product-review

name	product-review
description	Phase 11 Multi-Persona Product Review. Evaluates final product from 10 different professional perspectives to ensure real-world readiness. Triggered after Phase 10 Quality Score passes (>= 80).

Phase 11: Multi-Persona Product Review

Overview

Phase 11 evaluates the complete product (not just code) from multiple professional perspectives. While Phase 10 verifies code quality, Phase 11 ensures the product is ready for the real world.

Why This Matters:

• Code Quality Score 95/100 + Product Score 40/100 = Failure
• Technical excellence without market fit = wasted effort
• A product that users, investors, and support can't handle = not ready

Trigger Condition

IF Phase 10 Quality Score >= 80:
    THEN Execute Phase 11
ELSE:
    FIX Phase 10 issues first

Available Personas (10 total)

Core Personas (Always Run)

Persona	Agent	Focus Area	Weight
User	product-reviewer-user	UX, value delivery, usability	20%
Designer	product-reviewer-designer	Visual, accessibility, polish	15%
Entrepreneur	product-reviewer-entrepreneur	PMF, business viability, moat	20%
Marketer	product-reviewer-marketer	GTM, virality, conversion	15%
Developer	product-reviewer-developer	Maintainability, tech debt	10%

Extended Personas (Conditional)

Persona	Agent	When to Include	Weight
Investor	product-reviewer-investor	Seeking funding	5%
CS Lead	product-reviewer-cs	User-facing product	5%
Legal	product-reviewer-legal	Data/privacy sensitive	5%
Analyst	product-reviewer-analyst	Data-driven product	5%
DevOps	product-reviewer-devops	Production deployment	5%

Execution Flow

Step 1: Determine Active Personas

Always include:
- User (20%)
- Designer (15%)
- Entrepreneur (20%)
- Marketer (15%)
- Developer (10%)

Include if applicable:
- Investor: IF seeking_funding = true
- CS: IF has_user_support = true
- Legal: IF handles_personal_data = true OR regulated_industry = true
- Analyst: IF data_driven = true
- DevOps: IF self_hosted = true OR complex_infra = true

Adjust weights proportionally to sum = 100%

Step 2: Parallel Execution

Launch all active personas in parallel (background):

task(
  subagent_type="product-reviewer-user",
  run_in_background=true,
  prompt="Evaluate product from end-user perspective..."
)

task(
  subagent_type="product-reviewer-designer",
  run_in_background=true,
  prompt="Evaluate product design and UX..."
)

... (repeat for all active personas)

Wait for all to complete.
Collect results.

Step 3: Score Aggregation

## Score Calculation

Product Score = Σ (Persona Score × Weight)

Example (Core 5 only):
- User: 85/100 × 0.25 = 21.25
- Designer: 78/100 × 0.20 = 15.60
- Entrepreneur: 82/100 × 0.25 = 20.50
- Marketer: 71/100 × 0.18 = 12.78
- Developer: 90/100 × 0.12 = 10.80
─────────────────────────────────
Product Score = 80.93/100

Step 4: Generate Report

## Phase 11 Product Review Complete

### Overall Product Score: [X]/100

### Persona Breakdown
| Persona | Score | Weight | Weighted |
|---------|-------|--------|----------|
| User | X/100 | 25% | X |
| Designer | X/100 | 20% | X |
| Entrepreneur | X/100 | 25% | X |
| Marketer | X/100 | 18% | X |
| Developer | X/100 | 12% | X |

### Red Flags (Score < 70)
- [ ] [Persona]: [Issue] - [Impact]

### Strengths (Score > 85)
- [ ] [Persona]: [Strength]

### Critical Issues (Must Fix)
1. ...

### Recommendations (Should Fix)
1. ...

### Quick Wins (Low Effort, High Impact)
1. ...

### Launch Readiness
- [ ] Product Score >= 75: Ready to launch
- [ ] All Critical Issues resolved
- [ ] No Red Flags blocking launch

Passing Criteria

Score Range	Decision	Action
>= 85	EXCELLENT	Launch immediately
75-84	GOOD	Launch with noted improvements
65-74	ACCEPTABLE	Launch to beta only, iterate
< 65	NOT READY	Do not launch, fix issues first

Minimum Thresholds (Any Below = Block)

Even if overall score is high, block if:
- User Score < 60 (unusable)
- Legal Score < 60 (compliance risk)
- DevOps Score < 50 (unstable)
- Security issues found (from Developer review)

Persona Prompt Templates

User Persona Prompt

You are product-reviewer-user. Evaluate this product.

Product: [Product Name]
Target User: [User Description]
Core Problem: [Problem Statement]

Evaluate from end-user perspective:
1. First Impression (0-10)
2. Onboarding Experience (0-10)
3. Core Task Completion (0-10)
4. Performance & Speed (0-10)
5. Frustration Points (0-10)
6. Delight Moments (0-10)
7. Problem-Solution Fit (0-10)
8. Would Return (0-10)
9. Would Recommend (0-10)
10. Would Pay (0-10)

For each, provide:
- Score with justification
- Specific evidence
- Improvement suggestion

End with:
- Overall User Score: X/100
- Top 3 Issues
- Top 3 Strengths
- Key Quote: "As a [user], I felt [emotion] because [reason]"

Designer Persona Prompt

You are product-reviewer-designer. Evaluate this product.

Product: [Product Name]
Design System: [If exists]

Evaluate design and UX:
1. Visual Hierarchy (0-10)
2. Typography (0-10)
3. Color System (0-10)
4. Layout & Spacing (0-10)
5. Interaction Design (0-10)
6. Consistency (0-10)
7. Responsive Design (0-10)
8. Accessibility (0-10)
9. Polish & Detail (0-10)
10. Innovation & Delight (0-10)

Include:
- WCAG 2.1 compliance check
- Responsive breakpoint test
- Color contrast validation

End with:
- Overall Design Score: X/100
- Critical Design Issues
- Accessibility Concerns
- Polish Recommendations

Entrepreneur Persona Prompt

You are product-reviewer-entrepreneur. Evaluate this product.

Product: [Product Name]
Market: [Target Market]
Competitors: [Known Competitors]

Evaluate business viability:
1. Problem-Solution Fit (0-10)
2. Value Proposition Clarity (0-10)
3. Target Market Definition (0-10)
4. Competitive Differentiation (0-10)
5. Business Model Viability (0-10)
6. Scalability (0-10)
7. Market Size (0-10)
8. Timing (0-10)
9. Founder-Market Fit (0-10)
10. Execution Quality (0-10)

End with:
- Overall Business Score: X/100
- Investment Potential: [Would/Wouldn't invest, why]
- Key Risks
- Strategic Recommendations
- Potential Pivots (if needed)

Marketer Persona Prompt

You are product-reviewer-marketer. Evaluate this product.

Product: [Product Name]
Current Channels: [If any]

Evaluate go-to-market readiness:
1. Hook Quality (0-10)
2. Landing Page Effectiveness (0-10)
3. Viral Potential (0-10)
4. SEO Readiness (0-10)
5. Conversion Funnel (0-10)
6. Social Proof (0-10)
7. Messaging Clarity (0-10)
8. Mobile Marketing Readiness (0-10)
9. Retention Mechanics (0-10)
10. Competitive Positioning (0-10)

End with:
- Overall GTM Score: X/100
- Top Growth Opportunities
- Critical Marketing Gaps
- Suggested Experiments
- Headline/CTA Recommendations

Developer Persona Prompt

You are product-reviewer-developer. Evaluate this product.

Product: [Product Name]
Tech Stack: [Stack Details]

Evaluate technical sustainability:
1. Code Readability (0-10)
2. Documentation Quality (0-10)
3. Test Coverage & Quality (0-10)
4. Architecture Quality (0-10)
5. Error Handling & Logging (0-10)
6. Security Practices (0-10)
7. Performance Considerations (0-10)
8. Development Experience (0-10)
9. Deployment & Operations (0-10)
10. Technical Debt (0-10)

End with:
- Overall Maintainability Score: X/100
- Would I Want to Maintain This: [Yes/No, why]
- Critical Tech Debt Items
- Security Concerns
- Onboarding Time Estimate

Integration with Workflow

Phase Positioning

Phase 10: Quality Score (Code)
    ↓ (IF Score >= 80)
Phase 11: Product Review (Multi-Persona)
    ↓ (IF Score >= 75)
LAUNCH READY

Workflow Update

Add to oh-my-speckit SKILL.md:

## Phase 11: Multi-Persona Product Review (AUTO-EXECUTE)

**Triggered after Phase 10 >= 80**

1. Determine active personas based on product type
2. Launch all reviewers in parallel (background)
3. Aggregate scores with weights
4. Generate comprehensive report
5. Decision:
   - Score >= 75: Proceed to launch
   - Score < 75: Fix issues, re-review

Example Output

## Phase 11 Product Review Complete

### ADHD CBT App Evaluation

**Overall Product Score: 78/100** ✅ (Launch Ready)

### Persona Breakdown

| Persona | Score | Weight | Weighted | Status |
|---------|-------|--------|----------|--------|
| User | 82/100 | 25% | 20.5 | ✅ |
| Designer | 75/100 | 20% | 15.0 | ✅ |
| Entrepreneur | 80/100 | 25% | 20.0 | ✅ |
| Marketer | 68/100 | 18% | 12.2 | ⚠️ |
| Developer | 88/100 | 12% | 10.6 | ✅ |

### Red Flags (Score < 70)
⚠️ **Marketer (68/100)**:
- Weak hook - "CBT for ADHD" not compelling
- No viral mechanics
- No social proof yet

### Strengths (Score > 85)
✅ **Developer (88/100)**:
- Excellent code quality
- Comprehensive tests
- Well-documented

### Critical Issues (Must Fix Before Launch)
1. **Improve marketing hook**
   - Current: "ADHD CBT App"
   - Suggested: "Rewire Your ADHD Brain in 5 Minutes a Day"

### Recommendations
1. Add testimonial section (even if just quotes)
2. Implement share feature for completed exercises
3. Add streak/gamification for retention

### Quick Wins
1. Update headline (10 min)
2. Add "as seen on" placeholder (5 min)
3. Add social share buttons (1 hr)

### Launch Readiness Checklist
- [x] Product Score >= 75
- [x] No User Score < 60
- [x] No Legal Score < 60
- [x] No DevOps Score < 50
- [ ] All Critical Issues resolved ← PENDING

**Recommendation**: Fix marketing hook, then launch to beta.

Advanced Configuration

Custom Personas

Create custom personas for specific industries:

# Healthcare SaaS
additional_personas:
  - product-reviewer-clinician
  - product-reviewer-patient
  - product-reviewer-hipaa

# Fintech
additional_personas:
  - product-reviewer-compliance
  - product-reviewer-risk
  - product-reviewer-trader

Persona Weights Customization

Adjust weights based on product stage:

# Early Stage (focus on PMF)
weights:
  user: 30%
  entrepreneur: 30%
  designer: 15%
  marketer: 15%
  developer: 10%

# Growth Stage (focus on scale)
weights:
  user: 20%
  marketer: 25%
  devops: 20%
  analyst: 15%
  developer: 10%
  designer: 10%

Philosophy

"A product that only engineers love is a technical success and a market failure. A product that only marketers love is a sales pitch without substance. Excellence requires all perspectives."

Phase 11 ensures we ship products, not just code.