Skip to main content
command CX Codex

analyze-cohorts — Claude Code command

analyze-cohorts runs cohort retention analysis on CSV files or generates SQL frameworks to measure feature adoption.

MIT ★ 28,211 updated 2026-10-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add phuryn/pm-skills
/plugin install pm-data-analytics@pm-skills
Open on GitHub

What analyze-cohorts does

The command provides two workflows. Provide an activity CSV with user IDs, signup dates, and event timestamps, and Claude Code processes the rows with Python pandas to generate retention tables and curves. If you do not have raw logs ready, it writes the extraction SQL and builds an analysis template instead.

The final output includes key findings, best and worst cohort comparisons, industry benchmarks, and actionable recommendations. Reports are saved as both Markdown and spreadsheet files alongside the generated Python code so you can rerun it later.

Meaningful output requires choosing an actual core action. Tracking plain logins instead of product activation skews the retention curve.

What it helps with

  • compute periodic retention rates from user activity spreadsheets
  • write SQL queries to extract cohort activity from your warehouse
  • evaluate onboarding redesigns by comparing feature adoption across cohorts
  • benchmark cohort retention numbers against industry baselines

Example prompts for the agent

  • /analyze-cohorts user_events.csv
  • /analyze-cohorts Monthly retention for users who signed up in Jan-Jun, grouped by acquisition channel
  • /analyze-cohorts Help me set up a cohort analysis for our onboarding redesign

How to install analyze-cohorts

1Plugin marketplace

/plugin marketplace add phuryn/pm-skills
/plugin install pm-data-analytics@pm-skills

2Manually: put the files in place

.claude/commands/analyze-cohorts.md

Call it with /analyze-cohorts. For all projects use ~/.claude/commands/

Questions about analyze-cohorts

How to install analyze-cohorts in Claude Code?

Run /plugin marketplace add phuryn/pm-skills and then /plugin install pm-data-analytics@pm-skills. Alternatively, save the file to .claude/commands/analyze-cohorts.md.

What does analyze-cohorts do?

It tracks cohort retention over days, weeks, or months, spots declining cohorts or seasonal shifts, and writes summary reports with follow-up SQL queries.

Can I run it without uploading real user data?

Yes. Describe your retention event and metrics, and the command produces the SQL queries, spreadsheet templates, and analytical framework for your stack.

Source text

analyze-cohorts.md · MIT
---
description: Perform cohort analysis on user data — retention curves, feature adoption, and engagement trends
argument-hint: "<data file or description of what to analyze>"
---

# /analyze-cohorts -- Cohort Analysis

Analyze user retention and engagement patterns by cohort. Upload your data or describe what you need, and get retention curves, feature adoption trends, and actionable insights.

## Invocation

```
/analyze-cohorts [upload a CSV of user activity data]
/analyze-cohorts Monthly retention for users who signed up in Jan-Jun, grouped by acquisition channel
/analyze-cohorts Help me set up a cohort analysis for our onboarding redesign
```

## Workflow

### Step 1: Accept Data or Define Analysis

Two paths:
- **With data**: User uploads a CSV/spreadsheet with user-level data (user_id, signup_date, activity_date, event_type, etc.)
- **Without data**: User describes the analysis they need → generate the SQL query and analysis framework

### Step 2: Define Cohorts

Ask:
- What defines a cohort? (signup week/month, acquisition channel, plan tier, first feature used)
- What is the retention event? (login, core action, any activity, purchase)
- What time granularity? (daily, weekly, monthly)
- What time range?

### Step 3: Analyze

Apply the **cohort-analysis** skill:

**If data is provided:**
- Process the data using Python (pandas) to create cohort tables
- Calculate retention rates per cohort per period
- Generate retention curves
- Identify patterns: improving/declining cohorts, seasonal effects, anomalies
- Compare feature adoption across cohorts

**If describing an analysis:**
- Design the cohort analysis framework
- Generate SQL queries to extract the data
- Create a template spreadsheet for the analysis
- Define the metrics and visualization approach

### Step 4: Generate Report

```
## Cohort Analysis: [Description]

**Date**: [today]
**Cohort definition**: [e.g., signup month]
**Retention event**: [e.g., completed a project]
**Granularity**: [weekly/monthly]

### Retention Table
| Cohort | Size | Week 1 | Week 2 | Week 3 | ... | Week 12 |
|--------|------|--------|--------|--------|-----|---------|

### Key Findings
1. **[Finding]** — [supporting data]
2. ...

### Cohort Comparison
- **Best-performing cohort**: [which, why]
- **Worst-performing cohort**: [which, why]
- **Trend**: [improving/declining/stable over time]

### Retention Benchmarks
| Period | Your Rate | Industry Benchmark | Gap |
|--------|----------|-------------------|-----|

### Recommendations
1. [What to investigate or change based on findings]
2. ...

### Follow-Up Queries
[SQL queries for deeper investigation]
```

If data was provided, save analysis as both markdown report and CSV/spreadsheet.

### Step 5: Offer Next Steps

- "Want me to **segment this further** by another dimension?"
- "Should I **set up metrics alerts** based on these retention thresholds?"
- "Want me to **design experiments** to improve retention for the weakest cohort?"

## Notes

- Cohort analysis is only as good as the retention event definition — push for a meaningful action, not just "logged in"
- Early cohorts often look different due to founding user bias — note this when comparing
- If retention is calculated using a Python script, save the script so the user can re-run with new data
- Seasonal effects can masquerade as trends — flag if cohort differences might be calendar-driven

© Paweł Huryn · MIT · phuryn/pm-skills

Similar slash commands

All slash commands for Data and databases →

From the same set120

The whole set →
value-proposition value-proposition maps a product or feature to a six-part template: target user, their job, current friction, your solution, resulting outcome, and why you beat alternatives. CX Codex +1 ★ 28,211repo stars test-scenarios Turns user stories and feature specifications into structured test scenarios covering happy paths, edge cases, and errors. CX Codex +1 ★ 28,211repo stars meeting-notes Turns a transcript or rough meeting notes into structured minutes with decisions, assigned actions, open questions, and next steps. CX Codex +1 ★ 28,211repo stars review-resume review-resume is a Claude Code command that evaluates product manager resumes against best practices and gives three priority improvements with examples. CX Codex +1 ★ 28,211repo stars transform-roadmap transform-roadmap is a Claude Code command that turns a feature list or existing roadmap into an outcome-led plan with success measures and strategic context for product planning. CX Codex +1 ★ 28,211repo stars market-product market-product is a Claude Code command that generates campaign ideas, positioning, value prop copy and product names. It supports launches, rebrands and competitive repositioning. CX Codex +1 ★ 28,211repo stars write-prd write-prd generates a lean Product Requirements Document from a brief idea, customer request, or uploaded problem summary. CX Codex +1 ★ 28,211repo stars competitive-analysis The competitive-analysis slash command maps a market, compares direct and indirect competitors, and surfaces ways to position a product differently. CX Codex +1 ★ 28,211repo stars

Project sponsors

Companies that keep this analytics open