{"id":"da265eb5-ba2b-4b40-b435-c2e63dad1676","shortId":"HxLyYa","kind":"skill","title":"analytics-product","tagline":"Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.","description":"# 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/MAU, feature flags, A/B 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://app.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%)  <- 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/B test com amostra estatisticamente significante\n5. Medir: 2 semanas minimo, p-value < 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 | <20% | 20-35% | 35-50% | >50% |\n| W4 | <10% | 10-20% | 20-30% | >30% |\n| W8 | <5% | 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/acao\n2. O que prediz crescimento de longo prazo? -> Usuarios com 3+ conv/semana\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/10000*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 / control_visitors\n    variant_rate = variant_conversions / variant_visitors\n    lift = (variant_rate - control_rate) / 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 < (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| `/event-taxonomy` | Define taxonomia de eventos |\n| `/funnel-analysis` | Analisa funil de conversao |\n| `/cohort-retention` | Calcula retencao por cohort |\n| `/north-star` | Define ou revisa North Star Metric |\n| `/ab-test` | Calcula significancia de A/B test |\n| `/dashboard-setup` | Cria dashboard de produto |\n| `/okr-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.","tags":["analytics","product","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-analytics-product","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/analytics-product","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34964 github stars · SKILL.md body (8,400 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":"2026-04-25T00:50:25.576Z","embedding":null,"createdAt":"2026-04-18T21:30:53.433Z","updatedAt":"2026-04-25T00:50:25.576Z","lastSeenAt":"2026-04-25T00:50:25.576Z","tsv":"'-12':568 '-20':561,570 '-30':563 '-35':554 '-50':556 '/ab-test':870 '/cohort-retention':858 '/dashboard-setup':876 '/event-taxonomy':848 '/funnel-analysis':853 '/north-star':863 '/okr-template':881 '0':529,536,840 '0.05':420 '0.7':374 '0.95':763 '1':384,579,630,804 '10':559,560 '10.000':631 '100':335,537,692,784,812,819 '100.000':636 '10000':688 '12':569 '120':668 '123':317 '17':351 '1f':693,824 '2':391,414,592,626,635,800 '20':370,552,553,562,571 '28':345 '2f':813,820 '3':364,398,602,604,620,675 '3.4':368 '30':564 '35':555 '4':404,830 '40':337,340,362 '5':412,566,567 '50':355,557 '6':421,844 '60':347 '7':663 '70':342 '8.5':360 'a/b':62,406,874 'ab':746 'acao':847 'accur':939 'activ':608,615 'advic':322 'aha':187,352 'alexa':324 'amostra':409 'analis':55,432 'analisa':854 'analysi':914,940,950,956,964,972 'analyt':2,4,22,28,95,135 'analytics-product':1,21,134 'ano':629,634 'api':269,273 'app.posthog.com':279 'appli':512,902,926 'aprend':422 'aquisicao':159 'ask':1006 'assist':80,112 'assistent':543 'ativacao':180,330 'ativar':45 'attempt':252 'auri':155,157,331,577 'axi':535 'benchmark':383,540 'best':887 'bom':549 'bool':708 'boundari':1014 'bring':147 'busi':321 'cada':379 'cadastro':344 'calcul':439,643,682 'calcula':859,871 'calculadora':732 'campaign':166 'cancel':243 'clarif':1008 'clear':890,981 'click':132 'clicou':338 'code':255,906 'cohort':11,35,57,434,440,459,494,511,516,519,525,533,862 'cohort_data.unstack':527,531 'coluna':448 'com':25,138,408,447,601,619,696 'comando':845,846 'combin':907 'common':915 'como':605 'complementari':910,946,952,960,968 'complet':129,173,177,210,237 'completou':343 'comprehens':913 'confid':761,805 'configurar':47 'context':892,932,937 'control':749,752,765,767,769,780,782,788,790,792,807,810,843 'conv/semana':603 'convers':126,133,182,202,209,318,657,750,756,768,774,789,793,795,799 'conversa':350,588,621 'conversao':54,857 'conversationalist':609,616 'converteu':371 'copi':492 'correto':122 'count':171,213,253,650,674 'creat':659 'crescimento':596 'cria':582,877 'criar':51 'criteria':1017 'current':228 'da':154,576 'dado':26,139 'dashboard':18,42,68,638,878 'data':148,517 'datafram':446 'date':452,480,506 'dau/mau':59 'day':219,248,664 'db':646,685 'db.query':648 'de':5,19,29,43,49,53,56,69,329,433,457,541,544,597,733,851,856,873,879,883 'decida':24,137 'def':280,300,438,642,699,745 'defin':849,864 'definicao':617 'definindo':572 'deme':151 'deploy':834 'describ':985 'design':959 'devic':208,323 'df':443,445,471,487 'dia':358,365 'dict':288,306,764 'discov':195 'discoveri':199 'distinct':291,308,651 'divid':532 'domain':83,114,924 'drop':381 'drop-off':380 'dt.to':482,507 'duraram':625 'durat':214,666 'e':17,41 'edward':150 'els':728,841 'enabl':702,711,718 'engin':945 'enhanc':949,955,963,971 'enough':935 'entend':392,427 'entende-s':426 'environ':997 'environment-specif':996 'errado':130 'error':254 'essenciai':153 'estatistica':735 'estatisticament':410 'event':158,285,295,296,442,444,451,453,470,479,486,505 'evento':9,33,50,152,852 'events_df.event':472,488 'exatament':387 'excelent':550 'experimentar':339 'expert':1002 'expertis':115,925 'f':690,809,816,822 'fail':250 'falhar':425 'featur':60,194,197,694,701,706,712,717 'fez':348 'first':181,468,499 'flag':61,695 'float':762 'framework':578 'funil':52,328,377,855 'funnel':10,34 'general':110 'general-purpos':109 'geram':590 'god':141 'group':669 'groupbi':476 'growth':681,684,944 'growth-engin':943 'handl':103 'hipotes':399 'host':275,278 'id':283,292,294,303,309,311,450,478,497,523,653,672,704,714,720 'identifi':301 'identificar':385 'iloc':528 'implementacao':256 'import':262,264,464,739,741 'input':1011 'insight/acao':591 'int':751,754,757,760 'intent':184,205,320 'interv':662 'inventor':967 'keep':842 'key':270,274 'lambda':513 'land':333 'last':221 'lift':777,821,823,839 'limit':973 'longo':598 'map':498 'match':982 'matriz':456 'medir':413,606 'medium':165 'melhor':431 'melhorar':403 'mesmo':423 'messag':212 'meta':336,341,346,354,361,369,628,633 'method':200 'metric':15,39,66,869 'min':481 'minimo':416 'minuto':627 'miss':1019 'mixpanel':8,32 'moment':188,353 'monet':951 'mudanca':401 'must':146 'na':366,622 'name':198,454,473,489 'need':78,108 'new':722,726 'new-onboarding-v2':721 'none':289 'north':13,37,64,574,611,639,644,867 'np':744 'number':193,463 'numpi':742 'nuniqu':524 'o':376,388,429,580,586,593 'objeto':119 'ok':548 'okr':16,40,67,884 'old':730 'onboard':167,172,723,727,731 'ond':386 'os':265 'os.environ':271 'os.environ.get':276 'other':145 'otimizando':375 'ou':865 'output':991 'outsid':922 'overview':27 'p':418,785,802,825,828 'p-valu':417 'page':334 'panda':465 'para':46,372,378,585,885 'passado':121 'payment':249 'pd':467 'period':483,508 'permiss':1012 'pessimo':547 'pitfal':916 'plan':240 'platform':222 'poderia':402 'por':393,861 'posthog':7,31,257,261,263,266,267,272,277,697 'posthog.capture':290 'posthog.feature':710 'posthog.identify':307 'practic':888 'prazo':599 'prediz':595 'primeira':349 'pro':327,373 'product':3,23,96,136,905,958,966 'product-design':957 'product-inventor':965 'produto':6,20,30,44,70,880,886 'progress':689 'project':268,895,936 'prop':163,169,174,183,190,196,204,211,218,226,232,238,244,251 'properti':287,297,298,312 'provid':889,934 'purpos':111 'python':156,258,259,437,641,698,736 'qual':400 'que':394,581,589,594,624 'rate':215,766,772,779,781,783,808,811,815,818 'reach':189 'real':584 'reason':245 'receita':223 'recommend':833,927 'record':396 'relat':941 'request':105 'requir':897,1010 'respons':185 'retencao':12,36,58,201,435,458,542,860 'retent':441,530,539 'retorna':455 'return':538,677,709,806 'revenu':241 'review':898,1003 'revisa':866 'round':827 'safeti':1013 'sai':390 'scalar':676 'scipi':738 'scope':984 'se':424,428 'second':667 'seguint':359 'select':649 'seman':436 'semana':367,415,546,623 'session':192,216,395,469,474,485,490,493,495,500,501,504,510 'sessions.groupby':518 'show':725,729 'sign':124,161 'signific':748,801,831,832,837 'significancia':734,872 'significant':411 'signup':131 'simpler':98 'sinc':220,503,521 'size':526,534 'skill':75,88,911,919,942,947,953,961,969,976 'skill-analytics-product' 'skip':179 'sourc':164 'source-sickn33' 'special':79 'specif':100,891,931,998 'star':14,38,65,575,612,640,645,868 'start':127,168,203,217,231,319,475,491 'stat':740 'stats.chi2_contingency':787 'step':170,178 'stop':1004 'str':284,286,304,705,707 'subscript':242 'substitut':994 'success':1016 'suggest':900 'survey':397 'target':233,687 'task':91,921,980 'taxonomia':850 'templat':882 'tenur':247 'test':63,407,747,875,1000 'testar':405 'tier':207,229,234,239,246,326 'time':175,186 'tool':101 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'track':48,281,315 'trait':305,313 'treat':989 'trigger':191,227,235 'trust':143 'understand':929 'unrel':93 'upgrad':128,224,230,236 'use':73,86,917,974 'user':107,123,160,206,282,293,302,310,316,325,449,477,496,522,652,671,703,713,719 'uso':314 'usou':363 'usuario':389,430,587,600,618 'v2':724 'valid':999 'valor':583 'valu':419,786,803,826,829 'variant':755,758,771,773,775,778,794,796,798,814,817,835 'verbo':120 'view':225 'visita':332 'visitor':753,759,770,776,791,797 'voltou':356 'voz':545 'w':149,484,509 'w1':551 'w4':558 'w8':565 'wac':610,613,632,637,647,655,678,679,686 'wac/10000':691 'week':460,462,502,520,607,614 'without':113,928 'work':118 'wow':680,683 'x':461,514 'x.n':515","prices":[{"id":"7488e8ff-579f-48b5-a389-3db234650d9e","listingId":"da265eb5-ba2b-4b40-b435-c2e63dad1676","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:30:53.433Z"}],"sources":[{"listingId":"da265eb5-ba2b-4b40-b435-c2e63dad1676","source":"github","sourceId":"sickn33/antigravity-awesome-skills/analytics-product","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/analytics-product","isPrimary":false,"firstSeenAt":"2026-04-18T21:30:53.433Z","lastSeenAt":"2026-04-25T00:50:25.576Z"}],"details":{"listingId":"da265eb5-ba2b-4b40-b435-c2e63dad1676","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"analytics-product","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34964,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-24T06:41:17Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"54fe553d8bc5682ed64b61bdd0e879fd40145f99","skill_md_path":"skills/analytics-product/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/analytics-product"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"analytics-product","description":"Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/analytics-product"},"updatedAt":"2026-04-25T00:50:25.576Z"}}