cohort-analysis

Name: cohort-analysis
Author: phuryn

1.8kinstalls2.5kforks

How to install cohort-analysis?

phuryn/pm-skills/cohort-analysis

$npx -y skills add phuryn/pm-skills --skill cohort-analysis

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

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

People who liked this also viewed

6 picks

Type

cohort-analysis

1.8kinstalls2.5kforks

View on GitHub

How to install cohort-analysis?

phuryn/pm-skills/cohort-analysis

$npx -y skills add phuryn/pm-skills --skill cohort-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

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

People who liked this also viewed

6 picks

Type