analytics-product - SKILL-开发者社区

name: analytics-product
description: “Analytics de produto — PostHog, Mixpanel, eventos, funnels, cohorts, retencao, north star metric, OKRs e dashboards de produto.”
risk: none
source: community
date_added: ‘2026-03-06’
author: renat
tags:

analytics
product
metrics
posthog
mixpanel
tools:
claude-code
antigravity
cursor
gemini-cli
codex-cli

分析产品 — 用数据做决策

概览

产品分析 — PostHog、Mixpanel、事件、漏斗、群组、留存、北极星指标、OKR 和产品仪表板。启用用于：配置事件追踪、创建转化漏斗、群组分析、留存、DAU/MAU、功能开关、A/B 测试、北极星指标、OKR、产品仪表板。

何时使用此技能

当你需要在这个领域的专业帮助时

使用此技能时请勿

该任务与分析产品无关
一个更简单、更具体的工具可以处理该请求
用户需要通用帮助，而不具备领域专长

运作方式

[objeto]_[verbo_passado] Correto: user_signed_up, conversation_started, upgrade_completed Errado: signup, click, conversion

分析产品 — 用数据做决定

“我们信仰上帝，其他人必须提供数据。”——W. 埃德华兹·戴明

Auri 的重要事件

AURI_EVENTS={# Aquisicao"user_signed_up":{"props":["source","medium","campaign"]},"onboarding_started":{"props":["step_count"]},"onboarding_completed":{"props":["time_to_complete","steps_skipped"]},# Ativacao"first_conversation":{"props":["intent","response_time"]},"aha_moment_reached":{"props":["trigger","session_number"]},"feature_discovered":{"props":["feature_name","discovery_method"]},# Retencao"conversation_started":{"props":["intent","user_tier","device"]},"conversation_completed":{"props":["messages_count","duration","rating"]},"session_started":{"props":["days_since_last","platform"]},# Receita"upgrade_viewed":{"props":["trigger","current_tier"]},"upgrade_started":{"props":["target_tier","trigger"]},"upgrade_completed":{"props":["tier","plan","revenue"]},"subscription_canceled":{"props":["reason","tier","tenure_days"]},"payment_failed":{"props":["attempt_count","error_code"]},}

Posthog 实现（Python）

fromposthogimportPosthogimportos posthog=Posthog(project_api_key=os.environ["POSTHOG_API_KEY"],host=os.environ.get("POSTHOG_HOST","https://app.posthog.com"))deftrack(user_id:str,event:str,properties:dict=None):posthog.capture(distinct_id=user_id,event=event,properties=propertiesor{})defidentify(user_id:str,traits:dict):posthog.identify(distinct_id=user_id,properties=traits)## Uso:track("user_123","conversation_started",{"intent":"business_advice","device":"alexa","user_tier":"pro"})

Auri 激活漏斗

Visita landing page (100%) | [meta: 40%] Clicou "Experimentar" (40%) | [meta: 70%] Completou cadastro (28%) | [meta: 60%] Fez primeira conversa (17%) <- AHA MOMENT | [meta: 50%] Voltou no dia seguinte (8.5%) | [meta: 40%] Usou 3+ dias na semana (3.4%) | [meta: 20%] Converteu para Pro (0.7%)

优化漏斗

Para cada drop-off > benchmark: 1. Identificar: onde exatamente o usuario sai? 2. Entender: por que? (session recordings, surveys) 3. Hipotese: qual mudanca poderia melhorar? 4. Testar: A/B test com amostra estatisticamente significante 5. Medir: 2 semanas minimo, p-value < 0.05 6. Aprender: mesmo se falhar, entende-se o usuario melhor

队列分析（每周保留）

defcalculate_cohort_retention(events_df):""" events_df: DataFrame com colunas [user_id, event_date, event_name] Retorna: matriz de retencao [cohort_week x week_number] """importpandasaspd first_session=events_df[events_df.event_name=="session_started"]\.groupby("user_id")["event_date"].min()\.dt.to_period("W")sessions=events_df[events_df.event_name=="session_started"].copy()sessions["cohort"]=sessions["user_id"].map(first_session)sessions["weeks_since"]=(sessions["event_date"].dt.to_period("W")-sessions["cohort"]).apply(lambdax:x.n)cohort_data=sessions.groupby(["cohort","weeks_since"])["user_id"].nunique()cohort_sizes=cohort_data.unstack().iloc[:,0]retention=cohort_data.unstack().divide(cohort_sizes,axis=0)*100returnretention

保留基准（语音助手）

Semana	Pessimo	Ok	Bom	Excelente
W1	<20%	20-35%	35-50%	>50%
W4	<10%	10-20%	20-30%	>30%
W8	<5%	5-12%	12-20%	>20%

定义 Auri 的北极星

Framework: 1. O que cria valor real para o usuario? -> Conversas que geram insight/acao 2. O que prediz crescimento de longo prazo? -> Usuarios com 3+ conv/semana 3. Como medir? -> "Weekly Active Conversationalists" (WAC) North Star: WAC (Weekly Active Conversationalists) Definicao: Usuarios com >= 3 conversas na semana que duraram >= 2 minutos Meta Ano 1: 10.000 WAC Meta Ano 2: 100.000 WAC

仪表板北极星

defcalculate_north_star(db):wac=db.query(""" SELECT COUNT(DISTINCT user_id) as wac FROM conversations WHERE created_at >= NOW() - INTERVAL '7 days' AND duration_seconds >= 120 GROUP BY user_id HAVING COUNT(*) >= 3 """).scalar()return{"wac":wac,"wow_growth":calculate_wow_growth(db,"wac"),"target":10000,"progress":f"{wac/10000*100:.1f}%"}

Posthog 功能标志

defis_feature_enabled(user_id:str,feature:str)->bool:returnposthog.feature_enabled(feature,user_id)ifis_feature_enabled(user_id,"new-onboarding-v2"):show_new_onboarding()else:show_old_onboarding()

统计显著性计算器

fromscipyimportstatsimportnumpyasnpdefab_test_significance(control_conversions:int,control_visitors:int,variant_conversions:int,variant_visitors:int,confidence:float=0.95)->dict:control_rate=control_conversions/control_visitors variant_rate=variant_conversions/variant_visitors lift=(variant_rate-control_rate)/control_rate*100_,p_value=stats.chi2_contingency([[control_conversions,control_visitors-control_conversions],[variant_conversions,variant_visitors-variant_conversions]])[:2]significant=p_value<(1-confidence)return{"control_rate":f"{control_rate*100:.2f}%","variant_rate":f"{variant_rate*100:.2f}%","lift":f"{lift:+.1f}%","p_value":round(p_value,4),"significant":significant,"recommendation":"Deploy variant"ifsignificantandlift>0else"Keep control"}

6. 命令

Comando	Acao
`/event-taxonomy`	Define taxonomia de eventos
`/funnel-analysis`	Analisa funil de conversao
`/cohort-retention`	Calcula retencao por cohort
`/north-star`	Define ou revisa North Star Metric
`/ab-test`	Calcula significancia de A/B test
`/dashboard-setup`	Cria dashboard de produto
`/okr-template`	Template de OKRs para produto