# Verify

> Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Claude Code built-in /verify (which runs the app to observe a single change working) — this one walks the CLAUDE.md "Features (Behavior Anchors)" list.

- Skill: `shenxingy/verify` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add shenxingy/verify`
- Raw SKILL.md: https://api.skillmd.com/api/skills/shenxingy/verify/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: shenxingy (https://skillmd.com/u/shenxingy)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/shenxingy/verify

---


# Verify Skill

Post-iteration verification used by `start.sh` to check that behavior anchors still pass after autonomous work. Not user-invocable — called internally by the autonomous loop.