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/lifecycle-playbook.md

Lifecycle metrics playbook

For "new users fell", "returning users crashed", "resurrecting stopped coming back".

1. Identify which status moved

Run posthog:query-lifecycle with the user's metric. Read which of new / returning / resurrecting / dormant changed.

2. Segment

AssistantLifecycleQuery doesn't support breakdownFilter. To compare segments, run posthog:query-lifecycle once per segment with properties filters on the series, or focus on a single status with lifecycleFilter.toggledLifecycles: ["new"] / ["returning"].

posthog:query-lifecycle
{
  "kind": "LifecycleQuery",
  "dateRange": { "date_from": "-30d" },
  "interval": "day",
  "series": [
    {
      "kind": "EventsNode",
      "event": "$pageview",
      "properties": [{ "type": "event", "key": "$geoip_country_code", "value": "US", "operator": "exact" }]
    }
  ]
}

3. Diagnose by status

  • New-user drop — find the project's first-session event via read-data-schema ($session_start, $pageview, or a signup event), then run posthog:query-paths from there to see where onboarding loses people.
  • Returning-user drop — posthog:query-trends on the cohort's key engagement events. Use interval zoom + actor drilldown if a specific day stands out.
  • Resurrecting drop — usually external. Re-check annotations and re-engagement campaign / email events.

Next

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