Retention Cohort Analysis
Use when analyzing retention, cohort behavior, repeat purchase, active user return, subscription renewal, or user stickiness over time. Builds cohort retention matrices from event data with a bundled zero-dependency script that masks immature cells, keeps curves on a fixed cohort set, compares segments, flags mix-adjusted anomaly cohorts, decomposes cohort-over-cohort change into mix vs retention effects, and renders an HTML report. 中文触发词:留存分析、Cohort、复购、续费、用户流失、次日留存。
Install
npx skills add shisuidata/ss-data-skills --skill retention-cohort-analysisgit clone --depth 1 https://github.com/shisuidata/ss-data-skills.git /tmp/ss-data-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ss-data-skills/skills/retention-cohort-analysis ~/.claude/skills/retention-cohort-analysisPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Retention Cohort Analysis ## 目标 分析用户、客户或业务对象在进入之后是否持续回来,并回答: 1. 留存曲线长什么样?后段有没有趋平(有没有稳定留下来的用户)? 2. 哪些分群留存更差?哪些批次异常? 3. 最近批次留存变差,是**来了不一样的用户**,还是**同样的用户留得更差**? 核心原则:**数字由脚本算,判断由人做**。留存矩阵、曲线、分群对比、异常批次和结构拆解用 `scripts/retention.py` 计算;模型负责定义口径、解释原因、提出验证动作。 ## 使用场景 - 新用户次日、7 日、30 日留存 - 周留存、月留存、会员续费、订阅续约 - 首购后复购 - 不同渠道、版本、首日行为的用户质量对比 - “最近几批用户留存变差了,为什么” - B 端客户活跃与流失 典型输入: ```text 帮我看不同渠道新用户的 7 日和 30 日留存,最近几周是不是变差了。 ``` ## 不适用场景 - 有序步骤的转化:使用 `funnel-analysis` - 有随机分组的实验:使用 `ab-test-analysis` - 指标口径本身有争议:先用 `metric-definition-reviewer` - 预测某个用户会不会流失:这是建模问题,使用 `feature-engineering-advisor` 和 `model-evaluation-reviewer` 没有明确“起点行为”和“回访行为”时,先定义 Cohort 口径。 ## 输入信息 最少输入: - 起点:注册、首购、首次签约等事件或时间 - 回访行为:主动打开、核心行为、再次购买、续费 - 用户或对象 ID、时间字段 推荐输入: - 事件明细 CSV + 用户属性 CSV(渠道、设备、套餐等) - Cohort 粒度:日 / 周 / 月 - 留存口径:第 N 期当期回访,还是 N 期内有过回访 - 按日时:自然日还是滚动 24 小时 - 想对比的两组批次(例如改版前后) 输入字段详见 [输入格式](references/input-schema.md)。 ## 上下文建议 推荐使用 [留存 Cohort 分析上下文模板](../../context/templates/cohort-context.md) 准备结构化输入。 通用分析背景请参考 [数据分析上下文模板](../../context/templates/analysis-context.md)。 最有价值的上下文是:起点行为、回访行为、时间口径(自然日 / 滚动 24 小时)、Cohort 粒度和分群维度。时间口径不明确时,必须先确认,不能混用。 ## 工作流程 1. **定义口径**:起点、回访行为(只算主动行为,排除推送到达、后台唤醒)、粒度、留存口径、时间边界。写成表格请用户确认。 2. **运行脚本**(能执行代码时必须运行):
Details
- Skill name
retention-cohort-analysis- Repository
- shisuidata/ss-data-skills
- Path
skills/retention-cohort-analysis/SKILL.md- License
- MIT
- Repo updated
- 8 November 2026
FAQ
What does the Retention Cohort Analysis skill do?
Use when analyzing retention, cohort behavior, repeat purchase, active user return, subscription renewal, or user stickiness over time. Builds cohort retention matrices from event data with a bundled zero-dependency script that masks immature cells, keeps curves on a fixed cohort set, compares segments, flags mix-adjusted anomaly cohorts, decomposes cohort-over-cohort change into mix vs retention effects, and renders an HTML report. 中文触发词:留存分析、Cohort、复购、续费、用户流失、次日留存。
How do I install the Retention Cohort Analysis skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add shisuidata/ss-data-skills --skill retention-cohort-analysis. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Retention Cohort Analysis popular?
It lives in shisuidata/ss-data-skills, which has 9 GitHub stars and 0 forks.
Related skills
Ab Test Analysis
9shisuidata/ss-data-skills
Use when designing, checking, or interpreting A/B tests and experiments. Computes significance, confidence intervals, sample ratio mismatch, power, CUPED, and sample size with a bundled zero-dependency script, then judges validity risks, guardrails, and ship/iterate/rollback decisions and renders an HTML experiment report. 中文触发词:A/B 实验、AB 测试、实验解读、显著性、样本量计算、能不能全量。
Business Root Cause Analysis
9shisuidata/ss-data-skills
Use when diagnosing business metric changes or anomalies such as GMV decline, conversion drop, retention loss, churn increase, revenue change, lead decline, or active user fluctuation with a structured root cause analysis plan. 中文触发词:指标归因、为什么下降、异常排查、GMV 下滑、指标波动原因。
Daily Report Writer
9shisuidata/ss-data-skills
Use when writing a concise daily report, daily worklog, standup update, shift handoff, or end-of-day summary for data analysis, data development, BI, governance, or operations work. 中文触发词:日报、日终同步、站会发言、值班交接。
Context Editing Guide
5realsigridjin/interview-copilot-with-skills
Managing context window, token optimization, summarization strategies for long conversations.
Recon
5franco-bianco/claude-skills
Systematically discover alternative endpoints, bypasses, and undocumented access paths on a target platform. Use after the normal flow works to find simpler or more efficient approaches.
Information Design
5nekoai-lab/claude-skills
スライド、レポート、ダッシュボード、提案書の作成時に、情報をわかりやすく、比較しやすく、誤解なく伝えるための設計原則を適用する
Browse the most popular Claude skills, all other skills, or write your own with the skills generator.