Skill · Build

verify-loop

Use when starting implementation or iterating a fix. Define a deterministic check for the acceptance criteria, run it red, then iterate until green.

Written by Kunanon Jarat

Original
Runs automatically
MIT
Superstacks v6.1.1

View on GitHub

Install this skill

Installs only verify-loop, globally, as a copy

DISABLE_TELEMETRY=1 npx skills add KunanonJ/superstacks -g -s verify-loop --copy -y

Third-party installer; DISABLE_TELEMETRY=1 turns its telemetry off.

Folder layout (verify-loop/SKILL.md). Unzip it into your agent’s skills directory.

Download verify-loop.zip

Flat layout: SKILL.md sits at the zip root, ready to upload as a skill.

Download verify-loop-flat.zip

Copy this folder from the repo at v6.1.1 into your agent’s skills directory

plugins/superstacks/skills/verify-loop/

verify-loop ships in the Superstacks plugin with the other skills. In Claude Code:

/plugin marketplace add KunanonJ/superstacks
/plugin install superstacks@superstacks

Run them one at a time. Codex, Cursor and ZIP steps are on the Skills page.

How it runs

Runs automatically.

The agent loads it when a task matches the description above. You can also ask for it by name.

Files

Folder on GitHub →

Origin

Original

Written for Superstacks

Written for Superstacks; sources.lock.json credits no upstream. Released under MIT with the rest of the pack.

License: MIT
Release: v6.1.1 · 2026-10-06

More in Build

Write the check first, then the code, and debug with evidence.

All 20 skills →

SKILL.md

View on GitHub

---
name: verify-loop
description: Use when starting implementation or iterating a fix. Define a deterministic check for the acceptance criteria, run it red, then iterate until green.
license: MIT
---

# Verify loop

The engineer designs a runnable check. The model spends tokens on judgment, not on being a human who copies errors between tools.

## Before writing code

1. Name the acceptance criteria in one sentence.
2. Pick a **deterministic** check that would fail today and pass when the work is done: unit or integration test, CLI assertion, perf trace, or a snapshot/console script.
3. Copy a runner from `scripts/` next to this skill into the repo (or run it in place). Do not install packages.

4. Run the check. Confirm it is red. Paste the runner output (`VERIFY_FAIL`).
5. Change code. Re-run the same command. Repeat until `VERIFY_PASS`.
6. Hand the same command to `verification-before-completion` before any success claim.

Never retype compiler, test, browser, or linter errors from memory. Re-run the command.

## Runners

| File | When |
| --- | --- |
| `scripts/verify.py` | Python stdlib wrapper. Prints pass/fail evidence. |
| `scripts/verify.sh` | POSIX wrapper with the same evidence format. |
| `scripts/check-snapshot-console.cjs` | Page snapshot plus console-error check. Uses Playwright already in the project. Exits 2 if it is missing. Never installs it. |

```text
python <this-skill>/scripts/verify.py -- <project-check>
bash <this-skill>/scripts/verify.sh -- <project-check>
node <this-skill>/scripts/check-snapshot-console.cjs <url> [shot.png]
```

Replace `<project-check>` with the repo's real command (`pytest`, a compiler, a perf trace). The wrapper does not choose the check.

## Rules

- One command is the source of truth for this ticket. Do not swap it mid-loop without saying why.
- Red before green. A check that was never red does not prove the fix.
- If the check needs a browser, use the snapshot template or a CDP script the repo already runs. Do not add runtime installs.
- Paste fresh runner output. Screenshots without `VERIFY_PASS`/`VERIFY_FAIL` are not enough.