Preamble (run first)
# 检查是否已有产品组合战略文档
if [ -f "docs/05-产品战略/产品组合战略.md" ]; then
echo "⚠️ 检测到已有产品组合战略文档"
echo ""
echo "您可以选择："
echo "A) 查看现有战略"
echo "B) 重新分析（会覆盖现有文档）"
echo "C) 更新战略（在现有基础上调整）"
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 confirmation,only 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:
- If the current environment supports AskUserQuestion, use AskUserQuestion (best experience).
- If the current environment does not support AskUserQuestion, you must ask the same question in a regular 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 round.
Execution process
Step 1: Identify the current product portfolio
How to ask: Use AskUserQuestion to ask one by one
Question 1: Number of products
Use AskUserQuestion to ask:
How many products are you currently managing/planning?
A) 1 product (single product) B) 2-3 products (small product portfolio) C) 4-6 products (medium product portfolio) D) 7 or more products (large product portfolio) E) Other (please enter manually)
Question 2: Product list
Based on the answer to Question 1, collect product information one by one:
Please list the names of all products (one product per line)
Example：
- Product A: Fresh food e-commerce mini program
- Product B: Community group buying platform
- Product C: B2B supply chain system
Step 2: Collect detailed product data
For each product, collect the following data (using AskUserQuestion):
Ask for each product：
Data item 1: Market share
What is the market share of {product name}?
A) High (>40% market share) B) Medium (15-40% market share) C) Low (<15% market share) D) Unknown, needs research
Data item 2: Market growth rate
What is the annual growth rate of the market where {product name} is located?
A) High growth (>10% annual growth) B) Medium growth (5-10% annual growth) C) Low growth (<5% annual growth) D) Negative growth (market shrinking)
Data item 3: Product life cycle stage
What stage is {product name} in?
A) Introduction stage (just launched, exploring the market) B) Growth stage (rapid growth stage) C) Maturity stage (stable growth, market saturation) D) Decline stage (growth slowing or negative growth)
Data item 4: Revenue contribution
What is {product name}'s contribution to overall revenue?
A) Primary revenue source (>40% of total revenue) B) Important revenue source (20-40% of total revenue) C) Secondary revenue source (<20% of total revenue) D) No revenue yet (investment period)
Data item 5: Strategic importance
How important is {product name} to the company's strategy?
A) Core strategic product B) Important strategic product C) Supplementary strategic product D) Exploratory product
Step 3: BCG Matrix Analysis
Based on the collected data, perform BCG matrix classification:
BCG Matrix Classification Rules：
- Stars: High market share + High market growth
- Cash Cows: High market share + Low market growth
- Question Marks: Low market share + High market growth
- Dogs: Low market share + Low market growth
Analysis Logic：
For each product:
- Determine the quadrant based on "market share" and "market growth rate"
- Adjust based on "product life cycle" and "strategic importance"
- Output classification results and recommendations
Step 4: Generate Product Portfolio Strategy Report
Use the Write tool to generate the document, prioritizing saving to a Chinese directory:
---
product: [产品组合]
created_at: [当前时间]
author: [用户]
skill: pm-portfolio
status: draft
---
# 产品组合战略报告
## 一、产品组合概览
**产品数量**: [X]个产品
| 产品名称 | 市场占有率 | 市场增长率 | 生命周期 | 收入贡献 | 战略重要性 |
|---------|-----------|-----------|---------|---------|-----------|
| [产品A] | 高 | 高 | 成长期 | 主要收入 | 核心战略 |
| [产品B] | 中 | 低 | 成熟期 | 重要收入 | 重要战略 |
| ... | ... | ... | ... | ... | ... |
---
## 二、BCG矩阵分析
### 明星产品（Stars）
**产品列表**: [产品A, 产品C]
**特征**：
- 高市场占有率，高市场增长
- 需要大量投资维持增长
- 未来可能转化为现金牛
**战略建议**：
- ✅ 继续投资，扩大市场份额
- ✅ 防御竞争对手
- ✅ 探索新的增长机会
---
### 现金牛产品（Cash Cows）
**产品列表**: [产品B]
**特征**：
- 高市场占有率，低市场增长
- 产生稳定现金流
- 无需大量投资
**战略建议**：
- ✅ 维持现状，收割利润
- ✅ 控制成本，提高效率
- ✅ 将现金流投资明星产品
---
### 问题产品（Question Marks）
**产品列表**: [产品D]
**特征**：
- 低市场占有率，高市场增长
- 需要大量投资
- 可能成为明星，也可能失败
**战略建议**：
- ⚠️ 选择性投资（评估潜力）
- ⚠️ 快速提升市场份额或放弃
- ⚠️ 重点关注差异化竞争
---
### 瘦狗产品（Dogs）
**产品列表**: [产品E]
**特征**：
- 低市场占有率，低市场增长
- 不产生现金流
- 占用资源
**战略建议**：
- ❌ 考虑退出或出售
- ❌ 最小化投入
- ❌ 寻找转型机会
---
## 三、产品生命周期管理
### 导入期产品
**产品列表**: [产品C]
**关键任务**：
- 验证市场需求
- 优化产品功能
- 建立用户基础
---
### 成长期产品
**产品列表**: [产品A]
**关键任务**：
- 快速扩张市场份额
- 优化用户体验
- 建立竞争壁垒
---
### 成熟期产品
**产品列表**: [产品B]
**关键任务**：
- 维护用户关系
- 提升运营效率
- 寻找新的增长点
---
### 衰退期产品
**产品列表**: [产品E]
**关键任务**：
- 评估退出时机
- 移交客户关系
- 收回剩余价值
---
## 四、资源分配建议
### 投资优先级
1. **高优先级**：明星产品 + 核心战略产品
- 投资比例：50-60%资源
- 目标：扩大市场份额
2. **中优先级**：现金牛产品 + 重要战略产品
- 投资比例：20-30%资源
- 目标：维持稳定收益
3. **低优先级**：问题产品 + 试探性产品
- 投资比例：10-20%资源
- 目标：验证或放弃
4. **待评估**：瘦狗产品
- 投资比例：最小化
- 目标：退出或转型
---
## 五、战略决策建议
### 组合平衡性分析
**当前组合特点**：
- 明星产品：X个（理想：2-3个）
- 现金牛产品：X个（理想：1-2个）
- 问题产品：X个（理想：2-3个）
- 瘦狗产品：X个（理想：0-1个）
**平衡性评估**：[优秀/良好/需改进]
**改进建议**：
1. [具体建议1]
2. [具体建议2]
3. [具体建议3]
---
### 潜在风险
1. **过度依赖现金牛**
- 风险：市场变化导致收入下降
- 应对：培育新的增长点
2. **问题产品过多**
- 风险：资源分散，成功率低
- 应对：集中资源，重点突破
3. **缺乏明星产品**
- 风险：未来增长乏力
- 应对：加大投资，培育明星
---
## 六、下一步建议
建议执行：
1. /pm-resource - 制定详细的资源分配方案
2. /pm-decision - 战略决策支持（如收购、自研、退出等）
3. /pm-roadmap - 制定产品路线图
---
**项目状态**: 产品组合分析完成
**生成时间**: [当前时间]
**生成工具**: super-pm
V2 Parallel Architecture Upgrade
Subagent Parallel Analysis
After the BCG matrix and life cycle analysis are completed, subagents can be dispatched to execute in parallel:
Agent 1: Market Data Collection
- Responsible for: searching for market growth rate and market share data for the industry of each product
- Search tool priority: prefer AnySearch (Bash call anysearch_cli.py (locate first: check ~/.claude/skills/anysearch/scripts/ ~/.opencode/skills/anysearch/scripts/ ~/.openclaw/skills/anysearch/scripts/ ~/.cursor/skills/anysearch/scripts/ ~/.anysearch/scripts/ or which anysearch_cli.py, once found use python3 <path>) search), on failure fall back to Exa MCP (mcp__exa__web_search_exa), and only use WebSearch as a last resort. When using WebSearch, mark it as fallback mode
Agent 2: Competitor Portfolio Benchmarking
- Responsible for: searching for benchmark companies' product portfolio strategies and layouts
- Search tool priority: prefer AnySearch (Bash call), on failure fall back to Exa MCP (mcp__exa__web_search_exa), and only use WebSearch as a last resort
V1 vs V2 Comparison
| Dimension | v1 (serial) | v2 (Subagent parallel) |
|---|---|---|
| Market data | Main agent searches or skips | Subagent collects independently |
| Competitor benchmarking | User subjective judgment | Subagent structured comparison |
| Token usage | Results occupy the main context | Subagent processes independently |
| Execution efficiency | Linear sequence | Parallel 2x speedup |
Notes
- Data accuracy: Guide users to provide real data; if uncertain, mark as "to be researched"
- Dynamic adjustment: Product portfolios change with the market; it is recommended to reassess regularly (quarterly)
- Strategic alignment: The product portfolio strategy should be consistent with the company's overall strategy
- Resource constraints: Consider actual resource limitations and avoid overly optimistic planning
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", "looks like" | 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
- 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.