product-manager-toolkit

# Product Manager Toolkit

Essential tools and frameworks for modern product management, from discovery to delivery.

---

## Table of Contents

- [Quick Start](#quick-start)
- [Core Workflows](#core-workflows)
  - [Feature Prioritization](#feature-prioritization-process)
  - [Customer Discovery](#customer-discovery-process)
  - [PRD Development](#prd-development-process)
- [Tools Reference](#tools-reference)
  - [RICE Prioritizer](#rice-prioritizer)
  - [Customer Interview Analyzer](#customer-interview-analyzer)
- [Input/Output Examples](#inputoutput-examples)
- [Integration Points](#integration-points)
- [Common Pitfalls](#common-pitfalls-to-avoid)

---

## Quick Start

### For Feature Prioritization
```bash
# Create sample data file
python scripts/rice_prioritizer.py sample

# Run prioritization with team capacity
python scripts/rice_prioritizer.py sample_features.csv --capacity 15
```

### For Interview Analysis
```bash
python scripts/customer_interview_analyzer.py interview_transcript.txt
```

### For PRD Creation
1. Choose template from `references/prd_templates.md`
2. Fill sections based on discovery work
3. Review with engineering for feasibility
4. Version control in project management tool

---

## Core Workflows

### Feature Prioritization Process

```
Gather → Score → Analyze → Plan → Validate → Execute
```

#### Step 1: Gather Feature Requests
- Customer feedback (support tickets, interviews)
- Sales requests (CRM pipeline blockers)
- Technical debt (engineering input)
- Strategic initiatives (leadership goals)

#### Step 2: Score with RICE
```bash
# Input: CSV with features
python scripts/rice_prioritizer.py features.csv --capacity 20
```

See `references/frameworks.md` for RICE formula and scoring guidelines.

#### Step 3: Analyze Portfolio
Review the tool output for:
- Quick wins vs big bets distribution
- Effort concentration (avoid all XL projects)
- Strategic alignment gaps

#### Step 4: Generate Roadmap
- Quarterly capacity allocation
- Dependency identification
- Stakeholder communication plan

#### Step 5: Validate Results
**Before finalizing the roadmap:**
- [ ] Compare top priorities against strategic goals
- [ ] Run sensitivity analysis (what if estimates are wrong by 2x?)
- [ ] Review with key stakeholders for blind spots
- [ ] Check for missing dependencies between features
- [ ] Validate effort estimates with engineering

#### Step 6: Execute and Iterate
- Share roadmap with team
- Track actual vs estimated effort
- Revisit priorities quarterly
- Update RICE inputs based on learnings

---

### Customer Discovery Process

```
Plan → Recruit → Interview → Analyze → Synthesize → Validate
```

#### Step 1: Plan Research
- Define research questions
- Identify target segments
- Create interview script (see `references/frameworks.md`)

#### Step 2: Recruit Participants
- 5-8 interviews per segment
- Mix of power users and churned users
- Incentivize appropriately

#### Step 3: Conduct Interviews
- Use semi-structured format
- Focus on problems, not solutions
- Record with permission
- Take minimal notes during interview

#### Step 4: Analyze Insights
```bash
python scripts/customer_interview_analyzer.py transcript.txt
```

Extracts:
- Pain points with severity
- Feature requests with priority
- Jobs to be done patterns
- Sentiment and key themes
- Notable quotes

#### Step 5: Synthesize Findings
- Group similar pain points across interviews
- Identify patterns (3+ mentions = pattern)
- Map to opportunity areas using Opportunity Solution Tree
- Prioritize opportunities by frequency and severity

#### Step 6: Validate Solutions
**Before building:**
- [ ] Create solution hypotheses (see `references/frameworks.md`)
- [ ] Test with low-fidelity prototypes
- [ ] Measure actual behavior vs stated preference
- [ ] Iterate based on feedback
- [ ] Document learnings for future research

---

### PRD Development Process

```
Scope → Draft → Review → Refine → Approve → Track
```

#### Step 1: Choose Template
Select from `references/prd_templates.md`:

| Template | Use Case | Timeline |
|----------|----------|----------|
| Standard PRD | Complex features, cross-team | 6-8 weeks |
| One-Page PRD | Simple features, single team | 2-4 weeks |
| Feature Brief | Exploration phase | 1 week |
| Agile Epic | Sprint-based delivery | Ongoing |

#### Step 2: Draft Content
- Lead with problem statement
- Define success metrics upfront
- Explicitly state out-of-scope items
- Include wireframes or mockups

#### Step 3: Review Cycle
- Engineering: feasibility and effort
- Design: user experience gaps
- Sales: market validation
- Support: operational impact

#### Step 4: Refine Based on Feedback
- Address technical constraints
- Adjust scope to fit timeline
- Document trade-off decisions

#### Step 5: Approval and Kickoff
- Stakeholder sign-off
- Sprint planning integration
- Communication to broader team

#### Step 6: Track Execution
**After launch:**
- [ ] Compare actual metrics vs targets
- [ ] Conduct user feedback sessions
- [ ] Document what worked and what didn't
- [ ] Update estimation accuracy data
- [ ] Share learnings with team

---

## Tools Reference

### RICE Prioritizer

Advanced RICE framework implementation with portfolio analysis.

**Features:**
- RICE score calculation with configurable weights
- Portfolio balance analysis (quick wins vs big bets)
- Quarterly roadmap generation based on capacity
- Multiple output formats (text, JSON, CSV)

**CSV Input Format:**
```csv
name,reach,impact,confidence,effort,description
User Dashboard Redesign,5000,high,high,l,Complete redesign
Mobile Push Notifications,10000,massive,medium,m,Add push support
Dark Mode,8000,medium,high,s,Dark theme option
```

**Commands:**
```bash
# Create sample data
python scripts/rice_prioritizer.py sample

# Run with default capacity (10 person-months)
python scripts/rice_prioritizer.py features.csv

# Custom capacity
python scripts/rice_prioritizer.py features.csv --capacity 20

# JSON output for integration
python scripts/rice_prioritizer.py features.csv --output json

# CSV output for spreadsheets
python scripts/rice_prioritizer.py features.csv --output csv
```

---

### Customer Interview Analyzer

NLP-based interview analysis for extracting actionable insights.

**Capabilities:**
- Pain point extraction with severity assessment
- Feature request identification and classification
- Jobs-to-be-done pattern recognition
- Sentiment analysis per section
- Theme and quote extraction
- Competitor mention detection

**Commands:**
```bash
# Analyze interview transcript
python scripts/customer_interview_analyzer.py interview.txt

# JSON output for aggregation
python scripts/customer_interview_analyzer.py interview.txt json
```

---

## Input/Output Examples
→ See references/input-output-examples.md for details

## Integration Points

Compatible tools and platforms:

| Category | Platforms |
|----------|-----------|
| **Analytics** | Amplitude, Mixpanel, Google Analytics |
| **Roadmapping** | ProductBoard, Aha!, Roadmunk, Productplan |
| **Design** | Figma, Sketch, Miro |
| **Development** | Jira, Linear, GitHub, Asana |
| **Research** | Dovetail, UserVoice, Pendo, Maze |
| **Communication** | Slack, Notion, Confluence |

**JSON export enables integration with most tools:**
```bash
# Export for Jira import
python scripts/rice_prioritizer.py features.csv --output json > priorities.json

# Export for dashboard
python scripts/customer_interview_analyzer.py interview.txt json > insights.json
```

---

## Common Pitfalls to Avoid

| Pitfall | Description | Prevention |
|---------|-------------|------------|
| **Solution-First** | Jumping to features before understanding problems | Start every PRD with problem statement |
| **Analysis Paralysis** | Over-researching without shipping | Set time-boxes for research phases |
| **Feature Factory** | Shipping features without measuring impact | Define success metrics before building |
| **Ignoring Tech Debt** | Not allocating time for platform health | Reserve 20% capacity for maintenance |
| **Stakeholder Surprise** | Not communicating early and often | Weekly async updates, monthly demos |
| **Metric Theater** | Optimizing vanity metrics over real value | Tie metrics to user value delivered |

---

## Best Practices

**Writing Great PRDs:**
- Start with the problem, not the solution
- Include clear success metrics upfront
- Explicitly state what's out of scope
- Use visuals (wireframes, flows, diagrams)
- Keep technical details in appendix
- Version control all changes

**Effective Prioritization:**
- Mix quick wins with strategic bets
- Consider opportunity cost of delays
- Account for dependencies between features
- Buffer 20% for unexpected work
- Revisit priorities quarterly
- Communicate decisions with context

**Customer Discovery:**
- Ask "why" five times to find root cause
- Focus on past behavior, not future intentions
- Avoid leading questions ("Wouldn't you love...")
- Interview in the user's natural environment
- Watch for emotional reactions (pain = opportunity)
- Validate qualitative with quantitative data

---

## Quick Reference

```bash
# Prioritization
python scripts/rice_prioritizer.py features.csv --capacity 15

# Interview Analysis
python scripts/customer_interview_analyzer.py interview.txt

# Generate sample data
python scripts/rice_prioritizer.py sample

# JSON outputs
python scripts/rice_prioritizer.py features.csv --output json
python scripts/customer_interview_analyzer.py interview.txt json
```

---

## Reference Documents

- `references/prd_templates.md` - PRD templates for different contexts
- `references/frameworks.md` - Detailed framework documentation (RICE, MoSCoW, Kano, JTBD, etc.)

{
  "format": "aiskill/v1",
  "skill": {
    "name": "product-manager-toolkit",
    "slug": "product-manager-toolkit",
    "version": "1.0.0",
    "description": "Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use when prioritizing features, synthesizing user research, writing requirement documentation, or developing product strategy.",
    "category": "Business",
    "tags": [
      "product-business",
      "research",
      "content",
      "product",
      "growth"
    ],
    "platforms": [
      "chatgpt",
      "claude-code",
      "cursor"
    ],
    "tested_environment": "Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and compatible agents",
    "license": "MIT"
  },
  "prompts": {
    "system": "# Product Manager Toolkit\r\n\r\nEssential tools and frameworks for modern product management, from discovery to delivery.\r\n\r\n---\r\n\r\n## Table of Contents\r\n\r\n- [Quick Start](#quick-start)\r\n- [Core Workflows](#core-workflows)\r\n  - [Feature Prioritization](#feature-prioritization-process)\r\n  - [Customer Discovery](#customer-discovery-process)\r\n  - [PRD Development](#prd-development-process)\r\n- [Tools Reference](#tools-reference)\r\n  - [RICE Prioritizer](#rice-prioritizer)\r\n  - [Customer Interview Analyzer](#customer-interview-analyzer)\r\n- [Input/Output Examples](#inputoutput-examples)\r\n- [Integration Points](#integration-points)\r\n- [Common Pitfalls](#common-pitfalls-to-avoid)\r\n\r\n---\r\n\r\n## Quick Start\r\n\r\n### For Feature Prioritization\r\n```bash\r\n# Create sample data file\r\npython scripts/rice_prioritizer.py sample\r\n\r\n# Run prioritization with team capacity\r\npython scripts/rice_prioritizer.py sample_features.csv --capacity 15\r\n```\r\n\r\n### For Interview Analysis\r\n```bash\r\npython scripts/customer_interview_analyzer.py interview_transcript.txt\r\n```\r\n\r\n### For PRD Creation\r\n1. Choose template from `references/prd_templates.md`\r\n2. Fill sections based on discovery work\r\n3. Review with engineering for feasibility\r\n4. Version control in project management tool\r\n\r\n---\r\n\r\n## Core Workflows\r\n\r\n### Feature Prioritization Process\r\n\r\n```\r\nGather → Score → Analyze → Plan → Validate → Execute\r\n```\r\n\r\n#### Step 1: Gather Feature Requests\r\n- Customer feedback (support tickets, interviews)\r\n- Sales requests (CRM pipeline blockers)\r\n- Technical debt (engineering input)\r\n- Strategic initiatives (leadership goals)\r\n\r\n#### Step 2: Score with RICE\r\n```bash\r\n# Input: CSV with features\r\npython scripts/rice_prioritizer.py features.csv --capacity 20\r\n```\r\n\r\nSee `references/frameworks.md` for RICE formula and scoring guidelines.\r\n\r\n#### Step 3: Analyze Portfolio\r\nReview the tool output for:\r\n- Quick wins vs big bets distribution\r\n- Effort concentration (avoid all XL projects)\r\n- Strategic alignment gaps\r\n\r\n#### Step 4: Generate Roadmap\r\n- Quarterly capacity allocation\r\n- Dependency identification\r\n- Stakeholder communication plan\r\n\r\n#### Step 5: Validate Results\r\n**Before finalizing the roadmap:**\r\n- [ ] Compare top priorities against strategic goals\r\n- [ ] Run sensitivity analysis (what if estimates are wrong by 2x?)\r\n- [ ] Review with key stakeholders for blind spots\r\n- [ ] Check for missing dependencies between features\r\n- [ ] Validate effort estimates with engineering\r\n\r\n#### Step 6: Execute and Iterate\r\n- Share roadmap with team\r\n- Track actual vs estimated effort\r\n- Revisit priorities quarterly\r\n- Update RICE inputs based on learnings\r\n\r\n---\r\n\r\n### Customer Discovery Process\r\n\r\n```\r\nPlan → Recruit → Interview → Analyze → Synthesize → Validate\r\n```\r\n\r\n#### Step 1: Plan Research\r\n- Define research questions\r\n- Identify target segments\r\n- Create interview script (see `references/frameworks.md`)\r\n\r\n#### Step 2: Recruit Participants\r\n- 5-8 interviews per segment\r\n- Mix of power users and churned users\r\n- Incentivize appropriately\r\n\r\n#### Step 3: Conduct Interviews\r\n- Use semi-structured format\r\n- Focus on problems, not solutions\r\n- Record with permission\r\n- Take minimal notes during interview\r\n\r\n#### Step 4: Analyze Insights\r\n```bash\r\npython scripts/customer_interview_analyzer.py transcript.txt\r\n```\r\n\r\nExtracts:\r\n- Pain points with severity\r\n- Feature requests with priority\r\n- Jobs to be done patterns\r\n- Sentiment and key themes\r\n- Notable quotes\r\n\r\n#### Step 5: Synthesize Findings\r\n- Group similar pain points across interviews\r\n- Identify patterns (3+ mentions = pattern)\r\n- Map to opportunity areas using Opportunity Solution Tree\r\n- Prioritize opportunities by frequency and severity\r\n\r\n#### Step 6: Validate Solutions\r\n**Before building:**\r\n- [ ] Create solution hypotheses (see `references/frameworks.md`)\r\n- [ ] Test with low-fidelity prototypes\r\n- [ ] Measure actual behavior vs stated preference\r\n- [ ] Iterate based on feedback\r\n- [ ] Document learnings for future research\r\n\r\n---\r\n\r\n### PRD Development Process\r\n\r\n```\r\nScope → Draft → Review → Refine → Approve → Track\r\n```\r\n\r\n#### Step 1: Choose Template\r\nSelect from `references/prd_templates.md`:\r\n\r\n| Template | Use Case | Timeline |\r\n|----------|----------|----------|\r\n| Standard PRD | Complex features, cross-team | 6-8 weeks |\r\n| One-Page PRD | Simple features, single team | 2-4 weeks |\r\n| Feature Brief | Exploration phase | 1 week |\r\n| Agile Epic | Sprint-based delivery | Ongoing |\r\n\r\n#### Step 2: Draft Content\r\n- Lead with problem statement\r\n- Define success metrics upfront\r\n- Explicitly state out-of-scope items\r\n- Include wireframes or mockups\r\n\r\n#### Step 3: Review Cycle\r\n- Engineering: feasibility and effort\r\n- Design: user experience gaps\r\n- Sales: market validation\r\n- Support: operational impact\r\n\r\n#### Step 4: Refine Based on Feedback\r\n- Address technical constraints\r\n- Adjust scope to fit timeline\r\n- Document trade-off decisions\r\n\r\n#### Step 5: Approval and Kickoff\r\n- Stakeholder sign-off\r\n- Sprint planning integration\r\n- Communication to broader team\r\n\r\n#### Step 6: Track Execution\r\n**After launch:**\r\n- [ ] Compare actual metrics vs targets\r\n- [ ] Conduct user feedback sessions\r\n- [ ] Document what worked and what didn't\r\n- [ ] Update estimation accuracy data\r\n- [ ] Share learnings with team\r\n\r\n---\r\n\r\n## Tools Reference\r\n\r\n### RICE Prioritizer\r\n\r\nAdvanced RICE framework implementation with portfolio analysis.\r\n\r\n**Features:**\r\n- RICE score calculation with configurable weights\r\n- Portfolio balance analysis (quick wins vs big bets)\r\n- Quarterly roadmap generation based on capacity\r\n- Multiple output formats (text, JSON, CSV)\r\n\r\n**CSV Input Format:**\r\n```csv\r\nname,reach,impact,confidence,effort,description\r\nUser Dashboard Redesign,5000,high,high,l,Complete redesign\r\nMobile Push Notifications,10000,massive,medium,m,Add push support\r\nDark Mode,8000,medium,high,s,Dark theme option\r\n```\r\n\r\n**Commands:**\r\n```bash\r\n# Create sample data\r\npython scripts/rice_prioritizer.py sample\r\n\r\n# Run with default capacity (10 person-months)\r\npython scripts/rice_prioritizer.py features.csv\r\n\r\n# Custom capacity\r\npython scripts/rice_prioritizer.py features.csv --capacity 20\r\n\r\n# JSON output for integration\r\npython scripts/rice_prioritizer.py features.csv --output json\r\n\r\n# CSV output for spreadsheets\r\npython scripts/rice_prioritizer.py features.csv --output csv\r\n```\r\n\r\n---\r\n\r\n### Customer Interview Analyzer\r\n\r\nNLP-based interview analysis for extracting actionable insights.\r\n\r\n**Capabilities:**\r\n- Pain point extraction with severity assessment\r\n- Feature request identification and classification\r\n- Jobs-to-be-done pattern recognition\r\n- Sentiment analysis per section\r\n- Theme and quote extraction\r\n- Competitor mention detection\r\n\r\n**Commands:**\r\n```bash\r\n# Analyze interview transcript\r\npython scripts/customer_interview_analyzer.py interview.txt\r\n\r\n# JSON output for aggregation\r\npython scripts/customer_interview_analyzer.py interview.txt json\r\n```\r\n\r\n---\r\n\r\n## Input/Output Examples\r\n→ See references/input-output-examples.md for details\r\n\r\n## Integration Points\r\n\r\nCompatible tools and platforms:\r\n\r\n| Category | Platforms |\r\n|----------|-----------|\r\n| **Analytics** | Amplitude, Mixpanel, Google Analytics |\r\n| **Roadmapping** | ProductBoard, Aha!, Roadmunk, Productplan |\r\n| **Design** | Figma, Sketch, Miro |\r\n| **Development** | Jira, Linear, GitHub, Asana |\r\n| **Research** | Dovetail, UserVoice, Pendo, Maze |\r\n| **Communication** | Slack, Notion, Confluence |\r\n\r\n**JSON export enables integration with most tools:**\r\n```bash\r\n# Export for Jira import\r\npython scripts/rice_prioritizer.py features.csv --output json > priorities.json\r\n\r\n# Export for dashboard\r\npython scripts/customer_interview_analyzer.py interview.txt json > insights.json\r\n```\r\n\r\n---\r\n\r\n## Common Pitfalls to Avoid\r\n\r\n| Pitfall | Description | Prevention |\r\n|---------|-------------|------------|\r\n| **Solution-First** | Jumping to features before understanding problems | Start every PRD with problem statement |\r\n| **Analysis Paralysis** | Over-researching without shipping | Set time-boxes for research phases |\r\n| **Feature Factory** | Shipping features without measuring impact | Define success metrics before building |\r\n| **Ignoring Tech Debt** | Not allocating time for platform health | Reserve 20% capacity for maintenance |\r\n| **Stakeholder Surprise** | Not communicating early and often | Weekly async updates, monthly demos |\r\n| **Metric Theater** | Optimizing vanity metrics over real value | Tie metrics to user value delivered |\r\n\r\n---\r\n\r\n## Best Practices\r\n\r\n**Writing Great PRDs:**\r\n- Start with the problem, not the solution\r\n- Include clear success metrics upfront\r\n- Explicitly state what's out of scope\r\n- Use visuals (wireframes, flows, diagrams)\r\n- Keep technical details in appendix\r\n- Version control all changes\r\n\r\n**Effective Prioritization:**\r\n- Mix quick wins with strategic bets\r\n- Consider opportunity cost of delays\r\n- Account for dependencies between features\r\n- Buffer 20% for unexpected work\r\n- Revisit priorities quarterly\r\n- Communicate decisions with context\r\n\r\n**Customer Discovery:**\r\n- Ask \"why\" five times to find root cause\r\n- Focus on past behavior, not future intentions\r\n- Avoid leading questions (\"Wouldn't you love...\")\r\n- Interview in the user's natural environment\r\n- Watch for emotional reactions (pain = opportunity)\r\n- Validate qualitative with quantitative data\r\n\r\n---\r\n\r\n## Quick Reference\r\n\r\n```bash\r\n# Prioritization\r\npython scripts/rice_prioritizer.py features.csv --capacity 15\r\n\r\n# Interview Analysis\r\npython scripts/customer_interview_analyzer.py interview.txt\r\n\r\n# Generate sample data\r\npython scripts/rice_prioritizer.py sample\r\n\r\n# JSON outputs\r\npython scripts/rice_prioritizer.py features.csv --output json\r\npython scripts/customer_interview_analyzer.py interview.txt json\r\n```\r\n\r\n---\r\n\r\n## Reference Documents\r\n\r\n- `references/prd_templates.md` - PRD templates for different contexts\r\n- `references/frameworks.md` - Detailed framework documentation (RICE, MoSCoW, Kano, JTBD, etc.)",
    "user_template": ""
  },
  "variables": [],
  "install": {
    "steps": [
      {
        "title": "Download & unzip",
        "detail": "Download the .zip package from SkillVault and unzip it. The product-manager-toolkit/ folder contains SKILL.md plus any companion scripts, references and assets."
      },
      {
        "title": "Copy into your agent skills directory",
        "detail": "Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code), .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or reload the session."
      },
      {
        "title": "Use it",
        "detail": "Describe the task in natural language; the agent loads the skill automatically when the request matches the skill description."
      }
    ]
  },
  "usage": {
    "steps": []
  },
  "metadata": {
    "author": "SkillVault",
    "source": "https://skillvault.top/skills/product-manager-toolkit",
    "exported_at": "2026-11-03T07:44:36.858Z"
  }
}

format: aiskill/v1
skill:
  name: product-manager-toolkit
  slug: product-manager-toolkit
  version: 1.0.0
  description: >-
    Comprehensive toolkit for product managers including RICE prioritization, customer interview
    analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use when
    prioritizing features, synthesizing user research, writing requirement documentation, or
    developing product strategy.
  category: Business
  tags:
    - product-business
    - research
    - content
    - product
    - growth
  platforms:
    - chatgpt
    - claude-code
    - cursor
  tested_environment: >-
    Agent Skills convention (SKILL.md) — works with Claude Code, Cursor, ChatGPT/Codex and
    compatible agents
  license: MIT
prompts:
  system: "# Product Manager Toolkit\r\n\r\nEssential tools and frameworks for modern product management, from discovery to delivery.\r\n\r\n---\r\n\r\n## Table of Contents\r\n\r\n- [Quick Start](#quick-start)\r\n- [Core Workflows](#core-workflows)\r\n  - [Feature Prioritization](#feature-prioritization-process)\r\n  - [Customer Discovery](#customer-discovery-process)\r\n  - [PRD Development](#prd-development-process)\r\n- [Tools Reference](#tools-reference)\r\n  - [RICE Prioritizer](#rice-prioritizer)\r\n  - [Customer Interview Analyzer](#customer-interview-analyzer)\r\n- [Input/Output Examples](#inputoutput-examples)\r\n- [Integration Points](#integration-points)\r\n- [Common Pitfalls](#common-pitfalls-to-avoid)\r\n\r\n---\r\n\r\n## Quick Start\r\n\r\n### For Feature Prioritization\r\n```bash\r\n# Create sample data file\r\npython scripts/rice_prioritizer.py sample\r\n\r\n# Run prioritization with team capacity\r\npython scripts/rice_prioritizer.py sample_features.csv --capacity 15\r\n```\r\n\r\n### For Interview Analysis\r\n```bash\r\npython scripts/customer_interview_analyzer.py interview_transcript.txt\r\n```\r\n\r\n### For PRD Creation\r\n1. Choose template from `references/prd_templates.md`\r\n2. Fill sections based on discovery work\r\n3. Review with engineering for feasibility\r\n4. Version control in project management tool\r\n\r\n---\r\n\r\n## Core Workflows\r\n\r\n### Feature Prioritization Process\r\n\r\n```\r\nGather → Score → Analyze → Plan → Validate → Execute\r\n```\r\n\r\n#### Step 1: Gather Feature Requests\r\n- Customer feedback (support tickets, interviews)\r\n- Sales requests (CRM pipeline blockers)\r\n- Technical debt (engineering input)\r\n- Strategic initiatives (leadership goals)\r\n\r\n#### Step 2: Score with RICE\r\n```bash\r\n# Input: CSV with features\r\npython scripts/rice_prioritizer.py features.csv --capacity 20\r\n```\r\n\r\nSee `references/frameworks.md` for RICE formula and scoring guidelines.\r\n\r\n#### Step 3: Analyze Portfolio\r\nReview the tool output for:\r\n- Quick wins vs big bets distribution\r\n- Effort concentration (avoid all XL projects)\r\n- Strategic alignment gaps\r\n\r\n#### Step 4: Generate Roadmap\r\n- Quarterly capacity allocation\r\n- Dependency identification\r\n- Stakeholder communication plan\r\n\r\n#### Step 5: Validate Results\r\n**Before finalizing the roadmap:**\r\n- [ ] Compare top priorities against strategic goals\r\n- [ ] Run sensitivity analysis (what if estimates are wrong by 2x?)\r\n- [ ] Review with key stakeholders for blind spots\r\n- [ ] Check for missing dependencies between features\r\n- [ ] Validate effort estimates with engineering\r\n\r\n#### Step 6: Execute and Iterate\r\n- Share roadmap with team\r\n- Track actual vs estimated effort\r\n- Revisit priorities quarterly\r\n- Update RICE inputs based on learnings\r\n\r\n---\r\n\r\n### Customer Discovery Process\r\n\r\n```\r\nPlan → Recruit → Interview → Analyze → Synthesize → Validate\r\n```\r\n\r\n#### Step 1: Plan Research\r\n- Define research questions\r\n- Identify target segments\r\n- Create interview script (see `references/frameworks.md`)\r\n\r\n#### Step 2: Recruit Participants\r\n- 5-8 interviews per segment\r\n- Mix of power users and churned users\r\n- Incentivize appropriately\r\n\r\n#### Step 3: Conduct Interviews\r\n- Use semi-structured format\r\n- Focus on problems, not solutions\r\n- Record with permission\r\n- Take minimal notes during interview\r\n\r\n#### Step 4: Analyze Insights\r\n```bash\r\npython scripts/customer_interview_analyzer.py transcript.txt\r\n```\r\n\r\nExtracts:\r\n- Pain points with severity\r\n- Feature requests with priority\r\n- Jobs to be done patterns\r\n- Sentiment and key themes\r\n- Notable quotes\r\n\r\n#### Step 5: Synthesize Findings\r\n- Group similar pain points across interviews\r\n- Identify patterns (3+ mentions = pattern)\r\n- Map to opportunity areas using Opportunity Solution Tree\r\n- Prioritize opportunities by frequency and severity\r\n\r\n#### Step 6: Validate Solutions\r\n**Before building:**\r\n- [ ] Create solution hypotheses (see `references/frameworks.md`)\r\n- [ ] Test with low-fidelity prototypes\r\n- [ ] Measure actual behavior vs stated preference\r\n- [ ] Iterate based on feedback\r\n- [ ] Document learnings for future research\r\n\r\n---\r\n\r\n### PRD Development Process\r\n\r\n```\r\nScope → Draft → Review → Refine → Approve → Track\r\n```\r\n\r\n#### Step 1: Choose Template\r\nSelect from `references/prd_templates.md`:\r\n\r\n| Template | Use Case | Timeline |\r\n|----------|----------|----------|\r\n| Standard PRD | Complex features, cross-team | 6-8 weeks |\r\n| One-Page PRD | Simple features, single team | 2-4 weeks |\r\n| Feature Brief | Exploration phase | 1 week |\r\n| Agile Epic | Sprint-based delivery | Ongoing |\r\n\r\n#### Step 2: Draft Content\r\n- Lead with problem statement\r\n- Define success metrics upfront\r\n- Explicitly state out-of-scope items\r\n- Include wireframes or mockups\r\n\r\n#### Step 3: Review Cycle\r\n- Engineering: feasibility and effort\r\n- Design: user experience gaps\r\n- Sales: market validation\r\n- Support: operational impact\r\n\r\n#### Step 4: Refine Based on Feedback\r\n- Address technical constraints\r\n- Adjust scope to fit timeline\r\n- Document trade-off decisions\r\n\r\n#### Step 5: Approval and Kickoff\r\n- Stakeholder sign-off\r\n- Sprint planning integration\r\n- Communication to broader team\r\n\r\n#### Step 6: Track Execution\r\n**After launch:**\r\n- [ ] Compare actual metrics vs targets\r\n- [ ] Conduct user feedback sessions\r\n- [ ] Document what worked and what didn't\r\n- [ ] Update estimation accuracy data\r\n- [ ] Share learnings with team\r\n\r\n---\r\n\r\n## Tools Reference\r\n\r\n### RICE Prioritizer\r\n\r\nAdvanced RICE framework implementation with portfolio analysis.\r\n\r\n**Features:**\r\n- RICE score calculation with configurable weights\r\n- Portfolio balance analysis (quick wins vs big bets)\r\n- Quarterly roadmap generation based on capacity\r\n- Multiple output formats (text, JSON, CSV)\r\n\r\n**CSV Input Format:**\r\n```csv\r\nname,reach,impact,confidence,effort,description\r\nUser Dashboard Redesign,5000,high,high,l,Complete redesign\r\nMobile Push Notifications,10000,massive,medium,m,Add push support\r\nDark Mode,8000,medium,high,s,Dark theme option\r\n```\r\n\r\n**Commands:**\r\n```bash\r\n# Create sample data\r\npython scripts/rice_prioritizer.py sample\r\n\r\n# Run with default capacity (10 person-months)\r\npython scripts/rice_prioritizer.py features.csv\r\n\r\n# Custom capacity\r\npython scripts/rice_prioritizer.py features.csv --capacity 20\r\n\r\n# JSON output for integration\r\npython scripts/rice_prioritizer.py features.csv --output json\r\n\r\n# CSV output for spreadsheets\r\npython scripts/rice_prioritizer.py features.csv --output csv\r\n```\r\n\r\n---\r\n\r\n### Customer Interview Analyzer\r\n\r\nNLP-based interview analysis for extracting actionable insights.\r\n\r\n**Capabilities:**\r\n- Pain point extraction with severity assessment\r\n- Feature request identification and classification\r\n- Jobs-to-be-done pattern recognition\r\n- Sentiment analysis per section\r\n- Theme and quote extraction\r\n- Competitor mention detection\r\n\r\n**Commands:**\r\n```bash\r\n# Analyze interview transcript\r\npython scripts/customer_interview_analyzer.py interview.txt\r\n\r\n# JSON output for aggregation\r\npython scripts/customer_interview_analyzer.py interview.txt json\r\n```\r\n\r\n---\r\n\r\n## Input/Output Examples\r\n→ See references/input-output-examples.md for details\r\n\r\n## Integration Points\r\n\r\nCompatible tools and platforms:\r\n\r\n| Category | Platforms |\r\n|----------|-----------|\r\n| **Analytics** | Amplitude, Mixpanel, Google Analytics |\r\n| **Roadmapping** | ProductBoard, Aha!, Roadmunk, Productplan |\r\n| **Design** | Figma, Sketch, Miro |\r\n| **Development** | Jira, Linear, GitHub, Asana |\r\n| **Research** | Dovetail, UserVoice, Pendo, Maze |\r\n| **Communication** | Slack, Notion, Confluence |\r\n\r\n**JSON export enables integration with most tools:**\r\n```bash\r\n# Export for Jira import\r\npython scripts/rice_prioritizer.py features.csv --output json > priorities.json\r\n\r\n# Export for dashboard\r\npython scripts/customer_interview_analyzer.py interview.txt json > insights.json\r\n```\r\n\r\n---\r\n\r\n## Common Pitfalls to Avoid\r\n\r\n| Pitfall | Description | Prevention |\r\n|---------|-------------|------------|\r\n| **Solution-First** | Jumping to features before understanding problems | Start every PRD with problem statement |\r\n| **Analysis Paralysis** | Over-researching without shipping | Set time-boxes for research phases |\r\n| **Feature Factory** | Shipping features without measuring impact | Define success metrics before building |\r\n| **Ignoring Tech Debt** | Not allocating time for platform health | Reserve 20% capacity for maintenance |\r\n| **Stakeholder Surprise** | Not communicating early and often | Weekly async updates, monthly demos |\r\n| **Metric Theater** | Optimizing vanity metrics over real value | Tie metrics to user value delivered |\r\n\r\n---\r\n\r\n## Best Practices\r\n\r\n**Writing Great PRDs:**\r\n- Start with the problem, not the solution\r\n- Include clear success metrics upfront\r\n- Explicitly state what's out of scope\r\n- Use visuals (wireframes, flows, diagrams)\r\n- Keep technical details in appendix\r\n- Version control all changes\r\n\r\n**Effective Prioritization:**\r\n- Mix quick wins with strategic bets\r\n- Consider opportunity cost of delays\r\n- Account for dependencies between features\r\n- Buffer 20% for unexpected work\r\n- Revisit priorities quarterly\r\n- Communicate decisions with context\r\n\r\n**Customer Discovery:**\r\n- Ask \"why\" five times to find root cause\r\n- Focus on past behavior, not future intentions\r\n- Avoid leading questions (\"Wouldn't you love...\")\r\n- Interview in the user's natural environment\r\n- Watch for emotional reactions (pain = opportunity)\r\n- Validate qualitative with quantitative data\r\n\r\n---\r\n\r\n## Quick Reference\r\n\r\n```bash\r\n# Prioritization\r\npython scripts/rice_prioritizer.py features.csv --capacity 15\r\n\r\n# Interview Analysis\r\npython scripts/customer_interview_analyzer.py interview.txt\r\n\r\n# Generate sample data\r\npython scripts/rice_prioritizer.py sample\r\n\r\n# JSON outputs\r\npython scripts/rice_prioritizer.py features.csv --output json\r\npython scripts/customer_interview_analyzer.py interview.txt json\r\n```\r\n\r\n---\r\n\r\n## Reference Documents\r\n\r\n- `references/prd_templates.md` - PRD templates for different contexts\r\n- `references/frameworks.md` - Detailed framework documentation (RICE, MoSCoW, Kano, JTBD, etc.)"
  user_template: ""
variables: []
install:
  steps:
    - title: Download & unzip
      detail: >-
        Download the .zip package from SkillVault and unzip it. The product-manager-toolkit/ folder
        contains SKILL.md plus any companion scripts, references and assets.
    - title: Copy into your agent skills directory
      detail: >-
        Move the folder into your agent's skills directory — e.g. ~/.claude/skills/ (Claude Code),
        .codex/skills/, .cursor/skills/ or your project's .claude/skills/ folder — then restart or
        reload the session.
    - title: Use it
      detail: >-
        Describe the task in natural language; the agent loads the skill automatically when the
        request matches the skill description.
usage:
  steps: []
metadata:
  author: SkillVault
  source: https://skillvault.top/skills/product-manager-toolkit
  exported_at: "2026-11-03T07:44:36.858Z"