Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when the user needs product management workflows such as RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, go-to-market strategy, feature prioritization, research synthesis, or requirements documentation.
.claude/skills/majiayu000-product-manager-toolkit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 121% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 44% | 0% |
Essential tools and frameworks for modern product management, from discovery to delivery.
bashpython scripts/rice_prioritizer.py sample # Create sample CSV python scripts/rice_prioritizer.py sample_features.csv --capacity 15
bashpython scripts/customer_interview_analyzer.py interview_transcript.txt
references/prd_templates.mdbash # Create CSV with: name,reach,impact,confidence,effort python scripts/rice_prioritizer.py features.csv
bash python scripts/customer_interview_analyzer.py transcript.txt Extracts:
Advanced RICE framework implementation with portfolio analysis.
Features:
Usage Examples:
bash# Basic prioritization python scripts/rice_prioritizer.py features.csv # With custom team capacity (person-months per quarter) python scripts/rice_prioritizer.py features.csv --capacity 20 # Output as JSON for integration python scripts/rice_prioritizer.py features.csv --output json
NLP-based interview analysis for extracting actionable insights.
Capabilities:
Usage Examples:
bash# Analyze single interview python scripts/customer_interview_analyzer.py interview.txt # Output as JSON for aggregation python scripts/customer_interview_analyzer.py interview.txt json
Multiple PRD formats for different contexts:
Score = (Reach × Impact × Confidence) / Effort
Reach: # of users/quarter
Impact:
- Massive = 3x
- High = 2x
- Medium = 1x
- Low = 0.5x
- Minimal = 0.25x
Confidence:
- High = 100%
- Medium = 80%
- Low = 50%
Effort: Person-months Low Effort High Effort
High QUICK WINS BIG BETS
Value [Prioritize] [Strategic]
Low FILL-INS TIME SINKS
Value [Maybe] [Avoid]1. Context Questions (5 min)
- Role and responsibilities
- Current workflow
- Tools used
2. Problem Exploration (15 min)
- Pain points
- Frequency and impact
- Current workarounds
3. Solution Validation (10 min)
- Reaction to concepts
- Value perception
- Willingness to pay
4. Wrap-up (5 min)
- Other thoughts
- Referrals
- Follow-up permissionWe believe that [building this feature]
For [these users]
Will [achieve this outcome]
We'll know we're right when [metric]Outcome
├── Opportunity 1
│ ├── Solution A
│ └── Solution B
└── Opportunity 2
├── Solution C
└── Solution DAcquisition → Activation → Retention → Revenue → Referral
Key Metrics:
- Conversion rate at each step
- Drop-off points
- Time between steps
- Cohort variationsThis toolkit integrates with:
bash# Prioritization python scripts/rice_prioritizer.py features.csv --capacity 15 # Interview Analysis python scripts/customer_interview_analyzer.py interview.txt # Create sample data python scripts/rice_prioritizer.py sample # JSON outputs for integration python scripts/rice_prioritizer.py features.csv --output json python scripts/customer_interview_analyzer.py interview.txt json
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 22,738 | 26,936 | +18% | 1 | 1 | 0% | 4,957 | 8,314 | +68% | 0 | 0 | — |
case-01 | fail→pass | 16,749 | 13,619 | -19% | 1 | 1 | 0% | 3,483 | 2,478 | -29% | 0 | 0 | — |
case-02 | fail→fail | 3,569 | 7,802 | +119% | 1 | 1 | 0% | 591 | 2,424 | +310% | 0 | 0 | — |
case-03 | fail→pass | 10,913 | 4,488 | -59% | 1 | 1 | 0% | 1,826 | 2,923 | +60% | 0 | 0 | — |
case-04 | fail→pass | 6,906 | 2,268 | -67% | 1 | 1 | 0% | 1,151 | 2,543 | +121% | 0 | 0 | — |
case-05 | pass→pass | 8,723 | 4,223 | -52% | 1 | 1 | 0% | 1,255 | 2,788 | +122% | 0 | 0 | — |
case-06 | fail→pass | 8,998 | 1,783 | -80% | 1 | 1 | 0% | 1,434 | 2,418 | +69% | 0 | 0 | — |
case-07 | fail→pass | 12,040 | 4,163 | -65% | 1 | 1 | 0% | 1,965 | 2,831 | +44% | 0 | 0 | — |
case-08 | pass→pass | 3,249 | 1,882 | -42% | 1 | 1 | 0% | 473 | 2,410 | +410% | 0 | 0 | — |
case-09 | pass→pass | 2,758 | 1,877 | -32% | 1 | 1 | 0% | 428 | 2,398 | +460% | 0 | 0 | — |
case-10 | pass→pass | 3,367 | 2,083 | -38% | 1 | 1 | 0% | 514 | 2,436 | +374% | 0 | 0 | — |
case-11 | pass→pass | 5,632 | 2,957 | -47% | 1 | 1 | 0% | 873 | 2,584 | +196% | 0 | 0 | — |
case-12 | pass→pass | 4,520 | 1,994 | -56% | 1 | 1 | 0% | 753 | 2,399 | +219% | 0 | 0 | — |
case-13 | pass→pass | 7,466 | 3,867 | -48% | 1 | 1 | 0% | 1,252 | 2,821 | +125% | 0 | 0 | — |
case-14 | pass→pass | 7,794 | 1,599 | -79% | 1 | 1 | 0% | 1,156 | 2,386 | +106% | 0 | 0 | — |
case-15 | fail→pass | 7,375 | 12,136 | +65% | 1 | 1 | 0% | 1,218 | 2,645 | +117% | 0 | 0 | — |
case-16 | pass→pass | 13,050 | 7,379 | -43% | 1 | 1 | 0% | 2,003 | 3,191 | +59% | 0 | 0 | — |
case-17 | fail→pass | 7,028 | 5,491 | -22% | 1 | 1 | 0% | 1,125 | 2,996 | +166% | 0 | 0 | — |
case-18 | pass→pass | 3,308 | 3,604 | +9% | 1 | 1 | 0% | 487 | 2,686 | +452% | 0 | 0 | — |
case-19 | fail→pass | 13,464 | 5,631 | -58% | 1 | 1 | 0% | 2,001 | 3,017 | +51% | 0 | 0 | — |
case-20 | fail→fail | 13,540 | 3,519 | -74% | 1 | 1 | 0% | 2,010 | 2,665 | +33% | 0 | 0 | — |
case-21 | pass→pass | 15,352 | 13,395 | -13% | 1 | 1 | 0% | 3,002 | 5,002 | +67% | 0 | 0 | — |
case-23 | pass→pass | 9,685 | 8,059 | -17% | 1 | 1 | 0% | 1,894 | 3,742 | +98% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +35 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.