pm-report

Preamble

echo "📊 数据报告与用户反馈工具已启动"

# 检查数据指标体系
if [ -f "docs/02-方案设计/数据指标体系.md" ]; then
  echo "✅ 数据指标体系 - 已找到"
else
  echo "⏳ 数据指标体系 - 未找到（建议先执行 /pm-data）"
fi

---

Write-time boundaries

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 confirmation,only immediately before the actual Writecreate the parent directory of that output file. For complete installation, see skills/_shared/artifact-policy.md, and installing this skill alone 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 via 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 report type

Use AskUserQuestion to ask:

📊 Choose report type

A) Daily report (core metrics overview) B) Weekly report (weekly data summary) C) Monthly report (monthly data analysis) D) Special report (analysis of a specific topic, such as conversion rate analysis) E) User feedback organization (collect and categorize user feedback) F) Other (please enter manually)

💡 Tip:

• Daily monitoring → Daily report
• Team sync → Weekly report
• Management reporting → Monthly report
• Problem localization → Special report

Record to variable REPORT_TYPE

---

Step 2: Collect data

Based on the data metric system or manual input, collect key metric data.

📈 Metric data collection

Please provide the following core metric data (if unavailable, you may skip):

User metrics：

• DAU (daily active users): [input]
• MAU (monthly active users): [input]
• New users: [input]

Business metrics：

• GMV/revenue: [input]
• ARPU (average revenue per user): [input]

Conversion metrics：

• Overall conversion rate: [input]
• Conversion rate at each stage: [input]

A) I have complete data and will enter it item by item B) I only have partial data; fill in what I can first C) No data for now; only do trend analysis

---

Step 3: Data analysis

📊 Data analysis:

Comparative analysis：

• Period-over-period (compared with previous period): {[data]}
• Year-over-year (compared with same period last year): {[data]}
• Target achievement rate: {[data]}

Trend judgment：

• Upward trend: {metric} continues to rise
• Downward trend: {metric} needs attention
• Stable state: {metric} is within the normal range

Anomaly identification：

• {metric 1}: {describe anomaly}
• {metric 2}: {describe anomaly}

Do you need an in-depth analysis of a certain anomaly?

---

Step 4: Organize user feedback (optional)

If "User Feedback Compilation" is selected:

💬 User feedback sources:

A) App store reviews B) Customer service tickets C) User interviews/surveys D) Social media (Weibo/Zhihu) E) Internal feedback (operations/sales) F) Multiple of the above

Feedback categories：

• Bug/failure: [X] items
• Feature suggestions: [X] items
• Experience issues: [X] items
• Complaints/dissatisfaction: [X] items
• Praise: [X] items

High-frequency keywords: {keyword 1}, {keyword 2}, {keyword 3}

---

Step 5: Output report

Based on the report type, use Write to generate the corresponding document.

General report structure：

# {产品名称} - {报告类型} - {日期}

## 一、核心指标总览

| 指标 | 本期 | 上期 | 环比 | 目标 | 达成率 |
|------|------|------|------|------|--------|
| DAU | [X] | [X] | ±X% | [X] | X% |
| 新增用户 | [X] | [X] | ±X% | [X] | X% |
| GMV | [X] | [X] | ±X% | [X] | X% |
| 转化率 | X% | X% | ±Xpp | X% | X% |

## 二、数据趋势分析

### 2.1 核心指标趋势
{趋势描述}

### 2.2 关键变化说明
- {变化1}：{原因分析}
- {变化2}：{原因分析}

## 三、异常说明

| 异常指标 | 表现 | 原因 | 处理状态 |
|---------|------|------|---------|
| {指标} | {异常描述} | {初步判断} | 处理中/已解决 |

## 四、改进建议

1. {建议1}
2. {建议2}
3. {建议3}

---

**生成时间**: {时间戳}
**数据来源**: {数据来源}

File path：

• Daily report → docs/03-增长迭代/数据报告/日报-YYYY-MM-DD.md
• Weekly report → docs/03-增长迭代/数据报告/周报-YYYY-WW.md
• Monthly report → docs/03-增长迭代/数据报告/月报-YYYY-MM.md
• User feedback → docs/03-增长迭代/用户反馈/反馈汇总-YYYY-MM.md

---

Step 6: Completion prompt

✅ {report type} has been generated!

📄 File:docs/03-增长迭代/数据报告/{文件名}

🎯 Suggested next steps:

A) Run /pm-iteration - Create an iteration plan based on data B) Run /pm-retro - Iteration retrospective C) Generate another type of report

---

Fallback mechanism

Scenario: No data metric system

If there is no pre-existing data metric system document, prompt the user to manually enter key metrics.

---

V2 Parallel Architecture Upgrade

Architecture overview

Parallel Subagent analysis

After data collection is complete, dispatch 4 Subagents concurrently:

Subagent 1: Metric analysis

• Responsible for: calculating core metrics, period-over-period and year-over-year comparisons, target achievement rate

Subagent 2: Trend analysis

• Responsible for: identifying trend changes, cyclical patterns, inflection point determination

Subagent 3: User feedback

• Responsible for: compiling user feedback, sentiment analysis, keyword extraction

Subagent 4: Anomaly detection

• Responsible for: identifying data anomalies, root cause analysis, impact scope assessment

V1 vs V2 comparison

Metric	V1 (sequential analysis)	V2 (parallel analysis)	Improvement
Analysis time	~5 minutes	~2 minutes	2.5x
Main Agent context	~10,000 tokens	~3,000 tokens	70% saved
Analysis dimensions	Basic metric display	Comprehensive review across 4 dimensions	-
Report depth	Surface-level data listing	Deep insight discovery	More in-depth

---

Notes

1. Data definitions need to be aligned with the team to avoid inconsistent definitions
2. Period-over-period/year-over-year calculations need to specify the statistical period
3. Anomalous data needs to be annotated with the reason (known reason/to be investigated)
4. User feedback needs to distinguish emotional tendency (positive/negative/neutral)

---

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 critical steps due to time pressure	No exceptions; the tighter the time, the stricter you must be
The thought that "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.

---