# Verify

> Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

- Skill: `hmbown/verify` (Agent Skill)
- Install (CLI): `npx skillmds@latest add hmbown/verify`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hmbown/verify/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- Author: Hmbown (https://skillmd.com/u/hmbown)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hmbown/verify

---


# 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.