# Verify Completion Claims With Recorded Evidence

Completion claims can hide failed, skipped, or untested requirements. This skill guides requirement-level verification with observed output, commit-bound evidence, and explicit human acceptance.

## Install

```bash
npx skillstore add atri10/executor-verification
```

## Metadata

- Status: approved
- Slug: atri10-executor-verification
- Skillstore revision: r1
- Version status: missing
- Tree hash: 14caf2d5c5e2869b365b6c5b908fb28f1b0cee8e845096312bbd846a3df4e97b
- Author: atri10
- GitHub username: atri10
- License: MIT
- Repository: https://github.com/atri10/executor/tree/39ddcfe1d9f3497102622b72aa235fb0770187fe/skills/executor-verification
- Ref: 6d0b11444384184b7ae743742a7e233a9a705cd9
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, filesystem
- Quality score: 69
- Public page: https://skillstore.pages.dev/skills/atri10-executor-verification
- Manifest: https://skillstore.pages.dev/api/skills/atri10-executor-verification/manifest

## Capabilities

- Guide verification through each existing criterion and record PROVEN, FAILED, NOT-RUN, or UNAVAILABLE outcomes.
- Record project branch, commit, and worktree state alongside verification results.
- Structure append-only outcome rounds with requirement text, commands, observed output, and evidence citations.
- Provide a single-criterion evidence runner template with commit checks, refusal conditions, and a five-line report.
- Require suitable unit, integration, smoke, manual, or static evidence rather than treating every passing check as equivalent.
- Guide output redaction, companion secret scans, failure routing, and human acceptance before completion.

## Use Cases

- Verify a Feature Before Handoff: Walk existing acceptance criteria, gather suitable evidence, and present unresolved requirements before a feature handoff.
- Review Requirement Coverage: Compare observed test and smoke outcomes with requirements, without treating a passing unit suite as full feature proof.
- Coordinate Agent Verification: Dispatch one evidence runner per criterion, inspect the returned artifact, and route failures back to the owning implementation plan.

## Prompt Templates

### Check One Requirement

```
Verify criterion [reference] in [verification document] at the current state. Report its requirement, named method, observed output, and status without changing code.
```

### Build an Outcomes Round

```
Walk every criterion in [verification document]. Record state, commands, outcomes, and evidence citations. Summarize all four statuses and stop for human acceptance.
```

### Dispatch an Evidence Runner

```
Prepare one runner for [criterion] using the provided template. Fill every placeholder, select a model explicitly, and verify prerequisites before dispatch.
```

### Reverify After a Shared-Code Fix

```
Review fix [commit] against the existing ledger. Identify affected criteria and append a new round. Use isolated regression checks and scan retained evidence before committing.
```

## Limitations

- Companion Executor documentation and helper scripts are referenced but are not included in the two reviewed files.
- Requires an existing verification strategy and usable test capabilities; missing prerequisites remain explicit gaps.
- Does not fix application failures or independently approve completion; fixes and residual acceptance belong to other participants.
- Regression reverts need isolation, and secret-scan recovery needs retained-copy cleanup before evidence is committed.

## Best Practices

- Record the exact tested state and match each requirement to the evidence type its strategy names.
- Use an isolated worktree for regression reverts and preserve all existing user changes.
- Redact before capture, scan every retained evidence attempt, and resolve sensitive originals before tracking or committing.

## Anti Patterns

- Treating passing unit tests, clean review reports, or expected output as proof of every requirement.
- Changing code during verification to obtain a passing result without a separate fix and new evidence round.
- Hiding FAILED, NOT-RUN, or UNAVAILABLE outcomes when presenting the completion summary.

## Security Audit

- Audited at: 2026-10-05T18:24:08.971\+00:00
- Summary: All 155 static findings are false positives involving Markdown formatting, intended local verification, companion paths, or protective secret-handling guidance. Two semantic workflow risks concern unisolated regression reverts and retained evidence after secret-scan failures. No evidence found of malicious prompt injection or exfiltration; companion helper implementations are outside the two reviewed files.

## Stats

- Views: 1
- Downloads: 0
- Favorites: 0
- Popularity score: 0