Verify

SkillDev tools

Makes your agent re-run tests and checks to prove work is actually done before claiming completion.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Verify skill

About this capability

Prove a completion claim with fresh evidence before making it, the gate's exit code, the real diff, the remote's checks, the reviewer's verdict.

What this skill tells your AI

The instructions your AI receives, as published by automagik-dev/genie in skills/verify/SKILL.md and read by ahel’s review.

Evidence before claims, always. This skill runs commands and reads their output; it changes nothing, so a failure it finds routes to fix, never to a quiet repair here.

The rule

A claim you have not verified in this turn is not a claim, it is a hope. If the command that would prove it has not run since the last change, the honest report is the actual state plus what is still unproven.

Violating the letter of the rule violates its spirit: a paraphrase, an implication, or an expression of satisfaction is a completion claim too.

The gate function

Before any statement that work is done, correct, or passing:

  1. Identify the one command whose output proves this exact claim.
  2. Run it fresh and in full. A narrowed re-run proves only the narrowed scope.
  3. Read the whole output and the exit code, and count the failures rather than scanning for the word "pass".
  4. Decide. If the output confirms the claim, state the claim with the evidence beside it. If it does not, state the actual status with the same evidence.

Skipping a step is not a faster verification, it is a different activity.

What proves what

ClaimProofNot proof
The repository is greenbun run check exits zero, read in this turna previous run, a passing subset, "should pass"
Types are cleanthe typecheck stage inside that gatethe linter passing
A test suite passesthe suite's own output with a failure count of zeroone file re-run, a cached result
A bug is fixedthe original symptom re-exercised and now passingthe code changed and the reasoning looks right
A regression test worksit fails with the fix reverted and passes with it restoredit passes once
A worker did the workgit status and git diff over the owned scopethe worker's success report
A branch is mergeablethe remote's checks read back from the pull requesta local gate alone
A group is shippablea reviewer's returned verdict of SHIPFIX-FIRST treated as "close enough", or your own read of your own work
Requirements are meteach wish criterion walked one by one against evidencethe gate being green

Delegated work

A report from another agent is a pointer to evidence, not the evidence. Read the diff it claims to have produced and re-run the gate on the merged result. An agent that reports success having written nothing is the failure this row exists to catch.

Review verdicts are the same shape. SHIP is the only verdict that permits a completion claim. FIX-FIRST names gaps that must close and be re-reviewed; BLOCKED means the route changed and the claim is not available at all. Relay the verdict you received, never a softened version of it.

Red flags

Reach for this skill the moment you notice "should", "probably", or "seems to"; satisfaction arriving before output; a commit, push, or pull request forming without a fresh gate; exhaustion arguing that the remaining check is a formality. Each of those is the same event: the claim is running ahead of the proof.

Report

State the command, its exit status, and the claim it supports, in that order. Where expected evidence could not be captured, say which and why rather than leaving the gap silent.

Signals

GitHub stars
338
Forks
50
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
verify-automagik-dev
Source
github.com/automagik-dev/genie