‹ 首页

cohort-analysis

@guia-matthieu · 收录于 1 周前

Analyze user retention by cohort. Use when: measuring customer retention; understanding lifecycle patterns; comparing acquisition cohorts; tracking engagement over time; identifying churn risks

场景用户留存分析流失风险排查生命周期评估

适合你，如果正在追踪用户留存并想按获客批次对比行为变化。

/ 下载安装
cohort-analysis.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add guia-matthieu/clawfu-skills/cohort-analysis
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- guia-matthieu/clawfu-skills/cohort-analysis
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify guia-matthieu/clawfu-skills/cohort-analysis
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
132GitHub stars
~686最小装载
~2.8K含声明引用
~2.9K文本包总量
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · a69bf67

Cohort Analysis

Analyze retention and behavior patterns by grouping users into cohorts - understand how different customer groups behave over time.
When to Use This Skill
  • Retention tracking - Measure how users stick around over time
  • Acquisition analysis - Compare cohorts from different channels
  • Product changes - Measure impact on user behavior
  • Churn prediction - Identify at-risk cohorts
  • LTV estimation - Project customer lifetime value
What Claude Does vs What You Decide

| Claude Does | You Decide | |-------------|------------| | Structures analysis frameworks | Metric definitions | | Identifies patterns in data | Business interpretation | | Creates visualization templates | Dashboard design | | Suggests optimization areas | Action priorities | | Calculates statistical measures | Decision thresholds |

Dependencies
pip install pandas plotly click
Commands
Retention Analysis
python scripts/main.py retention data.csv --date-col signup --event-col purchase
python scripts/main.py retention data.csv --date-col signup --periods week
Visualize Cohorts
python scripts/main.py visualize cohorts.csv --output retention_chart.html
Export Report
python scripts/main.py report data.csv --date-col signup --event-col active --output report.html
Examples
Example 1: Analyze User Retention
python scripts/main.py retention users.csv --date-col signup_date --event-col last_active

# Output:
# Cohort Retention Analysis
# ──────────────────────────────────
# Cohort     Users    M1     M2     M3     M4
# Jan 2024   1,234    65%    48%    42%    38%
# Feb 2024   1,456    62%    45%    41%    --
# Mar 2024   1,321    68%    52%    --     --
# Apr 2024   1,567    64%    --     --     --
#
# Avg Retention: 65% → 48% → 42% → 38%
# Best Cohort: Mar 2024 (68% M1)
Example 2: Generate Visual Report
python scripts/main.py report transactions.csv \
  --date-col signup \
  --event-col purchase_date \
  --output retention_report.html

# Generates interactive HTML with:
# - Retention heatmap
# - Cohort size chart
# - Trend analysis
Cohort Table Format

| Cohort | Size | Period 0 | Period 1 | Period 2 | Period 3 | |--------|------|----------|----------|----------|----------| | 2024-01 | 1234 | 100% | 65% | 48% | 42% | | 2024-02 | 1456 | 100% | 62% | 45% | - | | 2024-03 | 1321 | 100% | 68% | - | - |

Skill Boundaries
What This Skill Does Well
  • Structuring data analysis
  • Identifying patterns and trends
  • Creating visualization frameworks
  • Calculating statistical measures
What This Skill Cannot Do
  • Access your actual data
  • Replace statistical expertise
  • Make business decisions
  • Guarantee prediction accuracy
Related Skills
  • [ab-test-stats](../ab-test-stats/) - Test retention experiments
  • [funnel-analyzer](../funnel-analyzer/) - Analyze conversion funnels
Skill Metadata
  • Mode: centaur
category: analytics
subcategory: retention
dependencies: [pandas, plotly]
difficulty: intermediate
time_saved: 4+ hours/week
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…