shopify-admin-churn-risk-scorer

Name: shopify-admin-churn-risk-scorer
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-churn-risk-scorer?

40rty-ai/shopify-admin-skills/shopify-admin-churn-risk-scorer

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-churn-risk-scorer

Installs into the current project.

Summary

Read-only: scores customers by churn probability based on purchase recency, frequency decay, and expected repurchase intervals.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Predicts which customers are at risk of churning by analyzing their purchase patterns against their historical buying frequency. Calculates an expected next-purchase date for each repeat customer, then scores churn risk based on how overdue they are. Read-only — no mutations.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session: `shopify store auth --store <domain> --scopes read_orders,read_customers`
6	- API scopes: `read_orders`, `read_customers`
7
8	## Parameters
9
10	\| Parameter \| Type \| Required \| Default \| Description \|
11	\|-----------\|------\|----------\|---------\|-------------\|
12	\| store \| string \| yes \| — \| Store domain \|
13	\| days_back \| integer \| no \| 365 \| Historical window for purchase pattern analysis \|
14	\| min_orders \| integer \| no \| 2 \| Minimum orders to calculate purchase interval (need 2+ for frequency) \|
15	\| risk_threshold \| float \| no \| 1.5 \| Multiplier of avg purchase interval before flagging as at-risk \|
16	\| format \| string \| no \| human \| Output format: `human` or `json` \|
17
18	## Safety
19
20	> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time.
21
22	## Churn Risk Scoring Model
23
24	For each customer with `min_orders` or more purchases:
25
26	1. Average Purchase Interval (API) = total days between first and last order / (order_count - 1)
27	2. Days Since Last Order (DSLO) = today - last_order_date
28	3. Overdue Ratio = DSLO / API
29	4. Churn Risk Score (0-100):
30	- Overdue ratio ≤ 1.0 → Score 0-20 (Active)
31	- Overdue ratio 1.0–1.5 → Score 20-50 (Cooling)
32	- Overdue ratio 1.5–2.5 → Score 50-80 (At Risk)
33	- Overdue ratio > 2.5 → Score 80-100 (Likely Churned)
34	5. Customer Lifetime Value (CLV) = total spend / customer age in years × expected remaining years
35
36	## Workflow Steps
37
38	1. OPERATION: `orders` — query
39	Inputs: `query: "created_at:>='<NOW - days_back days>'"`, `first: 250`, select `createdAt`, `totalPriceSet`, `customer { id, email, firstName, lastName }`, pagination cursor
40	Expected output: All orders with customer association
41
42	2. Group orders by customer, calculate per customer:
43	- Order dates (sorted chronologically)
44	- Average purchase interval
45	- Days since last order
46	- Total spend
47	- Order count
48
49	3. OPERATION: `customers` — query (enrichment)
50	Inputs: Customer IDs for at-risk and likely-churned segments
51	Expected output: Contact details, tags, total spend
52
53	4. Calculate churn risk score and classify into segments
54
55	5. Estimate revenue at risk = sum of (annual_spend × churn_probability) for at-risk customers
56
57	## GraphQL Operations
58
59	```graphql
60	# orders:query — validated against api_version 2025-01
61	query OrdersForChurnAnalysis($query: String!, $after: String) {
62	orders(first: 250, after: $after, query: $query) {
63	edges {
64	node {
65	createdAt
66	totalPriceSet { shopMoney { amount currencyCode } }
67	customer {
68	id
69	email
70	firstName
71	lastName
72	numberOfOrders
73	}
74	}
75	}
76	pageInfo { hasNextPage endCursor }
77	}
78	}
79	```
80
81	```graphql
82	# customers:query — validated against api_version 2025-01
83	query AtRiskCustomers($ids: [ID!]!) {
84	nodes(ids: $ids) {
85	... on Customer {
86	id
87	email
88	firstName
89	lastName
90	totalSpentV2 { amount currencyCode }
91	numberOfOrders
92	tags
93	createdAt
94	}
95	}
96	}
97	```
98
99	## Session Tracking
100
101	Claude MUST emit the following output at each stage. This is mandatory.
102
103	On start, emit:
104	```
105	╔══════════════════════════════════════════════╗
106	║ SKILL: Churn Risk Scorer ║
107	║ Store: <store domain> ║
108	║ Started: <YYYY-MM-DD HH:MM UTC> ║
109	╚══════════════════════════════════════════════╝
110	```
111
112	After each step, emit:
113	```
114	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
115	→ Params: <brief summary of key inputs>
116	→ Result: <count or outcome>
117	```
118
119	On completion, emit:
120
121	For `format: human` (default):
122	```
123	══════════════════════════════════════════════
124	CHURN RISK REPORT (<days_back> days analyzed)
125	Repeat customers scored: <n>
126	─────────────────────────────
127	Active (score 0-20): <n> (<pct>%)
128	Cooling (score 20-50): <n> (<pct>%)
129	At Risk (score 50-80): <n> (<pct>%) ⚠️
130	Likely Churned (80-100): <n> (<pct>%) 🔴
131
132	Revenue at risk: $<amount>/year
133
134	Top at-risk by value:
135	<name> (<email>) Score: <n> Last order: <date> Lifetime: $<n>
136
137	Output: churn_risk_<date>.csv
138	══════════════════════════════════════════════
139	```
140
141	## Output Format
142	CSV file `churn_risk_<YYYY-MM-DD>.csv` with columns:
143	`customer_id`, `email`, `first_name`,

People who liked this also viewed

6 picks

Type

shopify-admin-churn-risk-scorer

168stars17forks

View on GitHub

How to install shopify-admin-churn-risk-scorer?

40rty-ai/shopify-admin-skills/shopify-admin-churn-risk-scorer

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-churn-risk-scorer

Installs into the current project.

Summary

Read-only: scores customers by churn probability based on purchase recency, frequency decay, and expected repurchase intervals.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Predicts which customers are at risk of churning by analyzing their purchase patterns against their historical buying frequency. Calculates an expected next-purchase date for each repeat customer, then scores churn risk based on how overdue they are. Read-only — no mutations.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session: `shopify store auth --store <domain> --scopes read_orders,read_customers`
6	- API scopes: `read_orders`, `read_customers`
7
8	## Parameters
9
10	\| Parameter \| Type \| Required \| Default \| Description \|
11	\|-----------\|------\|----------\|---------\|-------------\|
12	\| store \| string \| yes \| — \| Store domain \|
13	\| days_back \| integer \| no \| 365 \| Historical window for purchase pattern analysis \|
14	\| min_orders \| integer \| no \| 2 \| Minimum orders to calculate purchase interval (need 2+ for frequency) \|
15	\| risk_threshold \| float \| no \| 1.5 \| Multiplier of avg purchase interval before flagging as at-risk \|
16	\| format \| string \| no \| human \| Output format: `human` or `json` \|
17
18	## Safety
19
20	> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time.
21
22	## Churn Risk Scoring Model
23
24	For each customer with `min_orders` or more purchases:
25
26	1. Average Purchase Interval (API) = total days between first and last order / (order_count - 1)
27	2. Days Since Last Order (DSLO) = today - last_order_date
28	3. Overdue Ratio = DSLO / API
29	4. Churn Risk Score (0-100):
30	- Overdue ratio ≤ 1.0 → Score 0-20 (Active)
31	- Overdue ratio 1.0–1.5 → Score 20-50 (Cooling)
32	- Overdue ratio 1.5–2.5 → Score 50-80 (At Risk)
33	- Overdue ratio > 2.5 → Score 80-100 (Likely Churned)
34	5. Customer Lifetime Value (CLV) = total spend / customer age in years × expected remaining years
35
36	## Workflow Steps
37
38	1. OPERATION: `orders` — query
39	Inputs: `query: "created_at:>='<NOW - days_back days>'"`, `first: 250`, select `createdAt`, `totalPriceSet`, `customer { id, email, firstName, lastName }`, pagination cursor
40	Expected output: All orders with customer association
41
42	2. Group orders by customer, calculate per customer:
43	- Order dates (sorted chronologically)
44	- Average purchase interval
45	- Days since last order
46	- Total spend
47	- Order count
48
49	3. OPERATION: `customers` — query (enrichment)
50	Inputs: Customer IDs for at-risk and likely-churned segments
51	Expected output: Contact details, tags, total spend
52
53	4. Calculate churn risk score and classify into segments
54
55	5. Estimate revenue at risk = sum of (annual_spend × churn_probability) for at-risk customers
56
57	## GraphQL Operations
58
59	```graphql
60	# orders:query — validated against api_version 2025-01
61	query OrdersForChurnAnalysis($query: String!, $after: String) {
62	orders(first: 250, after: $after, query: $query) {
63	edges {
64	node {
65	createdAt
66	totalPriceSet { shopMoney { amount currencyCode } }
67	customer {
68	id
69	email
70	firstName
71	lastName
72	numberOfOrders
73	}
74	}
75	}
76	pageInfo { hasNextPage endCursor }
77	}
78	}
79	```
80
81	```graphql
82	# customers:query — validated against api_version 2025-01
83	query AtRiskCustomers($ids: [ID!]!) {
84	nodes(ids: $ids) {
85	... on Customer {
86	id
87	email
88	firstName
89	lastName
90	totalSpentV2 { amount currencyCode }
91	numberOfOrders
92	tags
93	createdAt
94	}
95	}
96	}
97	```
98
99	## Session Tracking
100
101	Claude MUST emit the following output at each stage. This is mandatory.
102
103	On start, emit:
104	```
105	╔══════════════════════════════════════════════╗
106	║ SKILL: Churn Risk Scorer ║
107	║ Store: <store domain> ║
108	║ Started: <YYYY-MM-DD HH:MM UTC> ║
109	╚══════════════════════════════════════════════╝
110	```
111
112	After each step, emit:
113	```
114	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
115	→ Params: <brief summary of key inputs>
116	→ Result: <count or outcome>
117	```
118
119	On completion, emit:
120
121	For `format: human` (default):
122	```
123	══════════════════════════════════════════════
124	CHURN RISK REPORT (<days_back> days analyzed)
125	Repeat customers scored: <n>
126	─────────────────────────────
127	Active (score 0-20): <n> (<pct>%)
128	Cooling (score 20-50): <n> (<pct>%)
129	At Risk (score 50-80): <n> (<pct>%) ⚠️
130	Likely Churned (80-100): <n> (<pct>%) 🔴
131
132	Revenue at risk: $<amount>/year
133
134	Top at-risk by value:
135	<name> (<email>) Score: <n> Last order: <date> Lifetime: $<n>
136
137	Output: churn_risk_<date>.csv
138	══════════════════════════════════════════════
139	```
140
141	## Output Format
142	CSV file `churn_risk_<YYYY-MM-DD>.csv` with columns:
143	`customer_id`, `email`, `first_name`,

People who liked this also viewed

6 picks

Type