SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillspm-iteration

pm-iteration

General & other

View repository

Updated 10-15 23:47

About this skill

Preamble

echo "🔄 迭代计划工具已启动"

# 检查前置数据
echo "📊 正在检查前置数据..."
if [ -f "docs/03-增长迭代/数据报告与用户反馈.md" ]; then
  echo "✅ 数据报告 - 已找到"
fi
if [ -f "docs/03-增长迭代/产品路线图.md" ]; then
  echo "✅ 产品路线图 - 已找到"
fi

Write 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 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 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 process

Step 1: Determine iteration scope

Use AskUserQuestion to ask:

📋 Iteration planning

Iteration number: Iteration X Iteration cycle: 2 weeks recommended

Input sources for this iteration:

A) Data analysis results (data-driven optimization) B) User feedback (user demand-driven) C) Competitive analysis (market change-driven) D) Technical optimization (performance/architecture improvement) E) Business goals (strategic adjustment) F) A combination of multiple items above G) Product roadmap breakdown (extracted from long-term planning)

💡 Tip: It is recommended to focus each iteration on 1-2 core goals

Record to variable ITERATION_INPUT

Step 2: Set iteration goals

🎯 Set iteration goals

What are the core goals of this iteration? (1-2 recommended)

Goal examples：

  • Increase registration conversion rate to 30%
  • Complete development and launch of XX feature
  • Fix the top 5 user feedback issues

Goal 1: {goal description} Goal 2: {goal description}

Each goal needs to be measurable, such as "increase XX metric from X% to Y%"

Step 3: Collect iteration requirements

📝 Requirement list for this iteration:

Please list the requirements/tasks to be completed in this iteration (one per line):

Example:

  • Optimize the registration process (source: data-driven - low registration conversion rate)
  • Add product search feature (source: user feedback)
  • Fix slow homepage loading issue (source: technical optimization)

Enter "done" to finish input

Collected list REQUIREMENT_LIST

Step 4: Prioritize requirements

Prioritize requirements based on value and cost:

🎯 Requirement prioritization

P0 (must have): Affects core goals or blocks other requirements P1 (should have): Important but not urgent P2 (could have): Nice to have

Confirm the priority of each requirement:

Priority of requirement "{requirement name}"?

A) P0 - Must have B) P1 - Should have C) P2 - Could have D) Defer to next iteration

Step 5: Resource Allocation and Scheduling

👥 Resource Allocation:

Available development resources:

  • Frontend: [X] people
  • Backend: [X] people
  • Design: [X] people
  • QA: [X] people

Effort Estimation：

Requirement Priority Frontend Effort Backend Effort Total Effort
{Requirement 1} P0 X days X days X days
{Requirement 2} P0 X days X days X days
{Requirement 3} P1 X days X days X days
Total X days X days X days

Risk Assessment：

  • Is the total effort within the iteration capacity?
  • Are there any blocking dependencies?
  • Is scope adjustment needed?

Step 6: Output Iteration Plan

Use the Write tool to create docs/03-增长迭代/迭代计划-v{版本号}.md：

# 迭代计划 v{版本号}

## 一、迭代概览

- **迭代编号**：第X次迭代
- **周期**：YYYY-MM-DD 至 YYYY-MM-DD（2周）
- **核心目标**：
  1. {目标1}
  2. {目标2}

## 二、需求清单

| 优先级 | 需求名称 | 来源 | 前端工时 | 后端工时 | 负责人 |
|--------|---------|------|---------|---------|--------|
| P0 | {需求1} | {来源} | X天 | X天 | {负责人} |
| P0 | {需求2} | {来源} | X天 | X天 | {负责人} |
| P1 | {需求3} | {来源} | X天 | X天 | {负责人} |
| P2 | {需求4} | {来源} | X天 | X天 | {负责人} |

## 三、排期计划

### 第1周
- Day 1-2：{任务}
- Day 3-4：{任务}
- Day 5：{任务}

### 第2周
- Day 6-7：{任务}
- Day 8-9：{任务}
- Day 10：交付/测试/上线

## 四、风险与预案

| 风险 | 概率 | 影响 | 预案 |
|------|------|------|------|
| {风险} | H/M/L | H/M/L | {预案} |

## 五、验收标准

- 所有P0需求完成开发并测试通过
- {目标1}达成：{衡量标准}
- {目标2}达成：{衡量标准}

---

**文档状态**: 迭代计划完成
**生成时间**: {时间戳}
**生成工具**: super-pm

Step 7: Completion Prompt

✅ Iteration plan completed!

📄 Generated:docs/03-增长迭代/迭代计划-v{版本号}.md

🎯 Suggested next steps:

A) Run /pm-risk - Risk control plan B) Run /pm-agile - Agile management plan C) After the iteration starts, run /pm-report to track progress

Fallback Mechanism

Scenario: Too many requirements

If the total effort of requirements exceeds the iteration capacity:

⚠️ Total requirement effort {X days} exceeds iteration capacity {standard capacity}

Suggestions: A) Defer some P1/P2 requirements to the next iteration B) Add development resources C) Extend the iteration cycle

V2 Parallel Architecture Upgrade

Architecture Overview

Parallel Subagent Analysis

After confirming the requirement list, dispatch 4 Subagents concurrently:

Subagent 1: Requirement Analysis

  • Responsible for: assessing the business value, user impact scope, and relevance of requirements

Subagent 2: Effort Estimation

  • Responsible for: estimating development effort and testing effort for each requirement based on historical data

Subagent 3: Dependency Analysis

  • Responsible for: identifying technical dependencies, team dependencies, and external dependencies between requirements

Subagent 4: Risk Analysis

  • Responsible for: identifying scheduling risks, resource bottlenecks, and technical risks

V1 vs V2 Comparison

Metric V1 (Sequential Analysis) V2 (Parallel Analysis) Improvement
Analysis Time ~5 minutes ~2 minutes 2.5x
Main Agent Context ~12,000 tokens ~3,500 tokens 71% saved
Analysis Dimensions Manual item-by-item estimation 4-dimension parallel assessment -
Scheduling Accuracy Relies on experience Multi-dimensional cross-validation More accurate

Notes

  1. Each iteration focuses on 1-2 core objectives; avoid having too many objectives
  2. P0 requirements do not exceed 60% of iteration capacity
  3. Reserve 20% buffer time to handle unexpected issues
  4. The iteration plan is confirmed and communicated to the team before the iteration starts

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 Practice
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 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.