Cohort Analysis & Retention Explorer skill

Perform cohort analysis on user engagement data — retention curves, feature adoption trends, and segment-level insights.

by phuryn·MIT license·★ 26,557 Stars on the repo·GitHub ↗

Use now

phuryn/main1 file shown

SKILL.md4.9 KB

Browse every file on GitHub↗

SKILL.md

Show the full text115 lines

cohort-analysis-3/SKILL.md115 lines · 4.9 KB

PreviewCode

Outline

RawView on GitHub

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)

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

Spot one or more significant patterns:
- 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: 2-3 significant insights from the data
Research Recommendations: Specific qualitative and quantitative follow-ups
Analysis Scripts (if requested): Python code for reproducible analysis
Next Steps: Prioritized actions based on findings

1	---
2	name: cohort-analysis
3	description: "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 time, investigating churn patterns, or identifying engagement trends."
4	---
5
6	# Cohort Analysis & Retention Explorer
7
8	## Purpose
9	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.
10
11	## How It Works
12
13	### Step 1: Read and Validate Your Data
14	- Accept CSV, Excel, or JSON data files with user cohort information
15	- Verify data structure: cohort identifier, time periods, engagement metrics
16	- Check for missing values and data quality issues
17	- Summarize key statistics (cohort sizes, date ranges, metrics available)
18
19	### Step 2: Generate Quantitative Analysis
20	- Calculate cohort retention rates and engagement trends
21	- Identify retention curves, drop-off patterns, and anomalies
22	- Compute feature adoption rates across cohorts
23	- Calculate month-over-month or period-over-period changes
24	- Generate Python analysis scripts using pandas and numpy if requested
25
26	### Step 3: Create Visualizations
27	- Generate retention heatmaps (cohorts vs. time periods)
28	- Create line charts showing cohort progression
29	- Build comparison charts for feature adoption
30	- Visualize drop-off points and engagement trends
31	- Output as interactive charts or static images
32
33	### Step 4: Identify Insights & Patterns
34	- Spot one or more significant patterns:
35	- Early churn in specific cohorts
36	- Late-stage engagement changes
37	- Feature adoption clusters
38	- Seasonal or temporal trends
39	- Highlight surprising findings and deviations
40	- Compare cohort performance to establish baselines
41
42	### Step 5: Suggest Follow-Up Research
43	- Recommend qualitative research methods:
44	- Targeted user interviews with churning users
45	- Feature usage surveys with engaged cohorts
46	- Session replays of key interaction patterns
47	- Win/loss analysis for high vs. low retention cohorts
48	- Design follow-up quantitative studies
49	- Suggest A/B tests or feature experiments
50
51	## Usage Examples
52
53	Example 1: Upload CSV Data
54	```
55	Upload cohort_engagement.csv with columns: cohort_month, weeks_active,
56	user_id, feature_x_usage, engagement_score
57
58	Request: "Analyze retention patterns and identify why Q4 2025 cohorts
59	underperform compared to Q3"
60	```
61
62	Example 2: Describe Data Format
63	```
64	"I have monthly user cohorts from Jan-Dec 2025. Each row shows:
65	cohort date, user ID, purchase frequency, and support tickets.
66	Analyze which cohorts show best long-term retention."
67	```
68
69	Example 3: Feature Adoption Analysis
70	```
71	Upload feature_usage.xlsx with cohort adoption data.
72
73	Request: "Compare adoption curves for our new feature across cohorts.
74	Which cohorts adopted fastest? Any patterns?"
75	```
76
77	## Key Capabilities
78
79	- Data Reading: Import CSV, Excel, JSON, SQL query results
80	- Retention Analysis: Calculate and visualize retention rates over time
81	- Cohort Comparison: Compare metrics across cohort groups
82	- Anomaly Detection: Flag unusual patterns or drop-offs
83	- Python Scripts: Generate reusable analysis code for ongoing analysis
84	- Visualizations: Create heatmaps, charts, and interactive dashboards
85	- Research Design: Suggest targeted follow-up studies and interview approaches
86	- Statistical Summary: Provide quantitative metrics and correlation analysis
87
88	## Tips for Best Results
89
90	1. Include time dimension: Provide data across multiple time periods
91	2. Define cohort clearly: Make cohort grouping explicit (signup month, feature launch date, etc.)
92	3. Provide context: Explain product changes, launches, or events during the period
93	4. Multiple metrics: Include retention, engagement, feature usage, revenue, etc.
94	5. Sufficient data: At least 3-4 cohorts for meaningful pattern identification
95	6. Request specific output: Ask for visualizations, Python scripts, or research recommendations
96
97	## Output Format
98
99	You'll receive:
100	- Data Summary: Cohort overview and data quality assessment
101	- Quantitative Findings: Key metrics, retention rates, and trend analysis
102	- Visualizations: Charts showing retention curves, adoption patterns
103	- Pattern Identification: 2-3 significant insights from the data
104	- Research Recommendations: Specific qualitative and quantitative follow-ups
105	- Analysis Scripts (if requested): Python code for reproducible analysis
106	- Next Steps: Prioritized actions based on findings
107
108	---
109
110	### Further Reading
111
112	- [Cohort Analysis 101: How to Reduce Churn and Make Better Product Decisions](https://www.productcompass.pm/p/cohort-analysis)
113	- [The Product Analytics Playbook: AARRR, HEART, Cohorts & Funnels for PMs](https://www.productcompass.pm/p/the-product-analytics-playbook-aarrr)
114	- [Are You Tracking the Right Metrics?](https://www.productcompass.pm/p/are-you-tracking-the-right-metrics)
115