RD

    留存数据建模 · Retention Data Modeler

    1

    把留存数据整理成可分析模型:队列定义、分层维度与预测目标一次定清。 Organize retention data into an analysis-ready model with cohort definitions, segmentation dimensions, and forecast targets.

    $7

    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
    RD

    留存数据建模 · Retention Data Modeler

    Example session with this skill installed

    请为订阅产品设计留存数据建模方案,目标预测 30 天流失风险。

    • Read your context and instructions
    • Compiled the retention data modeler

    留存数据建模方案已生成。

    队列定义

    • 队列:按首次订阅日
    • 事件:登录、核心功能使用、续费
    • 窗口:D1/D7/D30

    分层维度

    1. 渠道(自然/投放/合作)
    2. 套餐(月付/年付)
    3. 行为(活跃/沉默)
    4. 设备(移动/桌面)

    建模目标

    • 目标变量:30 天内是否流失
    • 特征:首周使用频次、功能深度、客诉次数
    • 评估:按队列分层验证 AUC

    Next steps

    1. 先产出近 90 天训练集口径。
    2. 特征缺失率 >30% 的列先剔除。
    3. 用滚动窗口验证防止过拟合。

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

    What you get

    Standardize cohort definitions across different data teams.Convert business goals into structured churn prediction specs.Generate data dimension tables for retention dashboards.Align retention event criteria for multi-platform analysis.

    About this skill

    它解决什么问题

    保留数据在没有模型的情况下到达：队列是混合的，细分未定义，并且没有可以预测或改进的目标变量。

    这个技能做什么

    • 定义队列窗口和保留事件标准。
    • 构建细分维度：渠道、计划、行为、设备。
    • 设置 D7、D30 和流失风险等建模目标。
    • 输出数据规范分析师可以直接实施。

    为什么比裸提示词强

    它强制执行一个建模框架：群组、事件、细分、目标，因此分析从共享数据契约开始。

    典型用例

    • 为流失预测模型准备数据。
    • 定义每月保留仪表板。
    • 跨团队标准化保留定义。

    局限

    它产生规格；数据管道和模型仍然需要实施。

    English · 英文介绍

    The problem

    Retention data arrives without a model: cohorts are mixed, segments undefined, and there is no target variable to predict or improve.

    What it does

    • Defines cohort windows and retention event criteria.
    • Builds segment dimensions: channel, plan, behavior, device.
    • Sets modeling targets like D7, D30, and churn risk.
    • Outputs a data spec analysts can implement directly.

    Why this beats prompting it yourself

    It enforces a modeling frame: cohort, event, segments, target, so the analysis starts from a shared data contract.

    Use cases

    • Preparing data for a churn prediction model.
    • Defining a monthly retention dashboard.
    • Standardizing retention definitions across teams.

    Known limitations

    It produces the spec; data pipelines and models still need implementation.

    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 today

    • Passed all security checks, Safe to install

    Listedtoday

    Frequently Asked Questions