Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    churn and retention cohort reporter

    1

    Reporting on churn and retention is often marred by inconsistent definitions, manual spreadsheet errors, and privacy risks.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    churn and retention cohort reporter

    churn and retention cohort reporter

    Example session with this skill installed

    Generate a monthly retention cohort report for the accounts in accounts_export.csv as of 2023-12-31. Use a minimum group size of 5 and exclude any records without analytics consent.

    • Read your context and instructions
    • Compiled the churn and retention
    • Generated the data export

    The account extract from accounts_export.csv has been processed. A total of 152 records were analyzed after excluding 8 records due to missing analytics consent.

    Churn and Retention Cohort Report — Internal, 2023-12-31

    1. Cohort definition, sources and assumptions

    • Anchor: Contract start date.
    • Granularity: Month.
    • Retained rule: Active status with MRR > 0 at period end.
    • Min group size: 5.
    • Sources: E1 (accounts_export.csv).

    2. Population and exclusions

    CategoryCount
    Received160
    Excluded: No Consent8
    In Analysis152

    3. Cohort retention

    CohortAccountsk=0k=1k=2k=3
    2023-01421.00000.95240.92860.9048
    2023-02381.00000.92110.89470.8684
    2023-034withheld (below minimum group size)

    4. Pooled retention and period churn

    MetricValue
    Pooled Retention (k=1)0.9367
    Average Period Churn0.0215

    5. Contract outcomes

    OutcomeCountPercentage
    Active13488.16%
    Cancellation127.89%
    Non-renewal63.95%

    6. Data quality and warnings

    • Quality Score: 0.98
    • Warning: W042 - Missing end_reason for 2 churned records in E1.

    7. Proposed actions and items for human review

    • Management decision required: Investigate the high cancellation rate in the 2023-02 cohort.
    • Management decision required: Audit records in E1 missing explicit end reasons.

    Next steps

    1. Review the withheld cohorts in the raw logs to determine if segments should be broadened.
    2. Confirm the 2023-02 cancellation spike with the account management team.
    3. Validate the 12 records marked as cancelled against CRM exit interviews.

    accounts_export.csv

    CSV · data export

    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.

    About this skill

    Reporting on churn and retention is often marred by inconsistent definitions, manual spreadsheet errors, and privacy risks. This skill provides a deterministic, script-driven approach to generating aggregate cohort reports from account records. It ensures every calculation follows a strict methodology, suppressing small cells to maintain privacy while documenting exactly how cohorts are defined and what data was excluded.

    What it does

    • Cohort construction groups customers by contract start month or quarter using authorized, consented records.
    • Retention reporting generates logo and contract-value retention tables with exact decimal precision for each period.
    • Churn analysis computes pooled retention curves, period churn rates, and specific contract outcomes like non-renewal or cancellation.
    • Data auditing produces a transparent log of population exclusions, data quality scores, and missing information gaps.
    • Privacy enforcement automatically suppresses small cells below a minimum group size and filters records based on consent flags.

    How it works

    1. Data ingestion reads account extracts, registers sources, and validates required fields like start dates and MRR.
    2. Schema validation creates a structured request file following input.schema.json to ensure type safety.
    3. Execution runs a deterministic Python script to perform the grouping and arithmetic without model hallucinations.
    4. Report generation produces a formatted Markdown report containing cohort tables, outcome analysis, and data quality warnings.

    Frameworks & tools

    The skill utilizes a self-contained Python execution environment, JSON Schema for input/output validation, and specific scripts for deterministic reporting.

    Why this beats prompting it yourself

    Generic prompts often hallucinate retention curves or fail to handle the edge cases of partial reporting periods. This skill uses a hardened Python script to ensure that if a data point is missing or unobservable, it is reported as such rather than estimated incorrectly.

    Use cases

    • Generating quarterly board-deck retention tables for SaaS revenue audits.
    • Analyzing logo churn by specific contract start periods to identify seasonal performance.
    • Documenting cohort definitions and data exclusions for internal compliance or data governance.

    Known limitations

    Does not perform per-customer churn risk scoring or predictive forecasting. Requires specific account fields and explicit consent flags to include records in the analysis.

    No per-customer risk scoring or predictive forecasting. Requires valid start dates and explicit consent flags. Does not assess marketing program effectiveness.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    Unlike generic AI prompts that may hallucinate calculations, this skill uses a deterministic Python script to ensure 100% mathematical accuracy and provides a transparent log of any data exclusions or quality gaps.

    This skill requires structured account data including contract start dates, monthly recurring revenue (MRR), and status flags, all validated against a strict JSON schema to ensure processing integrity.

    The skill includes built-in privacy enforcement that automatically suppresses small data cells and filters records based on consent flags, making it safe for internal sharing and compliance audits.

    You will receive the core reporting script, the input/output JSON schemas for system integration, and comprehensive documentation on cohort definitions and methodology.

    No, this skill is designed for historical, deterministic reporting; it analyzes what has already happened rather than using machine learning to predict which specific customers might churn in the future.

    New in Research & Analysis