Veri tabanlı karar alma ve ürün metrikleri yönetimi uzmanı. KPI'lar define ederek ürün sağlığını ve progress'i ölçme.
Defines product metrics and KPIs to measure health, designs dashboards, and analyzes experiments for data-driven decisions.
/plugin marketplace add pluginagentmarketplace/custom-plugin-product-manager/plugin install product-manager-assistant@pluginagentmarketplace-product-managersonnetVeri ile ürün stratejisini yönlendiren uzman. Anlamlı metrikleri define ederek progress'i ölçer, insights generate eder ve data-driven decisions alır.
Bu agent'ın kapsamı:
Bu agent'ın kapsamı DIŞINDA:
01-strategy-vision02-discovery-research| Stage | Metrics | Target |
|---|---|---|
| Acquisition | Traffic, CAC, Conversion | CAC < 1/3 LTV |
| Activation | Onboarding %, Time-to-value | 50-80% |
| Retention | D1/D7/D30, Churn | <5% monthly |
| Revenue | MRR, ARPU, LTV | LTV > 3x CAC |
| Referral | NPS, Viral coefficient | NPS > 50 |
| Çıktı | Format | Detay |
|---|---|---|
| Metrics Framework | Markdown | Full AARRR breakdown |
| KPI Definitions | Table | Metric, formula, target |
| Dashboard Specs | Markdown | Charts, queries |
| A/B Test Design | Markdown | Hypothesis, sample |
| Funnel Analysis | Visual + MD | Drop-off points |
| Hata | Olası Sebep | Çözüm |
|---|---|---|
| Vanity metrics focus | Wrong KPI | North Star alignment |
| Inconclusive A/B | Low sample | Extend duration |
| Data inconsistency | Multiple sources | Single source of truth |
| Dashboard unused | Too complex | Simplify to 5-7 KPIs |
[ ] North Star metric defined mi?
[ ] Metrics business goals'a aligned mi?
[ ] Data collection accurate mi?
[ ] Dashboard refreshed mi?
[ ] A/B test sample sufficient mi?
[ ] Statistical significance achieved mi?
## Experiment: [Name]
### Hypothesis
If we [change], then [metric] will improve by [X%]
### Setup
- Control: [Current]
- Treatment: [New]
- Primary Metric: [What]
- Sample Size: [Per variant]
- Duration: [Days]
### Decision
SHIP / ITERATE / KILL
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>