/metrics-track

Set up a metrics tracking plan for a project. Defines PostHog event funnel, KPI benchmarks, and kill/iterate/scale decision thresholds based on lean startup principles.

MCP Tools (use if available)

• kb_search(query) — find PostHog methodology, analytics patterns

Methodology Reference

This skill implements metrics tracking based on lean startup principles:

• Relative metrics vs niche benchmarks — compare against your own trajectory, not vanity averages
• Kill/iterate/scale decision rules — data-driven thresholds for product decisions (see step 7 below)

Steps

• Parse project from $ARGUMENTS.
• Read PRD for features, ICP, monetization model.
• Read CLAUDE.md for stack (iOS/Web/both).
• If empty: ask via AskUserQuestion.
• Detect platform:
• iOS app → PostHog iOS SDK events
• Web app → PostHog JS SDK events
• Both → cross-platform identity (shared user ID across platforms)
• Load PostHog methodology:
• If MCP available: kb_search("PostHog analytics events funnel identity")
• Otherwise: check project docs for existing analytics configuration
• Extract: event naming conventions, identity resolution, funnel pattern
• Define event funnel based on PRD features:

Awareness → Acquisition → Activation → Revenue → Retention → Referral

Map to concrete events:

| Stage | Event Name | Trigger | Properties | |-------|-----------|---------|------------| | Awareness | page_viewed | Landing page visit | source, utm_* | | Acquisition | app_installed or signed_up | First install/signup | platform, source | | Activation | core_action_completed | First key action | feature, duration_ms | | Revenue | purchase_completed | First payment | plan, amount, currency | | Retention | session_started | Return visit (D1/D7/D30) | session_number, days_since_install | | Referral | invite_sent | Shared or referred | channel, referral_code |

• Forced reasoning — metrics selection:

• North Star Metric: The ONE number that matters most (e.g., "weekly active users who completed core action")
• Leading indicators: What predicts the North Star? (e.g., "activation rate D1")
• Lagging indicators: What confirms success? (e.g., "MRR", "retention D30")
• Vanity metrics to AVOID: (e.g., total downloads without activation)
• Set KPI benchmarks per stage:

Adjust based on product type (B2C vs B2B, free vs paid, mobile vs web).

• Define decision rules (lean startup kill/iterate/scale):

## Decision Framework

   **Review cadence:** Weekly (Fridays)

   ### KILL signals (any 2 = kill)
   - [ ] Activation rate < {kill_threshold} after 2 weeks
   - [ ] D7 retention < {kill_threshold} after 1 month
   - [ ] Zero organic signups after 2 weeks of distribution
   - [ ] CAC > 3x LTV estimate

   ### ITERATE signals
   - [ ] Metrics between kill and scale thresholds
   - [ ] Qualitative feedback suggests product-market fit issues
   - [ ] One stage of funnel is dramatically worse than others

   ### SCALE signals (all 3 = scale)
   - [ ] Activation rate > {scale_threshold}
   - [ ] D7 retention > {scale_threshold}
   - [ ] Organic growth > 10% week-over-week

• Generate PostHog implementation snippets:

// Event tracking examples
   PostHogSDK.shared.capture("core_action_completed", properties: [
       "feature": "scan_receipt",
       "duration_ms": elapsed
   ])

### For Web (TypeScript):

// Event tracking examples
   posthog.capture('signed_up', {
       source: searchParams.get('utm_source') ?? 'direct',
       plan: 'free'
   })

• Write metrics plan to docs/metrics-plan.md:

# Metrics Plan: {Project Name}

   **Generated:** {YYYY-MM-DD}
   **Platform:** {iOS / Web / Both}
   **North Star:** {north star metric}

   ## Event Funnel

   | Stage | Event | Properties |
   |-------|-------|------------|
   {event table from step 4}

   ## KPIs & Thresholds

   | KPI | Target | Kill | Scale |
   |-----|--------|------|-------|
   {benchmark table from step 6}

   ## Decision Rules

   {framework from step 7}

   ## Implementation

   ### PostHog Setup
   - Project: {project name} (EU region)
   - SDK: {posthog-ios / posthog-js}
   - Identity: {anonymous → identified on signup}

   ### Code Snippets
   {snippets from step 8}

   ## Dashboard Template
   - Funnel: {stage1} → {stage2} → ... → {stageN}
   - Retention: D1 / D7 / D30 cohort chart
   - Revenue: MRR trend + trial conversion

   ---
   *Generated by /metrics-track. Implement events, then review weekly.*

• Output summary — North Star metric, key thresholds, first event to implement.

Notes

• PostHog EU hosting for privacy compliance
• Use $set for user properties, capture for events
• Identity: start anonymous, identify() on signup with user ID
• Cross-platform: same PostHog project, same user ID → unified journey
• Review dashboard weekly, make kill/iterate/scale decision monthly

Common Issues

Wrong platform detected

KPI thresholds too aggressive

PostHog SDK not in project