Skip to content
Get packs

Cohort Analysis & Retention Explorer

Analyze user retention and feature adoption by cohort, with charts and follow-up research ideas

Source Download skill
Repository
phuryn/pm-skills
Stars
27,616
Licence
MIT
Files
1 file

What it does

This skill teaches an AI agent to analyze how groups of users (cohorts, such as people who signed up in the same month) keep using a product over time. Given a CSV, Excel or JSON file of user engagement data, the agent checks the data quality, calculates retention and feature adoption rates, draws retention heatmaps and line charts, and points out notable patterns like early churn. It also suggests qualitative follow-ups such as user interviews or A/B tests.

Great for

  • Product managers checking whether newer user groups retain better or worse than older ones
  • Growth or marketing analysts comparing feature adoption across launch periods
  • Data analysts who want a first-pass retention report and reusable pandas scripts

Skip it if

  • Decisions that need statistically rigorous conclusions: the skill gives directional insight, and its description does not mention significance testing, so results should be checked by an analyst
  • Sensitive personal data: uploading raw user records to an AI tool may breach privacy rules unless the data is anonymized first

Try asking

  • “Analyze retention patterns in cohort_engagement.csv and explain why Q4 cohorts underperform Q3”
  • “Compare adoption curves for our new feature across monthly cohorts in feature_usage.xlsx”
  • “Which signup cohorts from 2025 show the best long-term retention? Give me a heatmap”
  • “Write a reusable pandas script that calculates weekly retention by signup month”
Step-by-step guide: how to use Cohort Analysis & Retention ExplorerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    cohort-analysis.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip cohort-analysis.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip cohort-analysis.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Define the cohort clearly in your request (signup month, feature launch date) and include several time periods, ideally at least 3-4 cohorts
  • Mention product changes, launches or events during the period so the agent can interpret the patterns
  • Ask explicitly for a Python script if you want reproducible analysis you can rerun

What's inside

  • SKILL.md

Redistributed unmodified from phuryn/pm-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.