITView on GitHub

Keep a project's verification skill and feature map honest. Use when the user asks to maintain, audit, or update the verify skill, or when that map may have drifted from the app. Cover every feature from source and with one live drive. Edit only that skill directory.

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 9 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

  • TheOnlyFusionCubeSkill

    maintain-formal-verification-skill

    Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.

    Also in 19 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 3

    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:

    clean: Every feature got source and live coverage, and nothing needs shipping.

    line 18
  2. Distinctive:

    Index: Read the feature index and its sibling feature files.

    line 30
  3. Distinctive:

    Keep run notes in a scratch file.

    line 56

“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

Maintain a verification skill

A feature map rots when the app changes. Cover every feature file from source and exercise every feature live. The file shape and proof standards are the feature-map contract.

Outcomes

End on one, and say which:

  • clean. Every feature got source and live coverage, and nothing needs shipping.
  • changed. One set of proven corrections to the verification skill.
  • blocked. Coverage could not finish, or a proven fix could not be applied safely. Name the blocker.

Edit scope

Edit only the verification skill directory: its SKILL.md, features/, and harness scripts it owns. When the app no longer does what the map says, fix the map if the map is wrong. Report a product regression and leave the product code unchanged.

Pass

  1. Locate. Find the project verification skill: launch and drive sections, plus a feature map. Several candidates: ask which one. None: stop and load create-verification-skill.
  2. Index. Read the feature index and its sibling feature files. Fix missing, extra, duplicate, or dead entries. Done when the index and the files name the same set.
  3. Source wave. Launch one read-only subagent per feature file, together. Each returns a feature summary, the source entry points, likely drift with citations or none, and one live recipe. Children do not drive the app and do not edit files. Done when every feature file has a summary.
  4. Reconcile. Merge overlapping recipes into as few app states as practical. Spot-check cited drift. Add a missing user-facing surface only when you can name its source path.

  5. Live pass. Drive even when the source looks clean. Follow that skill's Launch section: one long-lived instance driven in series, or a fresh isolated session per drive for a short-lived CLI.

    For terminal drives, use the terminal lifecycle contract. Reclassify mistaken finite-CLI assumptions as verifier defects. Invalidate normal-exit evidence that required user cancellation or leaked owned windows.

    Hold these for the whole pass:

    • Doctor before the first drive, on each fresh session, and after any failed drive. When doctor cannot see a wedged UI on a healthy process, reset or relaunch.
    • Evidence captured so far is still at its named path after every cleanup. Check the path.
    • Clean residue a drive started when that drive is done. On a shared instance, clean the residue and leave the instance.

    A doctor failure caused by the skill is drift: fix it inside the edit scope and retry once. Restart only what that fix invalidated. A feature you cannot reach is verified-unreachable when you name the prerequisite and the route you tried. A prerequisite the map omits is drift. Re-drive a harness fix before it counts.

    Tear down after the last drive, including those re-proofs. Evidence stays.

  6. Triage. A wrong user-facing description is a map fix. Behavior the harness cannot drive is a harness fix: the script is executable and the skill body shows the command. Broken app behavior is a note for the user, outside this change.
  7. Ship or stop. For changed, re-read every changed file first. The change is the verification skill only. Open a pull request only when the user asked. For clean or blocked, leave the branch alone. Report the coverage.

Keep run notes in a scratch file. Leave them uncommitted.

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