人工确认检查点协议 — 关键决策前必须获得人工确认
Scanned 9/5/2026
Install to Claude Code
npx -y skills add WenJunDuan/Rlues --skill cunzhi --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cunzhi?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wenjunduan-cunzhi-fdc337d2)More formats (shields.io, HTML) on the badges page.
---
name: cunzhi
description: 人工确认检查点协议 — 关键决策前必须获得人工确认
context: main
---
# Cunzhi — 寸止检查点
## 检查点
| ID | 触发时机 | Path |
|:---|:---|:---|
| REQ_CONFIRMED | R₀ 需求理解确认 (R₀→R) | B+ |
| DESIGN_READY | 设计方案确定 (D→P) | B+ |
| PLAN_APPROVED | 任务列表确定 (P→E) | B+ |
| BIG_CHANGE | 修改 >100行 或 >3文件 | B+ |
| REVIEW_DONE | 审查通过 (Rev→A) | B+ |
| PATH_UPGRADE | 路径升级 | 全部 |
| FAIL_3X | T 阶段累计失败 ≥ 3 次 | 全部 |
## 交互格式
```
[cunzhi] {ID}
摘要: {一句话}
关键决策: {内容}
选项: [确认] [修改] [拒绝]
```
MCP 不可用 → 直接在对话中同格式请求确认。
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!