Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Measure what matters with proper event tracking, funnels, cohorts, and metrics. Use when setting up analytics, tracking features, or understanding behavior.
.claude/skills/nicepkg-product-analytics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -33% | 0% |
Measure what matters and make data-driven decisions.
The ONE metric that represents customer value
yamlExamples: Slack: Weekly Active Users Airbnb: Nights Booked Spotify: Time Listening Shopify: GMV Your North Star should: ✅ Represent customer value ✅ Correlate with revenue ✅ Be measurable frequently ✅ Rally the team
North Star Metric
├── Input Metrics (drive North Star)
│ ├── Acquisition
│ ├── Activation
│ └── Retention
└── KPIs (business health)
├── Revenue
├── Churn
└── LTVtypescript// Track user actions analytics.track('Button Clicked', { button_name: 'signup', page: 'homepage', user_id: '123' }) // Track page views analytics.page('Homepage', { referrer: document.referrer, path: window.location.pathname }) // Identify users analytics.identify('user-123', { email: 'user@example.com', plan: 'pro', created_at: '2024-01-15' })
yamlSign-up Funnel: 1. Land on homepage: 10,000 (100%) 2. Click signup: 2,000 (20%) 3. Fill form: 1,000 (10%) 4. Verify email: 800 (8%) 5. Complete onboarding: 400 (4%) Insights: - Biggest drop: Homepage to signup (80% lost) - Fix: Clarify value prop, add social proof
yamlWeek 1 Cohort (Jan 1-7): - D1: 80% active - D7: 40% active - D30: 20% active Week 2 Cohort (Jan 8-14): - D1: 85% active (+5%) - D7: 50% active (+10%) - D30: 30% active (+10%) Insight: Onboarding changes improved retention!
yamlGood Retention: - D1: 60-80% - D7: 40-60% - D30: 30-50% - Flattening curve (good!) Bad Retention: - D1: 40% - D7: 10% - D30: 2% - Steep drop-off (bad!)
`## Tools
Event Tracking:
Session Recording:
A/B Testing:
`## Dashboard Design
Executive Dashboard:
Product Dashboard:
Marketing Dashboard:
## Summary
Great analytics:
- ✅ One North Star Metric
- ✅ Track everything
- ✅ Regular review (weekly)
- ✅ Share insights widely
- ✅ Act on data quickly| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→pass | 14,802 | 12,820 | -13% | 1 | 1 | 0% | 2,374 | 3,087 | +30% | 0 | 0 | — |
case-01 | fail→fail | 15,576 | 12,927 | -17% | 1 | 1 | 0% | 2,767 | 3,230 | +17% | 0 | 0 | — |
case-02 | fail→fail | 17,561 | 13,364 | -24% | 1 | 1 | 0% | 2,610 | 3,047 | +17% | 0 | 0 | — |
case-03 | pass→pass | 15,490 | 13,728 | -11% | 1 | 1 | 0% | 2,360 | 3,255 | +38% | 0 | 0 | — |
case-04 | fail→pass | 10,751 | 4,593 | -57% | 1 | 1 | 0% | 1,838 | 1,741 | -5% | 0 | 0 | — |
case-05 | fail→pass | 14,054 | 7,470 | -47% | 1 | 1 | 0% | 2,674 | 2,391 | -11% | 0 | 0 | — |
case-06 | pass→pass | 9,444 | 3,301 | -65% | 1 | 1 | 0% | 1,703 | 1,523 | -11% | 0 | 0 | — |
case-07 | pass→pass | 13,460 | 9,783 | -27% | 1 | 1 | 0% | 2,018 | 2,538 | +26% | 0 | 0 | — |
case-09 | pass→pass | 15,371 | 15,029 | -2% | 1 | 1 | 0% | 2,307 | 3,278 | +42% | 0 | 0 | — |
case-10 | pass→pass | 14,663 | 2,787 | -81% | 1 | 1 | 0% | 2,196 | 1,444 | -34% | 0 | 0 | — |
case-11 | pass→pass | 13,129 | 7,470 | -43% | 1 | 1 | 0% | 2,003 | 2,207 | +10% | 0 | 0 | — |
case-12 | fail→pass | 18,967 | 18,666 | -2% | 1 | 1 | 0% | 2,839 | 3,954 | +39% | 0 | 0 | — |
case-13 | fail→pass | 12,522 | 13,826 | +10% | 1 | 1 | 0% | 1,846 | 3,144 | +70% | 0 | 0 | — |
case-14 | pass→pass | 14,926 | 9,420 | -37% | 1 | 1 | 0% | 2,296 | 2,414 | +5% | 0 | 0 | — |
case-15 | pass→pass | 15,847 | 14,475 | -9% | 1 | 1 | 0% | 2,555 | 3,301 | +29% | 0 | 0 | — |
case-16 | pass→pass | 8,834 | 2,694 | -70% | 1 | 1 | 0% | 1,416 | 1,404 | -1% | 0 | 0 | — |
case-17 | pass→pass | 15,453 | 12,834 | -17% | 1 | 1 | 0% | 2,502 | 3,393 | +36% | 0 | 0 | — |
case-18 | pass→pass | 17,694 | 18,578 | +5% | 1 | 1 | 0% | 2,837 | 4,002 | +41% | 0 | 0 | — |
case-19 | fail→pass | 13,482 | 2,107 | -84% | 1 | 1 | 0% | 2,097 | 1,399 | -33% | 0 | 0 | — |
case-20 | pass→pass | 13,944 | 11,704 | -16% | 1 | 1 | 0% | 2,265 | 2,956 | +31% | 0 | 0 | — |
case-21 | pass→pass | 15,179 | 14,719 | -3% | 1 | 1 | 0% | 2,761 | 3,901 | +41% | 0 | 0 | — |
case-22 | pass→pass | 4,772 | 3,638 | -24% | 1 | 1 | 0% | 916 | 1,677 | +83% | 0 | 0 | — |
case-23 | pass→pass | 14,644 | 16,145 | +10% | 1 | 1 | 0% | 3,172 | 4,398 | +39% | 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. The headline lift of +22 percentage points is the difference between those two pass rates over the 23 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.