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/retention-playbook.md

Retention metrics playbook

For "week-1 retention regressed", "March cohort isn't coming back".

0. Config sanity check

  • If totalIntervals exceeds the date range, the tail cells are always zero and look like a drop. Match totalIntervals to the range.
  • The most recent cohort hasn't had its full retention window yet — note as partial rather than a regression.

1. Isolate the cohort

targetEntity / returningEntity use {type: "events", name: "<event>"} and nest in retentionFilter. Compare affected cohort(s) to prior baselines side by side.

posthog:query-retention
{
  "kind": "RetentionQuery",
  "dateRange": { "date_from": "-90d" },
  "retentionFilter": {
    "targetEntity": { "type": "events", "name": "$pageview" },
    "returningEntity": { "type": "events", "name": "$pageview" },
    "totalIntervals": 8,
    "period": "Week",
    "retentionType": "retention_first_time"
  }
}

2. Event vs. users

Is the drop in the activity event itself or in the cohort doing it? Create or reuse a cohort for the affected period (posthog:cohorts-create / -list), then run posthog:query-trends on the activity event filtered to that cohort.

3. Split the dropout

Run posthog:query-lifecycle scoped to the affected cohort to separate "never retained" (new users who didn't return) from "lost later" (returning users who churned).

Next

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