Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    customer retention program analyst

    1

    Use when asked to measure campaign uplift against a holdout or produce a retention scorecard and test backlog.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Retention scorecard from cohort curves and holdout campaign data: uplift versus natural retention (95% screen), campaign profitability, uplift hypotheses, prioritized test backlog. Consent and licence guardrails exclude and count; record-level data refused; sends stay drafts for approval.

    What it does

    Builds a retention scorecard from aggregate cohort curves and separates campaign impact from natural retention with holdout comparisons: uplift with a two-proportion z screen, campaign profitability (incremental retained, net margin, ROI, cost per incremental), uplift hypotheses and a prioritized test backlog. Aggregate-scoped: record-level data is refused; campaigns without accepted consent or on a blocked-licence source are excluded and counted; every send, publish or scale action is a draft requiring human approval. Use when asked to measure campaign uplift against a holdout or produce a retention scorecard and test backlog.

    Use cases

    • Measure retention uplift against a holdout group using aggregate cohort curves and a two-proportion screen.
    • Calculate campaign profitability from incremental retained customers, net margin and cost per incremental customer.
    • Rank retention hypotheses into a prioritized test backlog, with every send or scale action left as a draft.

    What is included

    • SKILL.md: the workflow, trigger rules and output format.
    • references/: method notes and the markers used in outputs, loaded only when needed.
    • scripts/run.py: one self-contained Python script (standard library only) that does every calculation deterministically.
    • assets/: input and output schemas with a sample request and result.

    Limits

    Decision support only. Outputs label analytical estimates, information gaps and actions that need human approval. The skill does not send, publish, pay or change anything by itself, and it does not claim legal, regulatory or standards compliance.

    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 2 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    Retention scorecard from cohort curves and holdout campaign data: uplift versus natural retention (95% screen), campaign profitability, uplift hypotheses, prioritized test backlog. Consent and licence guardrails exclude and count; record-level data refused; sends stay drafts for approval.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use customer retention program analyst on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.