Cohort Analysis Playbook

    1

    Build retention matrices and cohort curves from event data, then turn them into a clear retention report.

    $13

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    Cohort Analysis Playbook

    Example session with this skill installed

    Using events.csv (user_id, signup_date, activity_date), build monthly signup cohorts for Jan–Apr 2026. Active = any login. Show retention for months 1–3 and tell me if newer cohorts retain better.

    • Read your context and instructions
    • Compiled the cohort analysis playbook
    • Generated the document

    Illustrative example on synthetic data. It follows this skill's cohort_report_template.md.

    Cohort Analysis Report: App logins, Jan–Apr 2026 cohorts

    Summary

    Newer cohorts retain better. Month-1 retention rose from

    38% (Jan) to 46% (Apr). The biggest drop-off for every cohort is between month 0 and month 1.

    Retention Matrix

    CohortUsersM1M2M3
    2026-012,14038%29%25%
    2026-021,98040%31%27%
    2026-032,31044%34%–
    2026-042,45046%––

    Key Findings

    Finding 1: Month-1 retention improved by 8 pp

    The improvement starts with the March cohort, which lines up with the new onboarding checklist launched on 2026-03-02.

    Finding 2: Curves flatten after month 2

    Between M2 and M3, each cohort loses only 2–4 pp. Users who survive month 2 tend to stay.

    Finding 3: Cohort sizes are healthy

    All cohorts have more than 1,900 users, so the rates are not noisy.

    Caveats & Limitations

    Cohorts from March onward have fewer observed periods. The onboarding link is a correlation, not a proven cause; confirm it with an A/B test.

    Recommended Next Steps

    1. Split the March and April cohorts by users who did and did not complete the checklist.
    2. Track M3 for the March cohort next month.
    3. Share the heatmap (retention_matrix.html) with the growth team.

    cohort-analysis-playbook.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    What you get

    Measuring retention over timeComparing acquisition cohortsFinding when users churnRetention heatmaps for stakeholders

    About this skill

    Cohort Analysis Playbook takes your agent from raw event data to a retention story. It defines the cohort and the retention event, builds a cohort-by-period table (with a starter SQL query and Python scripts), computes the retention matrix, and renders a heatmap and retention curves. It then interprets the patterns using a bundled glossary and a guide to common cohort patterns. The deliverables are a written report and a colour-coded HTML retention heatmap.

    Use it when

    • Someone asks "are we retaining users better than last quarter?"
    • You need N-day, weekly or monthly retention for a product or feature
    • You want to compare acquisition cohorts by channel, plan or signup date
    • You are looking for the period when users typically churn

    What's inside (installs as one folder, cohort-analysis/):

    • cohort-analysis/LICENSE
    • cohort-analysis/SKILL.md
    • cohort-analysis/assets/cohort_report_template.md
    • cohort-analysis/assets/retention_matrix.html
    • cohort-analysis/references/cohort_definition_patterns.md
    • cohort-analysis/references/retention_metrics_glossary.md
    • cohort-analysis/scripts/cohort_builder.py
    • cohort-analysis/scripts/cohort_query.sql
    • cohort-analysis/scripts/cohort_visualizer.py
    • cohort-analysis/scripts/retention_matrix.py

    Please read before buying: this is packaged from my free, MIT-licensed open-source library (https://github.com/nimrodfisher/data-analytics-skills). The same content is available there for free. You are paying for a ready-to-install package. It is a one-time purchase, sold as-is, with no support, updates or maintenance included. The MIT license is included.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 1 day ago

    • Passed all security checks, Safe to install

    Listed1 day ago

    What's inside

    Frequently Asked Questions