/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
If MCP tools are not available, fall back to Grep + Read.
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
- If MCP available:
-
Define event funnel based on PRD features:
Standard funnel:
Awareness → Acquisition → Activation → Revenue → Retention → ReferralSee
references/kpi-benchmarks.mdfor the full event table, KPI thresholds, PostHog code snippets, and A/B test template. Adapt events to the specific product. -
Forced reasoning — metrics selection: Before defining KPIs, write out:
- 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:
Use thresholds from
references/kpi-benchmarks.mdas starting point. Adjust for product type (B2B has lower volume/higher conversion, B2C mobile has higher volume/lower retention). -
Define decision rules — use kill/iterate/scale framework from
references/kpi-benchmarks.md. Adapt thresholds to project-specific values from step 6. -
Generate PostHog implementation snippets — use platform-specific examples from
references/kpi-benchmarks.md. Adapt event names and properties to the funnel defined in step 4. -
A/B Test Analysis Template — copy template from
references/kpi-benchmarks.mdinto the metrics plan. Include decision rules (SHIP / KEEP / EXTEND / INCONCLUSIVE). -
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}
## A/B Test Template
{template from step 9}
## 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, A/B template included.
Notes
- PostHog EU hosting for privacy compliance
- Use
$setfor user properties,capturefor 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
Cause: Project has both web and iOS indicators. Fix: Skill checks package manifests. If both exist, it generates cross-platform identity setup. Verify the detected platform in the output.
KPI thresholds too aggressive
Cause: Default thresholds are industry averages.
Fix: Adjust thresholds in docs/metrics-plan.md based on your niche. B2B typically has lower volume but higher conversion.
PostHog SDK not in project
Cause: Metrics plan generated but SDK not installed.
Fix: This skill generates the PLAN only. Install PostHog SDK separately: pnpm add posthog-js (web) or add posthog-ios via SPM (iOS).
Scan to join WeChat group