agentleFS
Sign inStart free
afaraha8403afaraha8403/balakit/.agents/skills/generating-app-verify/SKILL.md

generating-app-verify

Skill1 starsChanged 10 days agoMITView on GitHub

Generate a project-local verification skill that drives the real app the way a user does — web, CLI, API, or desktop. Apply when the user invokes /generating-app-verify, asks for a control or verify skill, or the project has no scripted way to prove behavior. Use refreshing-app-verify to keep the feature map honest. Use testing.mdc for when to write tests.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Every serious project needs a way to launch the app, exercise a feature as a user would, and keep evidence.

    line 28
  2. Very specific:

    Write skills/verify-<app>/SKILL.md with Launch, Doctor, Drive, Evidence, Cleanup, Helpers.

    line 35
  3. Distinctive:

    Run launch → doctor → drive one mapped feature → evidence still exists after cleanup.

    line 37
  4. Distinctive:

    If the checkout does not start, fix that first (or report it).

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Generate an app verify skill

Leading words: interview the repo, drive like a user, feature map, prove one feature, skills/verify-app.

Every serious project needs a way to launch the app, exercise a feature as a user would, and keep evidence. This skill writes that as skills/verify-<app>/ (Agent Skills path — not .cursor/ only).

Copy these steps into the todo list verbatim. Skip with skip: <reason>.

  1. Interview the repo (surface, run, drive, observe, isolate). Ask the user only what you cannot observe.
  2. Write skills/verify-<app>/SKILL.md with Launch, Doctor, Drive, Evidence, Cleanup, Helpers. Helpers live under helpers/ (not scripts/). A Launch helper is required even when the app is a one-shot CLI (ready signal = usage line + exit).
  3. Seed a feature map (features/README.md + 3–5 user-POV feature files).
  4. Run launch → doctor → drive one mapped feature → evidence still exists after cleanup.
  5. Point at /refreshing-app-verify.

If the checkout does not start, fix that first (or report it). A skill written against a broken base teaches the wrong steps.

Interview

  • Surface: web UI, CLI/TUI, desktop, API, mobile? Pick the primary.
  • Run: the repo's own documented dev command. Ports, env, seed, auth.
  • Drive: existing harness first (Playwright, expect, curl). Then browser/CDP, PTY, or HTTP.
  • Observe: screenshots, transcripts, bodies, logs, exit codes, DB.
  • Isolate: can two instances run? If not, say so — refuse to double-drive a shared session.

Generated skill

Frontmatter: name: verify-<app> and a description that names the app and surface. Sections with no placeholders:

  • Launch — exact command, ready signal, teardown.
  • Doctor — read-only "is this instance worth driving?"
  • Drive — real selectors/commands from this repo. ARIA, data attributes, prompt strings, routes — not coordinates.
  • Evidence — what to capture and where. Real user path, not internal setters. Side effects counted. Mocks only at a production boundary.
  • Cleanup — kill what you started. Evidence survives.
  • Helpers — executable; invocation shown in the body.

Feature files use four H2s: Sub-features / How to get to it (user POV) / Driving it with the harness / Gotchas. Shape: references/feature-map.md.

Reply contract

Paths written, which feature you proved, where the evidence lives, and that cleanup left the evidence in place.

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