cohort-analysis guides an agent through reading cohort data from CSV, Excel or JSON, checking its quality, and calculating retention rates and engagement trends. It builds retention heatmaps and cohort charts, picks out the significant patterns, and recommends qualitative and quantitative follow-ups such as churn interviews and A/B tests.
What You Get
- A data summary covering cohort sizes, date ranges and quality issues
- Retention rates, drop-off points and period-over-period changes
- Retention heatmaps and cohort progression charts
- Two or three significant patterns, such as early churn in one cohort
- Specific follow-up research such as churn interviews and win/loss analysis
- Reusable Python analysis scripts using pandas and numpy on request
Common Use Cases
- Finding out why a recent signup cohort retains worse than an earlier one
- Comparing how fast cohorts adopt a new feature
- Choosing which retention metrics to track for a subscription app
What Makes It Unique
It pairs the numbers with a research plan. After the retention analysis it names interviews, surveys, session replays and experiments that would explain what the data shows, so the output leads to the next piece of work.
Under The Hood
The skill is one SKILL.md of instructions with no bundled scripts. The agent reads the files you provide and, when you ask for it, writes Python scripts with pandas and numpy to compute retention and draw charts. It shows example prompts and an output format. It reaches no outside service.