cohort-analysis

Name: cohort-analysis
Author: Productfculty-aipm

70stars33forks

How to install cohort-analysis?

productfculty-aipm/pm-copilot-by-product-faculty/cohort-analysis

$npx -y skills add Productfculty-aipm/PM-Copilot-by-Product-Faculty --skill cohort-analysis

Installs into the current project.

Summary

Use this skill when the user asks about "cohort analysis", "retention cohorts", "how to read cohort data", "analyze my retention", "what does my cohort data say", "cohort retention curves", "D7/D30 retention", "how to improve cohort retention", or has cohort data they want to int

Files · 1

View on GitHub

SKILL.md

1	# Cohort Analysis
2
3	You are helping the user analyze cohort retention data to understand how well the product retains users over time, identify where users drop off, and recommend actions to improve retention.
4
5	Framework: AARRR (Retention stage), Lenny Rachitsky's retention benchmarks, North Star framework.
6
7	## Step 1 — Load Context
8
9	Read `memory/user-profile.md` for product stage and business model. Read `context/company/analytics-baseline.md` for existing retention baselines and targets.
10
11	## Step 2 — Understanding the Cohort Data
12
13	Ask the user to provide:
14	- The cohort data (can be a table, CSV, or described verbally)
15	- The cohort definition (what event defines "day 0"? — signup, first action, subscription start?)
16	- The measurement event (what defines "active" in day N? — login? Core action? Payment?)
17	- The timeframe (weekly or monthly cohorts? How many periods?)
18
19	If the data is provided, identify:
20	- Cohort size (how many users started in each cohort?)
21	- Retention rates at each time period (D1, D7, D30, D60, D90, or W1, W4, W12)
22	- Trend: are newer cohorts retaining better or worse than older ones?
23	- The "elbow" — where does the sharpest drop occur?
24
25	## Step 3 — Retention Benchmarks
26
27	Compare the user's retention to benchmarks from Lenny's data:
28
29	Mobile apps (consumer):
30	- D1: 40% is good; 25% is typical; < 15% is concerning
31	- D7: 20% is good; 10% is typical; < 5% is concerning
32	- D30: 10% is good; 5% is typical; < 2% is very concerning
33
34	SaaS / B2B:
35	- Week 1: 70%+ is good; 50–70% is typical; < 50% is concerning
36	- Month 1: 50%+ is good; 30–50% is typical
37	- Month 3: 30%+ is good; <20% is concerning
38
39	Freemium:
40	- Day 7: 15–25% returning users is typical
41	- Conversion to paid: 2–5% is typical for free-to-paid
42
43	Calibrate recommendations to the user's stage and model from memory.
44
45	## Step 4 — Diagnose the Drop-Off
46
47	Find the point of sharpest drop:
48
49	If the drop is at D1 (first day): Activation problem — users aren't experiencing the core value in their first session
50	- Fix: Improve onboarding flow; reduce time to first value; shorten the path to the "aha moment"
51
52	If the drop is at D7 (first week): Habit formation problem — the product isn't building a regular use pattern
53	- Fix: Add triggers for return (email, notification); deepen value in the core loop; improve D3–D5 experience
54
55	If the drop is at D30 (first month): Value realization problem — initial excitement fades without ongoing value
56	- Fix: Surface new value over time; expand the use case; proactive engagement around the next value moment
57
58	If cohorts are getting worse over time (newer cohorts retain less): Product-market fit may be drifting — new users coming in are less well-matched to the product than early users
59	- Investigate: Has targeting changed? Has the product changed in ways that affect new users more than existing ones?
60
61	## Step 5 — Cohort Segmentation
62
63	Ask: can the cohort be segmented to find which users retain and which don't?
64
65	Segment by:
66	- Acquisition channel (organic vs. paid vs. referral)
67	- Activation action taken (did they complete the setup? Use the core feature?)
68	- Persona segment (from persona file)
69	- Cohort timing (January cohort vs. June cohort — did a product change affect one?)
70
71	This segmentation usually reveals: a subset of users who retain very well, and a subset who churn almost immediately. Understanding the difference drives the highest-ROI improvements.
72
73	## Step 6 — Output
74
75	Produce:
76	- Cohort data summary and pattern description
77	- Benchmark comparison with verdict: above/at/below benchmark
78	- Drop-off diagnosis with 2–3 most likely causes
79	- Segmentation recommendation (which cut would reveal the most insight?)
80	- Top 3 actions ranked by expected impact on retention
81	- One experiment to run in the next sprint to test the primary diagnosis

People who liked this also viewed

6 picks

Type

cohort-analysis

70stars33forks

View on GitHub

How to install cohort-analysis?

productfculty-aipm/pm-copilot-by-product-faculty/cohort-analysis

$npx -y skills add Productfculty-aipm/PM-Copilot-by-Product-Faculty --skill cohort-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Cohort Analysis
2
3	You are helping the user analyze cohort retention data to understand how well the product retains users over time, identify where users drop off, and recommend actions to improve retention.
4
5	Framework: AARRR (Retention stage), Lenny Rachitsky's retention benchmarks, North Star framework.
6
7	## Step 1 — Load Context
8
9	Read `memory/user-profile.md` for product stage and business model. Read `context/company/analytics-baseline.md` for existing retention baselines and targets.
10
11	## Step 2 — Understanding the Cohort Data
12
13	Ask the user to provide:
14	- The cohort data (can be a table, CSV, or described verbally)
15	- The cohort definition (what event defines "day 0"? — signup, first action, subscription start?)
16	- The measurement event (what defines "active" in day N? — login? Core action? Payment?)
17	- The timeframe (weekly or monthly cohorts? How many periods?)
18
19	If the data is provided, identify:
20	- Cohort size (how many users started in each cohort?)
21	- Retention rates at each time period (D1, D7, D30, D60, D90, or W1, W4, W12)
22	- Trend: are newer cohorts retaining better or worse than older ones?
23	- The "elbow" — where does the sharpest drop occur?
24
25	## Step 3 — Retention Benchmarks
26
27	Compare the user's retention to benchmarks from Lenny's data:
28
29	Mobile apps (consumer):
30	- D1: 40% is good; 25% is typical; < 15% is concerning
31	- D7: 20% is good; 10% is typical; < 5% is concerning
32	- D30: 10% is good; 5% is typical; < 2% is very concerning
33
34	SaaS / B2B:
35	- Week 1: 70%+ is good; 50–70% is typical; < 50% is concerning
36	- Month 1: 50%+ is good; 30–50% is typical
37	- Month 3: 30%+ is good; <20% is concerning
38
39	Freemium:
40	- Day 7: 15–25% returning users is typical
41	- Conversion to paid: 2–5% is typical for free-to-paid
42
43	Calibrate recommendations to the user's stage and model from memory.
44
45	## Step 4 — Diagnose the Drop-Off
46
47	Find the point of sharpest drop:
48
49	If the drop is at D1 (first day): Activation problem — users aren't experiencing the core value in their first session
50	- Fix: Improve onboarding flow; reduce time to first value; shorten the path to the "aha moment"
51
52	If the drop is at D7 (first week): Habit formation problem — the product isn't building a regular use pattern
53	- Fix: Add triggers for return (email, notification); deepen value in the core loop; improve D3–D5 experience
54
55	If the drop is at D30 (first month): Value realization problem — initial excitement fades without ongoing value
56	- Fix: Surface new value over time; expand the use case; proactive engagement around the next value moment
57
58	If cohorts are getting worse over time (newer cohorts retain less): Product-market fit may be drifting — new users coming in are less well-matched to the product than early users
59	- Investigate: Has targeting changed? Has the product changed in ways that affect new users more than existing ones?
60
61	## Step 5 — Cohort Segmentation
62
63	Ask: can the cohort be segmented to find which users retain and which don't?
64
65	Segment by:
66	- Acquisition channel (organic vs. paid vs. referral)
67	- Activation action taken (did they complete the setup? Use the core feature?)
68	- Persona segment (from persona file)
69	- Cohort timing (January cohort vs. June cohort — did a product change affect one?)
70
71	This segmentation usually reveals: a subset of users who retain very well, and a subset who churn almost immediately. Understanding the difference drives the highest-ROI improvements.
72
73	## Step 6 — Output
74
75	Produce:
76	- Cohort data summary and pattern description
77	- Benchmark comparison with verdict: above/at/below benchmark
78	- Drop-off diagnosis with 2–3 most likely causes
79	- Segmentation recommendation (which cut would reveal the most insight?)
80	- Top 3 actions ranked by expected impact on retention
81	- One experiment to run in the next sprint to test the primary diagnosis

People who liked this also viewed

6 picks

Type