# Verify · WillowRyu

> Use after /execute to verify the changes are correct. Reads .handoff/{config,plan,task}.md, runs the verification commands from plan (typically test + lint; typecheck is execute's job), compares plan-vs-code, writes review.md, and on success cleans up handoff state. For multi-phase plans, advances phase markers instead of full cleanup until the last phase. STRONGLY recommended to run in a fresh chat — fresh context is the entire point of this stage. Part of the agent-handoff bundle (4 skills) — install /setup-handoff, /plan, /execute, /verify together.

## Facts
- Page: https://tashan.sh/capability/skill-willowryu-verify
- tashan id: skill:WillowRyu/verify
- Source: https://github.com/WillowRyu/agent-handoff
- Type: skill
- Category: devtools
- tashan score: 34.0 / 100
- Adoption: 17.0
- Upkeep: 52.0
- Freshness: 74.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: MIT
- Official: no

## Install

```sh
cp -r verify ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-15 by tashan (https://tashan.sh) from public evidence. Scorer s5.