AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

investigate-metric

Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries. Use when the user reports an anomaly, asks "why did X change?", asks to explain or walk them through a chart, or needs root-cause analysis for a trend, funnel, retention, stickiness, or lifecycle metric.

Original source
posthog
License
MIT
Pinned revision
cac7c80a9e5b73484d18eda1bffb47297c938e0c

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read posthog--investigate-metric at revision cac7c80a9e5b73484d18eda1bffb47297c938e0c, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 11

references/trend-playbook.md

Trend metrics playbook

For "DAU dropped", "revenue spiked", "clicks fell after the release".

1. Zoom in

Rerun posthog:query-trends at interval: "hour" scoped to the suspicious day(s). A one-hour cliff is an incident or deploy; a full-day shift is a broader cause (campaign, cohort change, tracking regression).

2. Break down

Try several breakdowns. Use read-data-schema to find candidate properties. Pipe results through breakdown_attribution.py — it ranks by absolute delta and flags offsetting moves. If no segment isolates the delta, the cause is system-wide.

posthog:query-trends
{
  "kind": "TrendsQuery",
  "dateRange": { "date_from": "-30d" },
  "interval": "day",
  "series": [{ "kind": "EventsNode", "event": "$pageview", "math": "dau" }],
  "breakdownFilter": {
    "breakdowns": [{ "property": "plan", "type": "event" }],
    "breakdown_limit": 10
  }
}

3. Identify affected users

Run posthog:query-trends-actors on the anomalous bucket (or breakdown value that moved). For UI-shaped drops, pull session recordings for the same segment.

4. Errors / logs

posthog:query-error-tracking-issues-list and posthog:query-logs for the window. Confirm timing, plausible mechanism, and user overlap before treating as the cause.

5. Cohort composition

Run posthog:query-lifecycle on the same event. If the drop is concentrated in one status (new users didn't arrive, dormant users didn't resurrect), the user mix changed rather than per-user behavior.

Next

Return to SKILL.md for Step 4 (cross-check) and Step 5 (write findings), in the format you chose in Step 1.