[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-b81bf5dc-8ba9-43c8-8509-4f36c61e05e4":3,"$fRys3BQLuQCOjxWr1ZEuPM9mTjJkMbder89IiA3rBtEA":43},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":34},"b81bf5dc-8ba9-43c8-8509-4f36c61e05e4","analytics-product","产品分析——PostHog，Mixpanel，事件，漏斗，群体，留存，北极星指标，OKR和产品仪表盘。","cat_prod_data","mod_productivity","sickn33,productivity","---\nname: analytics-product\ndescription: \"Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.\"\nrisk: none\nsource: community\ndate_added: '2026-03-06'\nauthor: renat\ntags:\n- analytics\n- product\n- metrics\n- posthog\n- mixpanel\ntools:\n- claude-code\n- antigravity\n- cursor\n- gemini-cli\n- codex-cli\n---\n\n# ANALYTICS-PRODUCT — Decida com Dados\n\n## Overview\n\nAnalytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto. Ativar para: configurar tracking de eventos, criar funil de conversao, analise de cohort, retencao, DAU\u002FMAU, feature flags, A\u002FB testing, north star metric, OKRs, dashboard de produto.\n\n## When to Use This Skill\n\n- When you need specialized assistance with this domain\n\n## Do Not Use This Skill When\n\n- The task is unrelated to analytics product\n- A simpler, more specific tool can handle the request\n- The user needs general-purpose assistance without domain expertise\n\n## How It Works\n\n```\n[objeto]_[verbo_passado]\n\nCorreto:   user_signed_up, conversation_started, upgrade_completed\nErrado:    signup, click, conversion\n```\n\n## Analytics-Product — Decida Com Dados\n\n> \"In God we trust. All others must bring data.\" — W. Edwards Deming\n\n---\n\n## Eventos Essenciais Da Auri\n\n```python\nAURI_EVENTS = {\n    # Aquisicao\n    \"user_signed_up\":        {\"props\": [\"source\", \"medium\", \"campaign\"]},\n    \"onboarding_started\":    {\"props\": [\"step_count\"]},\n    \"onboarding_completed\":  {\"props\": [\"time_to_complete\", \"steps_skipped\"]},\n\n    # Ativacao\n    \"first_conversation\":    {\"props\": [\"intent\", \"response_time\"]},\n    \"aha_moment_reached\":    {\"props\": [\"trigger\", \"session_number\"]},\n    \"feature_discovered\":    {\"props\": [\"feature_name\", \"discovery_method\"]},\n\n    # Retencao\n    \"conversation_started\":  {\"props\": [\"intent\", \"user_tier\", \"device\"]},\n    \"conversation_completed\":{\"props\": [\"messages_count\", \"duration\", \"rating\"]},\n    \"session_started\":       {\"props\": [\"days_since_last\", \"platform\"]},\n\n    # Receita\n    \"upgrade_viewed\":        {\"props\": [\"trigger\", \"current_tier\"]},\n    \"upgrade_started\":       {\"props\": [\"target_tier\", \"trigger\"]},\n    \"upgrade_completed\":     {\"props\": [\"tier\", \"plan\", \"revenue\"]},\n    \"subscription_canceled\": {\"props\": [\"reason\", \"tier\", \"tenure_days\"]},\n    \"payment_failed\":        {\"props\": [\"attempt_count\", \"error_code\"]},\n}\n```\n\n## Implementacao Posthog (Python)\n\n```python\nfrom posthog import Posthog\nimport os\n\nposthog = Posthog(\n    project_api_key=os.environ[\"POSTHOG_API_KEY\"],\n    host=os.environ.get(\"POSTHOG_HOST\", \"https:\u002F\u002Fapp.posthog.com\")\n)\n\ndef track(user_id: str, event: str, properties: dict = None):\n    posthog.capture(\n        distinct_id=user_id,\n        event=event,\n        properties=properties or {}\n    )\n\ndef identify(user_id: str, traits: dict):\n    posthog.identify(\n        distinct_id=user_id,\n        properties=traits\n    )\n\n## Uso:\n\ntrack(\"user_123\", \"conversation_started\", {\n    \"intent\": \"business_advice\",\n    \"device\": \"alexa\",\n    \"user_tier\": \"pro\"\n})\n```\n\n---\n\n## Funil De Ativacao Auri\n\n```\nVisita landing page          (100%)\n    | [meta: 40%]\nClicou \"Experimentar\"         (40%)\n    | [meta: 70%]\nCompletou cadastro            (28%)\n    | [meta: 60%]\nFez primeira conversa         (17%)  \u003C- AHA MOMENT\n    | [meta: 50%]\nVoltou no dia seguinte        (8.5%)\n    | [meta: 40%]\nUsou 3+ dias na semana        (3.4%)\n    | [meta: 20%]\nConverteu para Pro            (0.7%)\n```\n\n## Otimizando O Funil\n\n```\nPara cada drop-off > benchmark:\n1. Identificar: onde exatamente o usuario sai?\n2. Entender: por que? (session recordings, surveys)\n3. Hipotese: qual mudanca poderia melhorar?\n4. Testar: A\u002FB test com amostra estatisticamente significante\n5. Medir: 2 semanas minimo, p-value \u003C 0.05\n6. Aprender: mesmo se falhar, entende-se o usuario melhor\n```\n\n---\n\n## Analise De Cohort (Retencao Semanal)\n\n```python\ndef calculate_cohort_retention(events_df):\n    \"\"\"\n    events_df: DataFrame com colunas [user_id, event_date, event_name]\n    Retorna: matriz de retencao [cohort_week x week_number]\n    \"\"\"\n    import pandas as pd\n\n    first_session = events_df[events_df.event_name == \"session_started\"] \\\n        .groupby(\"user_id\")[\"event_date\"].min() \\\n        .dt.to_period(\"W\")\n\n    sessions = events_df[events_df.event_name == \"session_started\"].copy()\n    sessions[\"cohort\"] = sessions[\"user_id\"].map(first_session)\n    sessions[\"weeks_since\"] = (\n        sessions[\"event_date\"].dt.to_period(\"W\") - sessions[\"cohort\"]\n    ).apply(lambda x: x.n)\n\n    cohort_data = sessions.groupby([\"cohort\", \"weeks_since\"])[\"user_id\"].nunique()\n    cohort_sizes = cohort_data.unstack().iloc[:, 0]\n    retention = cohort_data.unstack().divide(cohort_sizes, axis=0) * 100\n\n    return retention\n```\n\n## Benchmarks De Retencao (Assistentes De Voz)\n\n| Semana | Pessimo | Ok | Bom | Excelente |\n|--------|---------|-----|-----|-----------|\n| W1 | \u003C20% | 20-35% | 35-50% | >50% |\n| W4 | \u003C10% | 10-20% | 20-30% | >30% |\n| W8 | \u003C5% | 5-12% | 12-20% | >20% |\n\n---\n\n## Definindo A North Star Da Auri\n\n```\nFramework:\n1. O que cria valor real para o usuario? -> Conversas que geram insight\u002Facao\n2. O que prediz crescimento de longo prazo? -> Usuarios com 3+ conv\u002Fsemana\n3. Como medir? -> \"Weekly Active Conversationalists\" (WAC)\n\nNorth Star: WAC (Weekly Active Conversationalists)\nDefinicao: Usuarios com >= 3 conversas na semana que duraram >= 2 minutos\n\nMeta Ano 1: 10.000 WAC\nMeta Ano 2: 100.000 WAC\n```\n\n## Dashboard North Star\n\n```python\ndef calculate_north_star(db):\n    wac = db.query(\"\"\"\n        SELECT COUNT(DISTINCT user_id) as wac\n        FROM conversations\n        WHERE\n            created_at >= NOW() - INTERVAL '7 days'\n            AND duration_seconds >= 120\n        GROUP BY user_id\n        HAVING COUNT(*) >= 3\n    \"\"\").scalar()\n\n    return {\n        \"wac\": wac,\n        \"wow_growth\": calculate_wow_growth(db, \"wac\"),\n        \"target\": 10000,\n        \"progress\": f\"{wac\u002F10000*100:.1f}%\"\n    }\n```\n\n---\n\n## Feature Flags Com Posthog\n\n```python\ndef is_feature_enabled(user_id: str, feature: str) -> bool:\n    return posthog.feature_enabled(feature, user_id)\n\nif is_feature_enabled(user_id, \"new-onboarding-v2\"):\n    show_new_onboarding()\nelse:\n    show_old_onboarding()\n```\n\n## Calculadora De Significancia Estatistica\n\n```python\nfrom scipy import stats\nimport numpy as np\n\ndef ab_test_significance(\n    control_conversions: int,\n    control_visitors: int,\n    variant_conversions: int,\n    variant_visitors: int,\n    confidence: float = 0.95\n) -> dict:\n    control_rate = control_conversions \u002F control_visitors\n    variant_rate = variant_conversions \u002F variant_visitors\n    lift = (variant_rate - control_rate) \u002F control_rate * 100\n\n    _, p_value = stats.chi2_contingency([\n        [control_conversions, control_visitors - control_conversions],\n        [variant_conversions, variant_visitors - variant_conversions]\n    ])[:2]\n\n    significant = p_value \u003C (1 - confidence)\n\n    return {\n        \"control_rate\": f\"{control_rate*100:.2f}%\",\n        \"variant_rate\": f\"{variant_rate*100:.2f}%\",\n        \"lift\": f\"{lift:+.1f}%\",\n        \"p_value\": round(p_value, 4),\n        \"significant\": significant,\n        \"recommendation\": \"Deploy variant\" if significant and lift > 0 else \"Keep control\"\n    }\n```\n\n---\n\n## 6. Comandos\n\n| Comando | Acao |\n|---------|------|\n| `\u002Fevent-taxonomy` | Define taxonomia de eventos |\n| `\u002Ffunnel-analysis` | Analisa funil de conversao |\n| `\u002Fcohort-retention` | Calcula retencao por cohort |\n| `\u002Fnorth-star` | Define ou revisa North Star Metric |\n| `\u002Fab-test` | Calcula significancia de A\u002FB test |\n| `\u002Fdashboard-setup` | Cria dashboard de produto |\n| `\u002Fokr-template` | Template de OKRs para produto |\n\n## Best Practices\n\n- Provide clear, specific context about your project and requirements\n- Review all suggestions before applying them to production code\n- Combine with other complementary skills for comprehensive analysis\n\n## Common Pitfalls\n\n- Using this skill for tasks outside its domain expertise\n- Applying recommendations without understanding your specific context\n- Not providing enough project context for accurate analysis\n\n## Related Skills\n\n- `growth-engine` - Complementary skill for enhanced analysis\n- `monetization` - Complementary skill for enhanced analysis\n- `product-design` - Complementary skill for enhanced analysis\n- `product-inventor` - Complementary skill for enhanced analysis\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,235,1881,"2026-05-16 13:02:38",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"效率工具","productivity","mdi-lightning-bolt-outline","文档处理、数据分析、自动化工作流",4,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":32,"skillCount":33,"createdAt":26},"数据分析","data-analysis","mdi-chart-bar","数据可视化、统计分析",2,30,[35],{"id":36,"skillId":4,"version":37,"fileName":38,"fileSize":39,"filePath":40,"fileHash":41,"manifest":42,"createdAt":19},"04ae6f39-b2d8-4937-84e5-81f89dae2014","1.0.0","analytics-product.zip",3789,"uploads\u002Fskills\u002Fb81bf5dc-8ba9-43c8-8509-4f36c61e05e4\u002Fanalytics-product.zip","93a60539821df2dd8eff02e502780aee40b0295f6e5acd01e185cb369ae0135a","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":8783}]",{"code":44,"message":45,"data":46},200,"success",{"items":47,"stats":48,"page":51},[],{"averageRating":49,"totalRatings":49,"ratingCounts":50},0,[49,49,49,49,49],{"limit":52,"offset":49,"hasMore":53,"nextOffset":52,"ratedOnly":16},15,false]