{"id":"517bb25b-08f8-4c1b-b34a-8fdb5519bade","shortId":"bfkRAj","kind":"skill","title":"product-analytics","tagline":"Product analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention. Covers AARRR framework, funnel analysis, cohort analysis, and experimentation.","description":"# Product Analytics\n\n## Core Principles\n\n- **Metrics over vanity** — Focus on actionable metrics tied to business outcomes\n- **Data-driven decisions** — Hypothesize, measure, learn, iterate\n- **User-centric measurement** — Track behavior, not just pageviews\n- **Statistical rigor** — Understand significance, avoid false positives\n- **Privacy-first** — Respect user data, comply with GDPR/CCPA\n- **North Star focus** — Align all teams around one key metric\n\n---\n\n## Hard Rules (Must Follow)\n\n> These rules are mandatory. Violating them means the skill is not working correctly.\n\n### No PII in Events\n\n**Events must NEVER contain personally identifiable information.**\n\n```javascript\n// ❌ FORBIDDEN: PII in event properties\ntrack('user_signed_up', {\n  email: 'user@example.com',     // PII!\n  name: 'John Doe',              // PII!\n  phone: '+1234567890',          // PII!\n  ip_address: '192.168.1.1',     // PII!\n  credit_card: '4111...',        // NEVER!\n});\n\n// ✅ REQUIRED: Anonymized/hashed identifiers only\ntrack('user_signed_up', {\n  user_id: hash('user@example.com'),  // Hashed\n  plan: 'pro',\n  source: 'organic',\n  country: 'US',                       // Broad location OK\n});\n\n// Masking utilities\nconst maskEmail = (email) => {\n  const [name, domain] = email.split('@');\n  return `${name[0]}***@${domain}`;\n};\n```\n\n### Object_Action Event Naming\n\n**All event names must follow the object_action snake_case format.**\n\n```javascript\n// ❌ FORBIDDEN: Inconsistent naming\ntrack('signup');                    // No object\ntrack('newProject');                // camelCase\ntrack('Upload File');               // Spaces and PascalCase\ntrack('user-created');              // kebab-case\ntrack('BUTTON_CLICKED');            // SCREAMING_CASE\n\n// ✅ REQUIRED: object_action snake_case\ntrack('user_signed_up');\ntrack('project_created');\ntrack('file_uploaded');\ntrack('payment_completed');\ntrack('checkout_started');\n```\n\n### Actionable Metrics Only\n\n**Track metrics that drive decisions, not vanity metrics.**\n\n```javascript\n// ❌ FORBIDDEN: Vanity metrics without context\ntrack('page_viewed');               // No insight\ntrack('button_clicked');            // Too generic\ntrack('app_opened');                // Doesn't indicate value\n\n// ✅ REQUIRED: Actionable metrics tied to outcomes\ntrack('feature_activated', {\n  feature: 'dark_mode',\n  time_to_activation_hours: 2.5,\n  user_segment: 'power_user',\n});\n\ntrack('checkout_completed', {\n  order_value: 99.99,\n  items_count: 3,\n  payment_method: 'credit_card',\n  coupon_applied: true,\n});\n```\n\n### Statistical Rigor for Experiments\n\n**A/B tests must have proper sample size and significance thresholds.**\n\n```javascript\n// ❌ FORBIDDEN: Drawing conclusions too early\n// \"After 100 users, variant B has 5% higher conversion!\"\n// This is not statistically significant.\n\n// ✅ REQUIRED: Proper experiment setup\nconst experimentConfig = {\n  name: 'new_checkout_flow',\n  hypothesis: 'New flow increases conversion by 10%',\n\n  // Statistical requirements\n  significance_level: 0.05,      // 95% confidence\n  power: 0.80,                   // 80% power\n  minimum_detectable_effect: 0.10, // 10% lift\n\n  // Calculated sample size\n  sample_size_per_variant: 3842,\n\n  // Guardrails\n  max_duration_days: 14,\n  stop_if_degradation: -0.05,    // Stop if 5% worse\n};\n```\n\n---\n\n## Quick Reference\n\n### When to Use What\n\n| Scenario | Framework/Tool | Key Metric |\n|----------|---------------|------------|\n| Overall product health | North Star Metric | Time spent listening (Spotify), Nights booked (Airbnb) |\n| Growth optimization | AARRR (Pirate Metrics) | Conversion rates per stage |\n| Feature validation | A/B Testing | Statistical significance (p < 0.05) |\n| User engagement | Cohort Analysis | Day 1/7/30 retention rates |\n| Conversion optimization | Funnel Analysis | Drop-off rates per step |\n| Feature impact | Attribution Modeling | Multi-touch attribution |\n| Experiment success | Statistical Testing | Power, significance, effect size |\n\n---\n\n## North Star Metric\n\n### Definition\n\nA North Star Metric is the **one metric** that best captures the core value your product delivers to customers. When this metric grows sustainably, your business succeeds.\n\n### Characteristics of Good NSMs\n\n```\n✓ Captures product value delivery\n✓ Correlates with revenue/growth\n✓ Measurable and trackable\n✓ Movable by product/engineering\n✓ Understandable by entire org\n✓ Leading (not lagging) indicator\n```\n\n### Examples by Company\n\n| Company | North Star Metric | Why It Works |\n|---------|------------------|--------------|\n| **Spotify** | Time Spent Listening | Core value = music enjoyment |\n| **Airbnb** | Nights Booked | Revenue driver + value delivered |\n| **Slack** | Daily Active Teams | Engagement = product stickiness |\n| **Facebook** | Monthly Active Users | Network effect foundation |\n| **Amplitude** | Weekly Learning Users | Value = analytics insights |\n| **Dropbox** | Active Users Sharing Files | Core product behavior |\n\n### NSM Framework\n\n```\nNorth Star Metric\n       ↓\n┌──────┴──────┬──────────┬──────────┐\n│             │          │          │\nInput 1    Input 2   Input 3   Input 4\n(Supporting metrics that drive NSM)\n\nExample: Spotify\nNSM: Time Spent Listening\n├── Daily Active Users\n├── Playlists Created\n├── Songs Added to Library\n└── Share/Social Actions\n```\n\n### How to Define Your NSM\n\n1. **Identify core value proposition**\n   - What job does your product do for users?\n   - When do users get \"aha!\" moment?\n\n2. **Find the metric that represents this value**\n   - Transaction completed? (e.g., Nights Booked)\n   - Time engaged? (e.g., Time Listening)\n   - Content created? (e.g., Messages Sent)\n\n3. **Validate it correlates with business success**\n   - Does NSM increase → revenue increases?\n   - Can product changes move this metric?\n\n4. **Define supporting input metrics**\n   - What user behaviors drive NSM?\n   - Break into 3-5 key inputs\n\n---\n\n## AARRR Framework (Pirate Metrics)\n\n### Overview\n\nThe AARRR framework tracks the customer lifecycle across five stages:\n\n```\nACQUISITION → ACTIVATION → RETENTION → REFERRAL → REVENUE\n```\n\n### Stage Definitions\n\n#### 1. Acquisition\n**When users discover your product**\n\n**Key Questions:**\n- Where do users come from?\n- Which channels have best quality users?\n- What's the cost per acquisition (CPA)?\n\n**Metrics:**\n```\n• Website visitors\n• App installs\n• Sign-ups per channel\n• Cost per acquisition (CPA)\n• Channel conversion rates\n```\n\n**Example Events:**\n```javascript\n// Landing page view\ntrack('page_viewed', {\n  page: 'landing',\n  utm_source: 'google',\n  utm_medium: 'cpc',\n  utm_campaign: 'brand_search'\n});\n\n// Sign-up started\ntrack('signup_started', {\n  source: 'homepage_cta'\n});\n```\n\n#### 2. Activation\n**When users experience core product value**\n\n**Key Questions:**\n- What's the \"aha!\" moment?\n- How long to first value?\n- What % reach activation?\n\n**Metrics:**\n```\n• Time to first action\n• Activation rate (% completing key action)\n• Setup completion rate\n• Feature adoption rate\n```\n\n**Example \"Aha!\" Moments:**\n```\nSlack:     Send 2,000 messages in team\nTwitter:   Follow 30 users\nDropbox:   Upload first file\nLinkedIn:  Connect with 5 people\n```\n\n**Example Events:**\n```javascript\n// Activation milestone\ntrack('activated', {\n  user_id: 'usr_123',\n  activation_action: 'first_project_created',\n  time_to_activation_hours: 2.5\n});\n```\n\n#### 3. Retention\n**When users keep coming back**\n\n**Key Questions:**\n- What's Day 1/7/30 retention?\n- Which cohorts retain best?\n- What drives churn?\n\n**Metrics:**\n```\n• Day 1/7/30 retention rate\n• Weekly/Monthly active users (WAU/MAU)\n• Churn rate\n• Usage frequency\n• Feature stickiness (DAU/MAU)\n```\n\n**Retention Calculation:**\n```\nDay X Retention = Users returning on Day X / Total users in cohort\n\nExample:\nCohort: 1000 users signed up Jan 1\nDay 7: 300 returned\nDay 7 Retention = 300/1000 = 30%\n```\n\n**Example Events:**\n```javascript\n// Daily engagement\ntrack('session_started', {\n  user_id: 'usr_123',\n  session_count: 42,\n  days_since_signup: 15\n});\n```\n\n#### 4. Referral\n**When users recommend your product**\n\n**Key Questions:**\n- What's the viral coefficient (K-factor)?\n- Which users refer most?\n- What referral incentives work?\n\n**Metrics:**\n```\n• Viral coefficient (K-factor)\n• Referral rate (% users referring)\n• Invites sent per user\n• Invite conversion rate\n• Net Promoter Score (NPS)\n```\n\n**Viral Coefficient:**\n```\nK = (% users who refer) × (avg invites per user) × (invite conversion rate)\n\nExample:\nK = 0.20 × 5 × 0.30 = 0.30\n\nK > 1: Viral growth (each user brings >1 new user)\nK < 1: Need paid acquisition\n```\n\n**Example Events:**\n```javascript\n// Referral actions\ntrack('invite_sent', {\n  user_id: 'usr_123',\n  channel: 'email',\n  recipients: 3\n});\n\ntrack('referral_converted', {\n  referrer_id: 'usr_123',\n  new_user_id: 'usr_456',\n  channel: 'email'\n});\n```\n\n#### 5. Revenue\n**When users generate business value**\n\n**Key Questions:**\n- What's customer lifetime value (LTV)?\n- What's LTV:CAC ratio?\n- Which segments monetize best?\n\n**Metrics:**\n```\n• Monthly Recurring Revenue (MRR)\n• Average Revenue Per User (ARPU)\n• Customer Lifetime Value (LTV)\n• LTV:CAC ratio\n• Conversion to paid\n• Revenue churn\n```\n\n**LTV Calculation:**\n```\nLTV = ARPU × Gross Margin / Churn Rate\n\nExample:\nARPU: $50/month\nGross Margin: 80%\nChurn: 5%/month\n\nLTV = $50 × 0.80 / 0.05 = $800\n\nHealthy LTV:CAC ratio: 3:1 or higher\n```\n\n**Example Events:**\n```javascript\n// Revenue events\ntrack('subscription_started', {\n  user_id: 'usr_123',\n  plan: 'pro',\n  mrr: 29.99,\n  billing_cycle: 'monthly'\n});\n\ntrack('upgrade_completed', {\n  user_id: 'usr_123',\n  from_plan: 'basic',\n  to_plan: 'pro',\n  mrr_change: 20.00\n});\n```\n\n### AARRR Metrics Dashboard\n\n```markdown\n## Acquisition\n- Total visitors: 50,000\n- Sign-ups: 2,500 (5% conversion)\n- Top channels: Organic (40%), Paid (30%), Referral (20%)\n\n## Activation\n- Activated users: 1,750 (70% of sign-ups)\n- Time to activation: 3.2 hours (median)\n- Activation funnel drop-off: 30% at setup step 2\n\n## Retention\n- Day 1: 60%\n- Day 7: 35%\n- Day 30: 20%\n- Churn: 5%/month\n\n## Referral\n- K-factor: 0.4\n- Users referring: 15%\n- Invites per user: 4.2\n- Invite conversion: 25%\n\n## Revenue\n- MRR: $125,000\n- ARPU: $50\n- LTV: $800\n- LTV:CAC: 4:1\n- Conversion to paid: 25%\n```\n\n---\n\n## Key Metrics & Formulas\n\n### Engagement Metrics\n\n```\nDaily Active Users (DAU)\n= Unique users performing key action per day\n\nMonthly Active Users (MAU)\n= Unique users performing key action per month\n\nStickiness = DAU / MAU × 100%\n• 20%+ = Good (users engage 6+ days/month)\n• 10-20% = Average\n• <10% = Low engagement\n\nSession Duration\n= Average time between session start and end\n\nSession Frequency\n= Average sessions per user per time period\n```\n\n### Retention Metrics\n\n```\nRetention Rate (Classic)\n= Users active in Week N / Users in original cohort\n\nRetention Rate (Bracket)\n= Users active in Week N / Users active in Week 0\n\nChurn Rate\n= (Users at start - Users at end) / Users at start\n\nQuick Ratio (Growth Health)\n= (New MRR + Expansion MRR) / (Churned MRR + Contraction MRR)\n• >4 = Excellent growth\n• 2-4 = Good\n• <1 = Shrinking\n```\n\n### Conversion Metrics\n\n```\nConversion Rate\n= (Conversions / Total visitors) × 100%\n\nFunnel Conversion\n= (Users completing final step / Users entering funnel) × 100%\n\nTime to Convert\n= Median time from first touch to conversion\n```\n\n### Revenue Metrics\n\n```\nMonthly Recurring Revenue (MRR)\n= Sum of all monthly subscription values\n\nAnnual Recurring Revenue (ARR)\n= MRR × 12\n\nAverage Revenue Per User (ARPU)\n= Total revenue / Number of users\n\nCustomer Lifetime Value (LTV)\n= ARPU × Average customer lifetime (months)\nOR\n= ARPU × Gross Margin % / Monthly Churn Rate\n\nCustomer Acquisition Cost (CAC)\n= Total sales & marketing spend / New customers acquired\n\nLTV:CAC Ratio\n= LTV / CAC\n• >3:1 = Healthy\n• 1:1 = Unsustainable\n\nPayback Period\n= CAC / (ARPU × Gross Margin %)\n• <12 months = Good\n• 12-18 months = Acceptable\n• >18 months = Concerning\n```\n\n---\n\n## Event Tracking Best Practices\n\n### Event Naming Convention\n\n```\nObject + Action pattern (recommended)\n\n✓ user_signed_up\n✓ project_created\n✓ file_uploaded\n✓ payment_completed\n\n✗ signup (unclear)\n✗ new_project (inconsistent)\n✗ Upload File (inconsistent case)\n```\n\n### Event Properties Structure\n\n```javascript\n// Standard event structure\n{\n  event: \"checkout_completed\",        // Event name\n  timestamp: \"2025-12-16T10:30:00Z\",  // When\n  user_id: \"usr_123\",                 // Who\n  session_id: \"ses_abc\",              // Session context\n  properties: {                       // Event-specific data\n    order_id: \"ord_789\",\n    total_amount: 99.99,\n    currency: \"USD\",\n    item_count: 3,\n    payment_method: \"credit_card\",\n    coupon_used: true,\n    discount_amount: 10.00\n  },\n  context: {                          // Global context\n    app_version: \"2.4.1\",\n    platform: \"web\",\n    user_agent: \"...\",\n    ip: \"192.168.1.1\",\n    locale: \"en-US\"\n  }\n}\n```\n\n### Critical Events to Track\n\n```markdown\n## User Lifecycle\n- user_signed_up\n- user_activated (first key action)\n- user_onboarded (completed setup)\n- user_upgraded (plan change)\n- user_churned (canceled/inactive)\n\n## Feature Usage\n- feature_viewed\n- feature_used\n- feature_completed\n\n## Commerce\n- product_viewed\n- product_added_to_cart\n- checkout_started\n- payment_completed\n- order_fulfilled\n\n## Engagement\n- session_started\n- session_ended\n- page_viewed\n- search_performed\n- content_shared\n\n## Errors\n- error_occurred\n- payment_failed\n- api_error\n```\n\n### Privacy & Compliance\n\n```javascript\n// ✓ GOOD: No PII in events\ntrack('user_signed_up', {\n  user_id: hashUserId('user@example.com'),  // Hashed\n  plan: 'pro',\n  source: 'organic'\n});\n\n// ✗ BAD: Contains PII\ntrack('user_signed_up', {\n  email: 'user@example.com',  // PII!\n  password: '...',            // Never log!\n  credit_card: '...'          // Never log!\n});\n\n// Masking strategies\nconst maskEmail = (email) => {\n  const [name, domain] = email.split('@');\n  return `${name[0]}***@${domain}`;\n};\n\nconst maskCard = (card) => `****${card.slice(-4)}`;\n```\n\n---\n\n## See Also\n\n- [reference/event-tracking.md](reference/event-tracking.md) — Event tracking and data modeling guide\n- [reference/metrics-framework.md](reference/metrics-framework.md) — North Star, AARRR, key metrics deep dive\n- [reference/experimentation.md](reference/experimentation.md) — A/B testing and statistical best practices\n- [reference/retention.md](reference/retention.md) — Cohort analysis and retention strategies\n- [templates/tracking-plan.md](templates/tracking-plan.md) — Event tracking plan template","tags":["product","analytics","claude","arsenal","majiayu000","agent-skills","ai-agents","ai-coding-assistant","automation","claude-code","code-review","developer-tools"],"capabilities":["skill","source-majiayu000","skill-product-analytics","topic-agent-skills","topic-ai-agents","topic-ai-coding-assistant","topic-automation","topic-claude","topic-claude-code","topic-code-review","topic-developer-tools","topic-devops","topic-productivity","topic-prompt-engineering","topic-python"],"categories":["claude-arsenal"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/majiayu000/claude-arsenal/product-analytics","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add majiayu000/claude-arsenal","source_repo":"https://github.com/majiayu000/claude-arsenal","install_from":"skills.sh"}},"qualityScore":"0.464","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 29 github stars · SKILL.md body (14,553 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-01T07:01:15.220Z","embedding":null,"createdAt":"2026-04-18T22:24:19.816Z","updatedAt":"2026-05-01T07:01:15.220Z","lastSeenAt":"2026-05-01T07:01:15.220Z","tsv":"'+1234567890':135 '-0.05':400 '-12':1559 '-16':1560 '-18':1510 '-20':1325 '-4':1402,1739 '-5':702 '/month':1144,1255 '0':178,1374,1733 '0.05':371,444,1148 '0.10':381 '0.20':1033 '0.30':1035,1036 '0.4':1260 '0.80':375,1147 '000':847,1201,1274 '00z':1563 '1':595,629,727,943,1038,1044,1048,1155,1220,1245,1282,1404,1495,1497,1498 '1/7/30':450,897,908 '10':366,382,1324,1327 '10.00':1602 '100':337,1317,1413,1423 '1000':938 '12':1451,1506,1509 '123':874,964,1063,1074,1169,1183,1568 '125':1273 '14':396 '15':971,1263 '18':1513 '192.168.1.1':139,1614 '2':597,648,802,846,1205,1242,1401 '2.4.1':1608 '2.5':295,884 '20':1216,1252,1318 '20.00':1192 '2025':1558 '25':1270,1286 '29.99':1173 '3':308,599,671,701,885,1067,1154,1494,1592 '3.2':1230 '30':853,952,1214,1238,1251,1562 '300':946 '300/1000':951 '35':1249 '3842':391 '4':601,689,972,1281,1398 '4.2':1267 '40':1212 '4111':143 '42':967 '456':1079 '5':342,403,862,1034,1082,1143,1207,1254 '50':1146,1200,1276 '50/month':1138 '500':1206 '6':1322 '60':1246 '7':945,949,1248 '70':1222 '750':1221 '789':1584 '80':376,1141 '800':1149,1278 '95':372 '99.99':305,1587 'a/b':17,320,439,1761 'aarrr':23,430,705,711,1193,1754 'abc':1573 'accept':1512 'acquir':1488 'acquisit':720,728,752,766,1051,1197,1479 'across':717 'action':40,181,191,226,245,280,623,829,834,876,1056,1300,1311,1524,1633 'activ':287,293,562,569,582,614,721,803,824,830,867,870,875,882,912,1217,1218,1229,1233,1293,1304,1354,1366,1371,1630 'ad':619,1657 'address':138 'adopt':839 'agent':1612 'aha':646,815,842 'airbnb':427,553 'align':82 'also':1741 'amount':1586,1601 'amplitud':574 'analysi':26,28,448,456,1770 'analyt':3,5,32,579 'analyz':20 'annual':1446 'anonymized/hashed':146 'api':1682 'app':273,757,1606 'appli':314 'around':85 'arpu':1115,1131,1137,1275,1456,1466,1472,1503 'arr':1449 'attribut':465,470 'averag':1111,1326,1332,1341,1452,1467 'avg':1024 'avoid':67 'b':340 'back':891 'bad':1705 'basic':1186 'behavior':59,588,696 'best':492,744,902,1105,1518,1765 'bill':1174 'book':426,555,660 'bracket':1364 'brand':790 'break':699 'bring':1043 'broad':164 'busi':44,508,676,1087 'button':220,268 'cac':1100,1121,1152,1280,1481,1490,1493,1502 'calcul':384,923,1129 'camelcas':205 'campaign':789 'canceled/inactive':1644 'captur':493,514 'card':142,312,1596,1719,1737 'card.slice':1738 'cart':1659 'case':193,218,223,228,1544 'centric':56 'chang':685,1191,1641 'channel':742,763,768,1064,1080,1210 'characterist':510 'checkout':243,301,358,1553,1660 'churn':905,915,1127,1134,1142,1253,1375,1394,1476,1643 'classic':1352 'click':221,269 'coeffici':985,999,1019 'cohort':27,447,900,935,937,1361,1769 'come':739,890 'commerc':1653 'compani':537,538 'complet':241,302,657,832,836,1179,1417,1535,1554,1636,1652,1663 'compli':76 'complianc':1685 'concern':1515 'conclus':333 'confid':373 'connect':860 'const':169,172,354,1724,1727,1735 'contain':113,1706 'content':666,1675 'context':261,1575,1603,1605 'contract':1396 'convent':1522 'convers':344,364,433,453,769,1012,1029,1123,1208,1269,1283,1406,1408,1410,1415,1433 'convert':1070,1426 'core':33,495,549,586,631,807 'correct':105 'correl':518,674 'cost':750,764,1480 'count':307,966,1591 'countri':162 'coupon':313,1597 'cover':22 'cpa':753,767 'cpc':787 'creat':215,235,617,667,879,1531 'credit':141,311,1595,1718 'critic':1619 'cta':801 'currenc':1588 'custom':501,715,1093,1116,1462,1468,1478,1487 'cycl':1175 'daili':561,613,956,1292 'dark':289 'dashboard':1195 'data':47,75,1580,1747 'data-driven':46 'dau':1295,1315 'dau/mau':921 'day':395,449,896,907,924,930,944,948,968,1244,1247,1250,1302 'days/month':1323 'decis':49,252 'deep':1757 'defin':14,626,690 'definit':482,726 'degrad':399 'deliv':499,559 'deliveri':517 'design':11 'detect':379 'discount':1600 'discov':731 'dive':1758 'doe':132 'doesn':275 'domain':174,179,1729,1734 'draw':332 'drive':251,605,697,904 'driven':48 'driver':557 'drop':458,1236 'drop-off':457,1235 'dropbox':581,855 'durat':394,1331 'e.g':658,663,668 'earli':335 'effect':380,477,572 'email':127,171,1065,1081,1712,1726 'email.split':175,1730 'en':1617 'en-us':1616 'end':1338,1382,1670 'engag':446,564,662,957,1290,1321,1329,1666 'enjoy':552 'enter':1421 'entir':529 'error':1677,1678,1683 'event':12,109,110,121,182,185,772,865,954,1053,1159,1162,1516,1520,1545,1550,1552,1555,1578,1620,1691,1744,1776 'event-specif':1577 'exampl':535,607,771,841,864,936,953,1031,1052,1136,1158 'excel':1399 'expans':1392 'experi':319,352,471,806 'experiment':30 'experimentconfig':355 'expert':8 'facebook':567 'factor':988,1002,1259 'fail':1681 'fals':68 'featur':286,288,437,463,838,919,1645,1647,1649,1651 'file':208,237,585,858,1532,1542 'final':1418 'find':649 'first':72,820,828,857,877,1430,1631 'five':718 'flow':359,362 'focus':38,81 'follow':92,188,852 'forbidden':118,196,257,331 'format':194 'formula':1289 'foundat':573 'framework':24,590,706,712 'framework/tool':412 'frequenc':918,1340 'fulfil':1665 'funnel':25,455,1234,1414,1422 'gdpr/ccpa':78 'generat':1086 'generic':271 'get':645 'global':1604 'good':512,1319,1403,1508,1687 'googl':784 'gross':1132,1139,1473,1504 'grow':505 'growth':7,428,1040,1388,1400 'guardrail':392 'guid':1749 'hard':89 'hash':155,157,1700 'hashuserid':1698 'health':417,1389 'healthi':1150,1496 'higher':343,1157 'homepag':800 'hour':294,883,1231 'hypothes':50 'hypothesi':360 'id':154,872,962,1061,1072,1077,1167,1181,1566,1571,1582,1697 'identifi':115,147,630 'impact':464 'incent':995 'inconsist':197,1540,1543 'increas':363,680,682 'indic':277,534 'inform':116 'input':594,596,598,600,692,704 'insight':266,580 'instal':758 'invit':1007,1011,1025,1028,1058,1264,1268 'ip':137,1613 'item':306,1590 'iter':53 'jan':942 'javascript':117,195,256,330,773,866,955,1054,1160,1548,1686 'job':635 'john':131 'k':987,1001,1020,1032,1037,1047,1258 'k-factor':986,1000,1257 'kebab':217 'kebab-cas':216 'keep':889 'key':87,413,703,734,810,833,892,979,1089,1287,1299,1310,1632,1755 'lag':533 'land':774,781 'lead':531 'learn':52,576 'level':370 'librari':621 'lifecycl':716,1625 'lifetim':1094,1117,1463,1469 'lift':383 'linkedin':859 'listen':423,548,612,665 'local':1615 'locat':165 'log':1717,1721 'long':818 'low':1328 'ltv':1096,1099,1119,1120,1128,1130,1145,1151,1277,1279,1465,1489,1492 'mandatori':96 'margin':1133,1140,1474,1505 'markdown':1196,1623 'market':1484 'mask':167,1722 'maskcard':1736 'maskemail':170,1725 'mau':1306,1316 'max':393 'mean':99 'measur':51,57,521 'median':1232,1427 'medium':786 'messag':669,848 'method':310,1594 'metric':15,35,41,88,246,249,255,259,281,414,420,432,481,486,490,504,541,593,603,651,688,693,708,754,825,906,997,1106,1194,1288,1291,1349,1407,1435,1756 'mileston':868 'minimum':378 'mode':290 'model':466,1748 'moment':647,816,843 'monet':1104 'month':568,1107,1176,1303,1313,1436,1443,1470,1475,1507,1511,1514 'movabl':524 'move':686 'mrr':1110,1172,1190,1272,1391,1393,1395,1397,1439,1450 'multi':468 'multi-touch':467 'music':551 'must':91,111,187,322 'n':1357,1369 'name':130,173,177,183,186,198,356,1521,1556,1728,1732 'need':1049 'net':1014 'network':571 'never':112,144,1716,1720 'new':357,361,1045,1075,1390,1486,1538 'newproject':204 'night':425,554,659 'north':79,418,479,484,539,591,1752 'nps':1017 'nsm':589,606,609,628,679,698 'nsms':513 'number':1459 'object':180,190,202,225,1523 'occur':1679 'ok':166 'onboard':1635 'one':86,489 'open':274 'optim':429,454 'ord':1583 'order':303,1581,1664 'org':530 'organ':161,1211,1704 'origin':1360 'outcom':45,284 'overal':415 'overview':709 'p':443 'page':263,775,778,780,1671 'pageview':62 'paid':1050,1125,1213,1285 'pascalcas':211 'password':1715 'pattern':1525 'payback':1500 'payment':240,309,1534,1593,1662,1680 'peopl':863 'per':389,435,461,751,762,765,1009,1026,1113,1265,1301,1312,1343,1345,1454 'perform':1298,1309,1674 'period':1347,1501 'person':114 'phone':134 'pii':107,119,129,133,136,140,1689,1707,1714 'pirat':431,707 'plan':158,1170,1185,1188,1640,1701,1778 'platform':1609 'playlist':616 'posit':69 'power':298,374,377,475 'practic':1519,1766 'principl':34 'privaci':71,1684 'privacy-first':70 'pro':159,1171,1189,1702 'product':2,4,31,416,498,515,565,587,638,684,733,808,978,1654,1656 'product-analyt':1 'product/engineering':526 'project':234,878,1530,1539 'promot':1015 'proper':324,351 'properti':122,1546,1576 'proposit':633 'qualiti':745 'question':735,811,893,980,1090 'quick':405,1386 'rate':434,452,460,770,831,837,840,910,916,1004,1013,1030,1135,1351,1363,1376,1409,1477 'ratio':1101,1122,1153,1387,1491 'reach':823 'recipi':1066 'recommend':976,1526 'recur':1108,1437,1447 'refer':406,991,1006,1023,1262 'reference/event-tracking.md':1742,1743 'reference/experimentation.md':1759,1760 'reference/metrics-framework.md':1750,1751 'reference/retention.md':1767,1768 'referr':723,973,994,1003,1055,1069,1071,1215,1256 'repres':653 'requir':145,224,279,350,368 'respect':73 'retain':901 'retent':21,451,722,886,898,909,922,926,950,1243,1348,1350,1362,1772 'return':176,928,947,1731 'revenu':556,681,724,1083,1109,1112,1126,1161,1271,1434,1438,1448,1453,1458 'revenue/growth':520 'rigor':64,317 'rule':90,94 'run':16 'sale':1483 'sampl':325,385,387 'scenario':411 'score':1016 'scream':222 'search':791,1673 'see':1740 'segment':297,1103 'send':845 'sent':670,1008,1059 'ses':1572 'session':959,965,1330,1335,1339,1342,1570,1574,1667,1669 'setup':353,835,1240,1637 'share':584,1676 'share/social':622 'shrink':1405 'sign':125,151,231,760,793,940,1203,1225,1528,1627,1694,1710 'sign-up':759,792,1202,1224 'signific':66,328,349,369,442,476 'signup':200,797,970,1536 'sinc':969 'size':326,386,388,478 'skill':101 'skill-product-analytics' 'slack':560,844 'snake':192,227 'song':618 'sourc':160,783,799,1703 'source-majiayu000' 'space':209 'specif':1579 'spend':1485 'spent':422,547,611 'spotifi':424,545,608 'stage':436,719,725 'standard':1549 'star':80,419,480,485,540,592,1753 'start':244,795,798,960,1165,1336,1379,1385,1661,1668 'statist':63,316,348,367,441,473,1764 'step':462,1241,1419 'sticki':566,920,1314 'stop':397,401 'strategi':1723,1773 'structur':1547,1551 'subscript':1164,1444 'succeed':509 'success':472,677 'sum':1440 'support':602,691 'sustain':506 't10':1561 'team':84,563,850 'templat':1779 'templates/tracking-plan.md':1774,1775 'test':18,321,440,474,1762 'threshold':329 'tie':42,282 'time':291,421,546,610,661,664,826,880,1227,1333,1346,1424,1428 'timestamp':1557 'top':1209 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding-assistant' 'topic-automation' 'topic-claude' 'topic-claude-code' 'topic-code-review' 'topic-developer-tools' 'topic-devops' 'topic-productivity' 'topic-prompt-engineering' 'topic-python' 'total':932,1198,1411,1457,1482,1585 'touch':469,1431 'track':13,58,123,149,199,203,206,212,219,229,233,236,239,242,248,262,267,272,285,300,713,777,796,869,958,1057,1068,1163,1177,1517,1622,1692,1708,1745,1777 'trackabl':523 'transact':656 'true':315,1599 'twitter':851 'unclear':1537 'understand':65,527 'uniqu':1296,1307 'unsustain':1499 'up':761,1204,1226 'upgrad':1178,1639 'upload':207,238,856,1533,1541 'us':163,1618 'usag':917,1646 'usd':1589 'use':9,409,1598,1650 'user':55,74,124,150,153,214,230,296,299,338,445,570,577,583,615,641,644,695,730,738,746,805,854,871,888,913,927,933,939,961,975,990,1005,1010,1021,1027,1042,1046,1060,1076,1085,1114,1166,1180,1219,1261,1266,1294,1297,1305,1308,1320,1344,1353,1358,1365,1370,1377,1380,1383,1416,1420,1455,1461,1527,1565,1611,1624,1626,1629,1634,1638,1642,1693,1696,1709 'user-centr':54 'user-cr':213 'user@example.com':128,156,1699,1713 'usr':873,963,1062,1073,1078,1168,1182,1567 'util':168 'utm':782,785,788 'valid':438,672 'valu':278,304,496,516,550,558,578,632,655,809,821,1088,1095,1118,1445,1464 'vaniti':37,254,258 'variant':339,390 'version':1607 'view':264,776,779,1648,1655,1672 'violat':97 'viral':984,998,1018,1039 'visitor':756,1199,1412 'wau/mau':914 'web':1610 'websit':755 'week':575,1356,1368,1373 'weekly/monthly':911 'without':260 'work':104,544,996 'wors':404 'x':925,931","prices":[{"id":"420204f1-744c-4e7e-8cf6-7c1d6b13bb5d","listingId":"517bb25b-08f8-4c1b-b34a-8fdb5519bade","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"majiayu000","category":"claude-arsenal","install_from":"skills.sh"},"createdAt":"2026-04-18T22:24:19.816Z"}],"sources":[{"listingId":"517bb25b-08f8-4c1b-b34a-8fdb5519bade","source":"github","sourceId":"majiayu000/claude-arsenal/product-analytics","sourceUrl":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/product-analytics","isPrimary":false,"firstSeenAt":"2026-04-18T22:24:19.816Z","lastSeenAt":"2026-05-01T07:01:15.220Z"}],"details":{"listingId":"517bb25b-08f8-4c1b-b34a-8fdb5519bade","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"majiayu000","slug":"product-analytics","github":{"repo":"majiayu000/claude-arsenal","stars":29,"topics":["agent-skills","ai-agents","ai-coding-assistant","automation","claude","claude-code","code-review","developer-tools","devops","productivity","prompt-engineering","python","software-development","typescript","workflows"],"license":"mit","html_url":"https://github.com/majiayu000/claude-arsenal","pushed_at":"2026-04-29T04:12:22Z","description":"52 production-ready Claude Code skills and 7 specialized agents for software development, DevOps, product workflows, and automation.","skill_md_sha":"ca942a6ff94116dd5a365426bf1fb0283a1def85","skill_md_path":"skills/product-analytics/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/product-analytics"},"layout":"multi","source":"github","category":"claude-arsenal","frontmatter":{"name":"product-analytics","description":"Product analytics and growth expert. Use when designing event tracking, defining metrics, running A/B tests, or analyzing retention. Covers AARRR framework, funnel analysis, cohort analysis, and experimentation."},"skills_sh_url":"https://skills.sh/majiayu000/claude-arsenal/product-analytics"},"updatedAt":"2026-05-01T07:01:15.220Z"}}