SuperAPI AI Directory

pm-pool

Data & analytics

View repository

Updated 10-15 23:47

About this skill

Preamble (run first)

# 检查是否有需求池
if [ ! -f "docs/01-需求调研/需求池管理表.md" ]; then
  echo "⚠️  未找到需求池管理表"
  echo ""
  echo "将创建新的需求池"
fi

Write-time boundaries

When only discussing, do not write files; startup checks do not create directories. When the user asks to save 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 separately also follows this paragraph.


Cross-Agent interaction rules

When the process requires interaction with the user:

  1. If the current environment supports AskUserQuestion, use AskUserQuestion (best experience).
  2. If the current environment does not support AskUserQuestion, you must ask the same question using a normal chat message.
  3. Ask only one question at a time.
  4. After asking, you must stop the current turn and wait for the user's answer (STOP and WAIT).
  5. Do not generate documents or write to docs before the user answers.
  6. Existing docs files cannot replace the user's answer in this turn.

Execution flow

Step 1: Choose an operation

Use AskUserQuestion to ask:

🎯 What operation do you want to perform on the requirement pool?

A) Add a new requirement B) View the requirement pool C) Update requirement status D) Delete a requirement E) Export the requirement pool


Step 2: Execute the operation


Operation A: Add a new requirement

Use AskUserQuestion to ask one by one:

Question 1: Requirement name

Please enter the requirement name:

For example: "User login", "Search function"


Question 2: Requirement type

What is the requirement type?

A) New feature B) Feature optimization C) Bug fix D) Technical debt E) Other


Question 3: Priority

Requirement priority?

A) P0 - Urgent and important B) P1 - Important but not urgent C) P2 - Urgent but not important D) P3 - Not urgent and not important


Question 4: Source

Requirement source?

A) User feedback B) Business department C) Product planning D) Competitor analysis E) Other (please enter manually)


Question 5: Description

Please describe the requirement in detail:

Include background, goals, acceptance criteria, etc.


AI adds the requirement information to the requirement pool management table.


Operation B: View the requirement pool

Read docs/01-需求调研/需求池管理表.md, format and output:

📋 Requirement pool overview

Total requirements: {N} P0: {N} P1: {N} P2: {N} P3: {N}

Classified by status:

  • Pending evaluation: {N}
  • Planned: {N}
  • In development: {N}
  • Completed: {N}

View details?


Operation C: Update requirement status

List all requirements and let the user choose the requirement to update:

Please choose the requirement to update:

A) {Requirement 1} - Current status: Pending evaluation B) {Requirement 2} - Current status: Planned C) {Requirement 3} - Current status: In development ...

After the user chooses, ask for the new status:

What is the new status?

A) To be evaluated B) Planned C) In development D) In testing E) Launched F) Closed

Update the requirements pool management table.


Operation D: Delete requirement

List all requirements and let the user choose the requirement to delete:

Please select the requirement to delete:

A) {Requirement 1} B) {Requirement 2} ...

Delete after confirmation.


Operation E: Export requirements pool

Generate a shareable requirements pool document:

Select export format:

A) Markdown B) CSV C) JSON


Step 3: Update the requirements pool management table

If the requirements pool management table does not exist, use Write to create it:

# 需求池管理表

## 一、需求概览

- **需求总数**: {N}个
- **更新时间**: {当前时间}

---

## 二、需求列表

| ID | 需求名称 | 类型 | 优先级 | 状态 | 来源 | 创建时间 |
|----|----------|------|--------|------|------|----------|
| R001 | {需求1} | {类型} | {优先级} | {状态} | {来源} | {时间} |
| R002 | {需求2} | {类型} | {优先级} | {状态} | {来源} | {时间} |

---

## 三、需求详情

### R001: {需求名称}

**类型**: {类型}

**优先级**: {优先级}

**状态**: {状态}

**来源**: {来源}

**描述**:
{详细描述}

**验收标准**:
- {标准1}
- {标准2}

**负责人**: {负责人}

**预计完成时间**: {时间}

---

## 四、统计信息

### 4.1 按优先级

- P0: {N}个
- P1: {N}个
- P2: {N}个
- P3: {N}个

### 4.2 按状态

- 待评估: {N}个
- 已规划: {N}个
- 开发中: {N}个
- 已上线: {N}个

---

**最后更新**: {时间戳}
**生成工具**: super-pm

If the requirements pool already exists, use Edit to update it.


Step 4: Output completion prompt

Use AskUserQuestion:

✅ Requirements pool updated!

📄 Requirements pool management table:docs/01-需求调研/需求池管理表.md

🎯 Next step:

A) Continue managing the requirements pool B) Run /pm-priority - Prioritize requirements C) Run /pm-mvp - Plan MVP D) View requirements pool


Fallback mechanism

Scenario 1: Requirements pool does not exist

Automatically create a new requirements pool.

Scenario 2: Too many requirements

Provide filtering and search functionality.


Notes

  1. Unique ID: Assign a unique ID to each requirement (R001, R002...)
  2. Status transitions: Record status change history
  3. Adjustable priority: Adjust according to business changes
  4. Markdown storage: The requirements pool is human-readable and editable
  5. Regular cleanup: It is recommended to regularly clean up completed requirements

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 occurs:

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 "it should be fine this time" 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
  • 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.