Preamble (run first)
# 检查是否有优先级排序报告
if [ ! -f "docs/01-需求调研/优先级排序报告.md" ]; then
echo "⚠️ 未找到优先级排序报告"
echo ""
echo "建议先执行 /pm-priority 排序需求"
echo ""
echo "您可以选择:"
echo "A) 执行 /pm-priority 先排序需求(推荐)"
echo "B) 手动选择MVP功能(快速模式)"
fi
Boundaries when writing
When only discussing, do not write files; startup checks do not create directories. When the user requests saving artifacts, first confirm the current product, the exact output path, and the overwrite/append choice for existing files; after confirmationonly immediately before the actual Writecreate the parent directory of that output file. For full installation, see skills/_shared/artifact-policy.md; installing this skill alone also follows this paragraph.
Cross-Agent interaction rules
When the process requires interaction with the user:
- If the current environment supports AskUserQuestion, use AskUserQuestion (best experience).
- If the current environment does not support AskUserQuestion, you must ask the same question via a normal chat message.
- Ask only one question at a time.
- After asking, you must stop the current turn and wait for the user's answer (STOP and WAIT).
- Do not generate documents or write to docs before the user answers.
- Existing docs files cannot replace the user's answer in this turn.
Execution flow
Step 1: Read prerequisite data
Use the Read tool to read:
docs/01-需求调研/优先级排序报告.md(extract P0 requirements)docs/01-需求调研/需求调研报告.md(extract pain points)
Step 2: Choose MVP mode
Use AskUserQuestion:
🎯 Choose MVP mode:
A) Minimal MVP - core features only, rapid validation (2-4 weeks) B) Standard MVP - core features + basic experience (1-2 months) C) Full-chain MVP - complete user flow (2-3 months) D) Custom MVP - I will choose the features
Step 3: Determine the core feature set
If it is Minimal MVP:
Select the 3-5 most core features among P0-level requirements.
If it is Standard MVP:
Select all P0-level requirements.
If it is Full-chain MVP:
Select P0 + some P1 requirements, covering the complete user flow.
If it is Custom:
Ask one by one whether each requirement is included in the MVP.
Step 4: Risk assessment
AI assesses the risks of the MVP plan:
Technical risk:
- Are there technical difficulties?
- Is a new tech stack needed?
Business risk:
- Is the market window sufficient?
- Will competitors get ahead?
Resource risk:
- Does the team have enough manpower?
- Is the budget sufficient?
Step 5: Generate the MVP plan
Use the Write tool to create docs/01-需求调研/MVP方案.md:
# MVP方案
## 一、MVP概述
- **MVP模式**: {模式名称}
- **目标上线时间**: {时间}
- **核心验证目标**: {验证什么}
- **生成时间**: {当前时间}
---
## 二、核心功能集
| 序号 | 功能名称 | 优先级 | 工作量 | 负责人 |
|------|----------|--------|--------|--------|
| 1 | {功能1} | P0 | {工作量} | 待定 |
| 2 | {功能2} | P0 | {工作量} | 待定 |
| 3 | {功能3} | P0 | {工作量} | 待定 |
---
## 三、用户流程
### 3.1 核心用户旅程
User enters → {Step 1} → {Step 2} → {Step 3} → Complete
### 3.2 关键触点
- 触点1: {描述}
- 触点2: {描述}
---
## 四、技术方案
### 4.1 技术栈
- 前端: {技术}
- 后端: {技术}
- 数据库: {技术}
### 4.2 关键技术点
1. {技术点1}
2. {技术点2}
---
## 五、风险评估
### 5.1 技术风险
**风险**: {描述}
**应对**: {方案}
### 5.2 业务风险
**风险**: {描述}
**应对**: {方案}
### 5.3 资源风险
**风险**: {描述}
**应对**: {方案}
---
## 六、里程碑规划
| 里程碑 | 时间 | 交付物 |
|--------|------|--------|
| 设计完成 | Week 1 | 设计稿、原型 |
| 开发完成 | Week 2-3 | 功能代码 |
| 测试完成 | Week 4 | 测试报告 |
| 上线 | Week 5 | 产品上线 |
---
## 七、成功标准
### 7.1 业务指标
- 用户数: {目标}
- 留存率: {目标}
- 核心行为: {目标}
### 7.2 技术指标
- 性能: {目标}
- 稳定性: {目标}
---
## 八、下一步建议
建议执行:
1. **/pm-docs** - 生成PRD文档(推荐)
2. **/pm-proto** - 原型设计
3. **/pm-tech** - 技术对接方案
---
**项目状态**: MVP规划完成
**生成时间**: {时间戳}
**生成工具**: super-pm
Step 6: Output completion prompt
Use AskUserQuestion:
✅ MVP plan complete!
📄 MVP plan generated:
docs/01-需求调研/MVP方案.md🎯 Suggested next steps:
A) Run /pm-docs - generate PRD document (recommended) B) Run /pm-proto - prototype design C) Run /pm-tech - technical integration plan D) View MVP plan
Fallback mechanism
Scenario 1: No priority report
Provide a quick mode to manually select MVP features.
Scenario 2: Too many features
Remind the user to streamline features and focus on the core.
Notes
- Focus on core validation: The MVP must validate the core hypothesis
- Control scope: Avoid scope creep
- Rapid iteration: Launch as soon as possible to get feedback
- Risk assessment: Identify risks in advance and develop response plans
- Markdown storage: The MVP plan is human-readable and editable
Output quality comparison
✅ Good example:
- 有数据引用:「根据 Q4 数据,留存率从 35% 降至 28%」
- 有验证来源:「数据来源:Google Analytics, 2025-12-01」
- 有明确建议:「建议将新手引导步骤从 5 步减少至 3 步」
❌ Bad example:
- 模糊结论:「数据表明留存率有所下降」
- 无来源:「根据经验,这个功能很重要」
- 没有行动建议:「留存是个问题」
Common pitfalls / Red Flags — STOP
Stop immediately and backtrack if any of the following occur:
| Pitfall | Correct approach |
|---|---|
| Drawing conclusions using "should", "probably", "seems" | Must be based on actual data and verification |
| Claiming completion without running checks | Verify first, then state |
| Skipping key steps due to time pressure | No exceptions; the tighter the time, the stricter you must be |
| The thought "this time it should be fine" | Re-verify every time |
Output quality check / Verification Checklist
- Prerequisite dependencies are satisfied (input documents/data have been collected)
- All core steps have been executed
- The output document has been generated to the
docs/directory - Every judgment is supported by data/evidence
- 2-3 follow-up skills have been recommended
⚠️ If any item fails → complete it before marking as done.