Skip to content
Skills Library
Programming · Testing

create-verification-skill

/create-verification-skill

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.

Repository
pstack ↗
Licence
MIT
Last repository change
21.09.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 21.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.

Triggers from the description

make a control skill for this repo\
Original author description

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.

How it works

  1. 1. Interview the repo, not the user
  2. 2. Generate the skill
  3. 3. Seed the feature map
  4. 4. Prove the generated skill before handing it over
  5. 5. Offer the maintenance loop
Original SKILL.md headings · 43 lines, 1,050 words
SKILL.md preview
---
name: create-verification-skill
description: "Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior."
disable-model-invocation: true
---

# Create a verification skill

Before delegating, read [the harness instructions](../../harness/README.md) and the active harness file. Map agent names, tool arguments, and model roles there.

Every serious project needs a scripted way to drive the real app and prove behavior: launch it, exercise a feature the way a user would, and capture evidence. This skill generates that as a project-local skill, at whatever path the active harness uses for one (`harness/<detected>.md` names it), tailored to the repo. You write the generator's output for the next agent, not for a human: it will be read cold, mid-task, by an agent that has never seen the app.

## 1. Interview the repo, not the user

Answer these from the codebase and only ask the user what you cannot observe:

- **Surface:** what does a user actually touch? A web UI, a CLI/TUI, a desktop app, an API, a mobile app, a library? A repo can have several; pick the primary one and note the rest.
- **Run:** how does the app start locally? Prefer the repo's own documented dev command (package scripts, Makefile, README quickstart). Note ports, env vars, seed data, auth.
- **Drive:** for websites and Electron web renderers, read [browse-web](../browse-web/SKILL.md) and generate live interaction instructions for its selected driver. Reuse existing launch, fixture, and scenario knowledge; keep Playwright/Cypress and other automated suites as regression gates. For other surfaces, prefer existing expect scripts, PTY helpers, or HTTP endpoints; otherwise use a tmux/PTY harness for CLI/TUI and plain HTTP for services.
- **Observe:** what evidence can be captured? Screenshots, terminal transcripts, response bodies, logs, exit codes, DB state.
- **Isolate:** can two instances run side by side (ports, data dirs, profiles)? If not, say so in the generated skill: refusing to double-drive a shared instance beats corrupting the user's session.

If the checkout doesn't build or start as-is, fix that first (or report it precisely) before generating; a skill written against a broken base teaches wrong steps. When an irrelevant missing asset blocks startup (a static dir the API never serves, a sample config), the generated skill may create it, clearly marked as verification scaffolding, and remove it in cleanup.

## 2. Generate the skill

Write the generated skill to the active harness's project-local skill path (`harness/<detected>.md` names it; on Claude Code that is `.claude/skills/verify-<app>/SKILL.md`) with YAML frontmatter (`name: verify-<app>` and a `description` that names the app, the surface, and when to reach for it — without frontmatter the skill never registers) and these sections, each grounded in what the interview actually found (no placeholders left):

- **Launch:** the exact command that starts the app for verification, and how to tell it's ready (a log line, a port answering, a prompt). Include teardown. For a short-lived CLI or TUI there is no server to keep alive: launch means build the binary (or install deps) once, then start each drive in its own isolated PTY or tmux session.
- **Browser setup:** for web surfaces, name the selected driver and its prerequisites. For Computer Use, instruct the reader to discover and read the installed skill, check its runtime, identify the target app/URL, refresh app state after actions, inspect screenshots, and serialize access to the shared desktop. Do not hardcode a plugin cache path. For `agent-browser`, include a unique named session on every command, snapshot/semantic interactions, screenshot inspection, and session cleanup. Include concrete app-specific actions and evidence steps so the recipe remains usable without pstack installed.
- **Doctor:** one read-only check that answers "is this instance worth driving?" — process up, right version/build, port owned by us, auth valid. An agent runs this first whenever anything looks off.
- **Drive:** the harness recipe with real selectors/commands from this repo, not examples. Prefer stable handles (ARIA labels, data attributes, prompt strings, route paths) over coordinates and tab order.
- **Evidence:** what to capture for a proof and where it goes. State the proof standards: exercise the real user path, not internal setters or test-only endpoints; capture the action and the resulting state, not just the final screen; verify side effects (files written, rows inserted, messages sent) alongside what's visible; mocks only where a production boundary already isolates the external system. When the safe path is a dry-run or test mode, verify what it actually skips by observing (files, network, git refs) rather than trusting its name: some dry-runs still touch the network or open a browser.
- **Cleanup:** how to tear down instances the run created. Never kill by process name; kill what you started. Cleanup removes instances and scratch state, never the evidence: proof artifacts survive the teardown, in a location the skill names.
- **Helpers:** any script the skill ships is executable and its invocation is shown in the skill body. A helper the reader has to reverse-engineer is not a helper.

## 3. Seed the feature map

Create `<project-skill-path>/verify-<app>/features/README.md` plus one file per user-facing feature you can identify (aim for the top 3-5 to start, from routes, commands, menus, or docs). Follow the shape in [`references/feature-map-example/`](references/feature-map-example/) (its commands illustrate the `agent-browser` route; adapt them to the selected driver), with a README index and one file per feature. Each file answers, from the user's point of view: what the feature is, how to reach it, how to drive it with the harness, and what observable end state proves it works. The four H2s are `Sub-features`, `How to get to it (user POV)`, `Driving it with <harness>`, and `Gotchas`. The map is the repo's maintained verification source; a proof that drives one convenient entry point is incomplete when the map lists others.

## 4. Prove the generated skill before handing it over

Run its own instructions end to end once: launch, doctor, drive ONE mapped feature (one is enough; the map exists so later runs can cover the rest), capture evidence, clean up. After cleanup, confirm the evidence still exists at the named location — a cleanup that eats the proof fails this step. Fix what fails, and run the generated cleanup after every failed iteration too, so broken attempts don't strand processes and ports. A generated skill that was never executed is a draft, not a deliverable.

## 5. Offer the maintenance loop

Point the user at `/maintain-verification-skill` for keeping the map honest as the app changes. Suggest a cadence only if they ask.
Files in this package (5)
  • SKILL.md 7 KB
  • agents/openai.yaml 1 KB
  • references/feature-map-example/README.md 3 KB
  • references/feature-map-example/create-note.md 3 KB
  • references/feature-map-example/search.md 4 KB

Versions

RepositoryScoreLicence
This page · alexanderop/pstack100MIT
e2e-inc/e2e100Apache-2.0
tester-army/e2e100Apache-2.0
TimothyVang/deepmodebot100MIT
Calvin-LLC/skills100MIT
arjitj2/open-pstack100MIT
paperclipai/paperclip100MIT
backnotprop/pstack100MIT
kriscard/Skills100MIT

Database snapshot: 13.11.2026 · package version 583519797e76 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100prove-e2e-create
    Generate a repo-local skill, verify-<app>, that launches this repo's app, drives a feature the way a user does, captures evidence, and cleans up, in any language or platform. Seeds a feature map and proves the new skill by running it once. Use when a repo has no scripted way to…
  • 90agents-create-verification-skill
    Generate a project-local verify skill that drives the app like a user through a browser with Playwright, a CLI, or HTTP. Use for /agents-create-verification-skill, "make a verify skill for this repo", or when a project has no scripted way to prove UI, CLI, or service behavior.
  • 100vital-signs
    Katara checks the vital signs so she knows the patient is really well, not just quiet. Use for create-verification-skill, /create-verification-skill, "make a control skill for this repo", "make a driver skill for this repo", or when a project has no scripted way to prove UI,…
  • 100verification-skill
    Create, adopt or maintain a project's own verify-<app> skill, the scripted way for any agent to launch the real app, drive a feature the way a user does, and capture proof. Use for "create a verification skill", "make a control skill for this repo", "set up verification for this…
  • 100create-verify-skill
    Create a project verify-<app> skill that drives the running app the way a user does, with agent-browser for web apps and tuistory for terminal apps. Use when a project has no verify skill yet; not to refresh a drifted one (use maintain-verify-skill), not to draft a generic skill…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.