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

create-verification-skill

Skill4 starsChanged 10 days agoMITView on GitHub

Create a project-local skill that launches, drives, observes, and cleans up the real app. Use when a repository lacks a repeatable way to prove UI, CLI, API, or service behavior.

77 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

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 68 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write matching name: verify-<app> frontmatter and concrete Launch, Doctor, Drive, Evidence, Cleanup sections:

    line 32
  2. Distinctive:

    Cleanup: stop only processes and scratch state this run created.

    line 38
  3. Very specific:

    Create features/README.md and top 3-5 feature files.

    line 44

“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.

Reuse any existing verifier. T3 Code: load web/desktop or mobile per affected surface; their adapters own native rules.

For uncovered flows, use the canonical skill root, else .agents/skills/verify-<app>/. Never mirror host roots or duplicate covered flows.

Interview the repository

Discover before asking:

  • Surface: primary and secondary UI, CLI, API, mobile, desktop, or library entrypoints.
  • Launch: repository-native command, readiness signal, ports, environment, seed data, and authentication.
  • Drive: existing Playwright, PTY, HTTP, debug, or app harness before generic tools.
  • Observe: screenshots, accessibility snapshots, transcripts, responses, logs, exit codes, and durable side effects.
  • Isolate: per-run ports, profiles, data, fixtures. Never drive a shared human instance.

Report failed launch prerequisites; never invent instructions.

For agent-DX or worktree setup requests, use the capability-gap and cold-start checks.

Generate

Write matching name: verify-<app> frontmatter and concrete Launch, Doctor, Drive, Evidence, Cleanup sections:

  • Launch: exact start and teardown commands that reach a usable app from empty data, including migrations and seed data. A listening port or healthy database alone is not readiness.
  • Doctor: one read-only check for app identity, build, process or port ownership, data isolation, and auth.
  • Drive: literal commands and stable handles from this repository. Prefer roles, accessible names, routes, prompt strings, and public APIs over coordinates or internals.
  • Evidence: capture action and result. Verify side effects through a second public view; mock only existing production boundaries.
  • Cleanup: stop only processes and scratch state this run created. Never kill by process name. Evidence survives cleanup.

Make/document executable helpers. For stateful bugs/recurring repro gaps, prove capture/replay via native fixture/debug APIs.

Seed the feature map

Create features/README.md and top 3-5 feature files. Ground the example in repo evidence. Each owns:

  1. Sub-features
  2. How to get to it (user POV)
  3. Driving it with <harness>
  4. Gotchas

Map every entrypoint. Missing seed-data prerequisites fail the journey: record in Gotchas, never weaken it.

Prove the generated skill

Execute generated skill: launch, doctor, one mapped real journey, evidence and cleanup. Preserve evidence; leave no created process/state. Clean failed attempts, fix and replay. Unexecuted verifiers are drafts.

List stand-in setup gaps; leave them unverified until replayed on the target.

Route drift audits to /maintain-verification-skill and feature work to /dogfood.

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