← ClaudeAtlas

azhou-verifylisted

Run and report the authoritative Azhou AI Hub repository verification gate. Use before completion, handoff, commit, pull request, release, or when full-codebase evidence is requested.
TeFuirnever/azhou-ai-hub · ★ 1 · Code & Development · score 70
Install: claude install-skill TeFuirnever/azhou-ai-hub
# Azhou Verify **🦊 阿舟 · Azhou Verify** > 🧪 完整 gate 跑完,结论才成立。 Use the repository Foundation CLI as the only full-gate entry. Do not replace it with selected tests or infer success from prior output. ## Brand protocol Emit this exact display event once, at the start of every run, with the resolved checkout scope: ```text 🦊 阿舟 · Azhou Verify 启动|mode=verify|scope=<checkout> ``` Use `✅ 验证通过` only after the full gate exits successfully and its output is read back. Use `❌ 验证失败` for any failed or unavailable gate and `🔒 阿舟暂停这一项` when an explicit checkout is missing. Emoji is display-only; keep JSON keys, schema values, digests, paths, commands, test names, and raw evidence emoji-free. A host without Unicode may remove the leading emoji while preserving the fixed text, `|` separators, fields, and values. ## Workflow 1. Resolve the checkout from a user-supplied path, or from the current Git root only when both `scripts/azhou_hub.py` and `docs/skill-standard.md` exist. Do not scan unrelated directories or infer a harness home. 2. Run `python scripts/azhou_hub.py verify` from that checkout. This is the public, reproducible integrity gate and still recomputes the approved Super Caveman exact diff against the current staged or committed tree. Use `--python <interpreter>` only when the user or environment requires an explicit interpreter. 3. Add `--promotion-evidence` only for an explicitly requested maintainer/release replay after both required Git-external Super Caveman recor