business-cohort-analysis
Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights. Use when analyzing user retention by cohort, studying feature adoption over tim
SKILL.mdresources/agent-presets/skills/business-cohort-analysis/SKILL.md
GitHubApp 执行约定
先读取本技能正文及任务所需的本地参考资源。使用中文;工作目录由任务提供,仅读取用户提供、当前任务授权的资料。正文中的 $ARGUMENTS 及斜杠命令表示用户任务输入,不调用 Claude 专用命令。AskUserQuestion/提问通过 App ask_user;本地文件通过 read_file,成果使用 write_file 后 register_artifact,或 write_artifact。相对资源路径以本 SKILL.md 所在目录为起点。若技能读取结果含目录,按该目录构建资源绝对路径。
正文中 Search/WebFetch、Figma、CRM、广告平台及其它连接名称仅为可选来源;只使用 App 实际提供且已授权的工具。没有连接时从上传材料完成流程,把缺少的外部验证列出,不安装运行时插件或扫描用户全局配置。默认输出 Markdown/CSV 草稿;Office、图表、HTML、PNG 或图像生成只在对应工具和运行库可用时执行。不得擅自发送邮件、发表内容、签约、创建发票、修改线上商品或花费广告预算。
Cohort Analysis & Retention Explorer
Purpose
Analyze user engagement and retention patterns by cohort to identify trends in user behavior, feature adoption, and long-term engagement. Combine quantitative insights with qualitative research recommendations.
How It Works
Step 1: Read and Validate Your Data
- Accept CSV, Excel, or JSON data files with user cohort information
- Verify data structure: cohort identifier, time periods, engagement metrics
- Check for missing values and data quality issues
- Summarize key statistics (cohort sizes, date ranges, metrics available)
计算与解释口径
先判断输入是用户级事件还是按期聚合人数。聚合表只能计算各期人数/初始队列规模、人数差和留存百分点差;相邻两期人数相除只是比值,不代表前一期活跃者中有多少人留下。没有用户ID交集,不能报告同人续留、流失或回流人数,也不能用“流失了几分之几”解释人数差。对每个比较同时写出原值、分母和单位,区分百分点变化与相对百分比;叙述中的比例必须与公式同口径一致。
完整自然月指标须观察月闭合后计算,后续复算日期安排在该月结束之后。没有证据的模式保持未确定,不为凑足洞察数量编造流失、季节性或显著性。发布前逐句核对洞察,不能在口径声明中说“不可计算”却在后文给出同一指标的结论。
Step 2: Generate Quantitative Analysis
- Calculate cohort retention rates and engagement trends
- Identify retention curves, drop-off patterns, and anomalies
- Compute feature adoption rates across cohorts
- Calculate month-over-month or period-over-period changes
- Generate Python analysis scripts using pandas and numpy if requested
Step 3: Create Visualizations
- Generate retention heatmaps (cohorts vs. time periods)
- Create line charts showing cohort progression
- Build comparison charts for feature adoption
- Visualize drop-off points and engagement trends
- Output as interactive charts or static images
Step 4: Identify Insights & Patterns
- Identify only patterns supported by the available data; if unsupported, explicitly state no conclusion:
- Early churn in specific cohorts
- Late-stage engagement changes
- Feature adoption clusters
- Seasonal or temporal trends
- Highlight surprising findings and deviations
- Compare cohort performance to establish baselines
Step 5: Suggest Follow-Up Research
- Recommend qualitative research methods:
- Targeted user interviews with churning users
- Feature usage surveys with engaged cohorts
- Session replays of key interaction patterns
- Win/loss analysis for high vs. low retention cohorts
- Design follow-up quantitative studies
- Suggest A/B tests or feature experiments
Usage Examples
Example 1: Upload CSV Data
Upload cohort_engagement.csv with columns: cohort_month, weeks_active,
user_id, feature_x_usage, engagement_score
Request: "Analyze retention patterns and identify why Q4 2025 cohorts
underperform compared to Q3"
Example 2: Describe Data Format
"I have monthly user cohorts from Jan-Dec 2025. Each row shows:
cohort date, user ID, purchase frequency, and support tickets.
Analyze which cohorts show best long-term retention."
Example 3: Feature Adoption Analysis
Upload feature_usage.xlsx with cohort adoption data.
Request: "Compare adoption curves for our new feature across cohorts.
Which cohorts adopted fastest? Any patterns?"
Key Capabilities
- Data Reading: Import CSV, Excel, JSON, SQL query results
- Retention Analysis: Calculate and visualize retention rates over time
- Cohort Comparison: Compare metrics across cohort groups
- Anomaly Detection: Flag unusual patterns or drop-offs
- Python Scripts: Generate reusable analysis code for ongoing analysis
- Visualizations: Create heatmaps, charts, and interactive dashboards
- Research Design: Suggest targeted follow-up studies and interview approaches
- Statistical Summary: Provide quantitative metrics and correlation analysis
Tips for Best Results
- Include time dimension: Provide data across multiple time periods
- Define cohort clearly: Make cohort grouping explicit (signup month, feature launch date, etc.)
- Provide context: Explain product changes, launches, or events during the period
- Multiple metrics: Include retention, engagement, feature usage, revenue, etc.
- Sufficient data: At least 3-4 cohorts for meaningful pattern identification
- Request specific output: Ask for visualizations, Python scripts, or research recommendations
Output Format
You'll receive:
- Data Summary: Cohort overview and data quality assessment
- Quantitative Findings: Key metrics, retention rates, and trend analysis
- Visualizations: Charts showing retention curves, adoption patterns
- Pattern Identification: Evidence-supported insights only; do not invent significance or require a fixed count
- Research Recommendations: Specific qualitative and quantitative follow-ups
- Analysis Scripts (if requested): Python code for reproducible analysis
- Next Steps: Prioritized actions based on findings