寸止协议 - Pause and wait mechanism for human confirmation at critical decision points. Prevents AI from proceeding autonomously past important checkpoints. Core safety and collaboration mechanism.
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-ee073036)More formats (shields.io, HTML) on the badges page.
---
name: cunzhi
description: |
寸止协议 - Pause and wait mechanism for human confirmation at critical
decision points. Prevents AI from proceeding autonomously past important
checkpoints. Core safety and collaboration mechanism.
---
# 寸止 (Cunzhi) Protocol
## Concept
寸止 = "Stop at the inch" - Pause execution at critical points for human review.
## Cunzhi Points
| Point | When | Purpose |
|:---|:---|:---|
| `[REQ_READY]` | 需求分析完成 | 确认理解正确 |
| `[DESIGN_READY]` | 方案设计完成 | 确认技术方案 |
| `[PLAN_READY]` | 计划制定完成 | 确认执行计划 |
| `[PHASE_DONE]` | 阶段执行完成 | 确认继续下一阶段 |
| `[RELEASE_READY]` | 准备发布 | 确认发布 |
| `[TASK_DONE]` | 任务完成 | 确认归档 |
## Invocation
### MCP Tool (Preferred)
```yaml
Tool: mcp-feedback-enhanced
Action: request_confirmation
Message: "[PLAN_READY] 请确认执行计划..."
```
### Fallback
```markdown
---
🛑 **[PLAN_READY]** 寸止等待确认
请审查以上计划,确认后输入:
- `继续` - 执行计划
- `修改` - 调整后重新规划
- `取消` - 终止任务
---
```
## Rules
1. **必须等待** - 不可跳过寸止点
2. **明确输出** - 清晰展示等待内容
3. **选项明确** - 提供清晰的下一步选项
4. **状态保存** - 寸止时保存当前状态
## Integration
Called by:
- `riper` workflow at phase transitions
- `vibe-plan` after planning
- `vibe-review` before commit
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!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.