Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
Scanned 9/4/2026
Install to Claude Code
Skills Directorynpx -y skills add gabrielmoreira/agent-skills-mirror --skill verify --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Verify?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gabrielmoreira-verify-agent-skills-mirror)More formats (shields.io, HTML) on the badges page.
---
name: verify
description: Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
invocation: model+user
aliases-for: check-work
---
# Verify
## When to use
Use when the user wants proof the real surface works, not only unit tests.
## Non-goals
- Unit tests alone are not end-to-end verification.
- Do not fake success without observable evidence.
## Workflow
1. Identify the real entrypoint (CLI binary, API, UI).
2. Exercise it with realistic inputs.
3. Capture outputs, exit codes, logs, or screenshots.
4. Report evidence and remaining uncertainty.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
