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/stickiness-playbook.md

Stickiness metrics playbook

For "DAU/MAU dropped", "sessions per week fell", "engagement decayed".

1. Segment

AssistantStickinessQuery doesn't support breakdownFilter. Run posthog:query-stickiness once per segment with property filters on the series, and compare side-by-side.

posthog:query-stickiness
{
  "kind": "StickinessQuery",
  "dateRange": { "date_from": "-30d" },
  "interval": "day",
  "series": [
    {
      "kind": "EventsNode",
      "event": "$pageview",
      "properties": [{ "type": "person", "key": "plan", "value": "pro", "operator": "exact" }]
    }
  ]
}

2. Drill into the low-stickiness segment

Run posthog:query-trends on a key engagement event filtered to that segment, then posthog:query-trends-actors on the trend. Pull recordings for a handful.

3. What sticky users do that non-sticky users don't

With a sticky and a non-sticky cohort, run posthog:query-trends on candidate core events scoped to each (filter via properties cohort filter). Events where the two diverge are the ones driving stickiness.

Next

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