shopify-admin-customer-acquisition-cost-by-source

Name: shopify-admin-customer-acquisition-cost-by-source
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-customer-acquisition-cost-by-source?

40rty-ai/shopify-admin-skills/shopify-admin-customer-acquisition-cost-by-source

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-customer-acquisition-cost-by-source

Installs into the current project.

Summary

Read-only: estimates customer acquisition cost (CAC) per traffic source by joining order count per landing site / referrer with configurable ad spend.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Estimates customer acquisition cost (CAC) for each traffic source by combining the number of new-customer orders attributed to a landing page / referrer with a configurable ad spend input per source. Output answers: "for every dollar spent on source X, how many new customers did we acquire and at what unit cost?" Read-only — no mutations. Provides the data foundation for paid-media budget reallocation.
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 (e.g., mystore.myshopify.com) \|
13	\| days_back \| integer \| no \| 30 \| Lookback window for orders to attribute \|
14	\| ad_spend \| object \| no \| {} \| Map of source name → spend in store currency, e.g. `{"google": 4500, "meta": 3200, "tiktok": 1800}` \|
15	\| new_customers_only \| bool \| no \| true \| Count only first-order customers as "acquired" \|
16	\| min_orders_per_source \| integer \| no \| 5 \| Minimum orders for a source to be reported \|
17	\| format \| string \| no \| human \| Output format: `human` or `json` \|
18
19	## Safety
20
21	> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time. Ad spend values are caller-provided; this skill does not pull from any ad platform.
22
23	## Workflow Steps
24
25	1. OPERATION: `orders` — query
26	Inputs: `query: "created_at:>='<NOW - days_back days>'"`, `first: 250`, select `customer { id, numberOfOrders }`, `customerJourneySummary { firstVisit { landingPage referrerUrl source } }`, `landingPageUrl`, `referrerUrl`, `totalPriceSet`, pagination cursor
27	Expected output: All orders in the window with referral and customer attribution; paginate until `hasNextPage: false`
28
29	2. Group orders by normalized source. Resolution order:
30	- `customerJourneySummary.firstVisit.source` if present
31	- Else parse domain from `referrerUrl`
32	- Else parse `landingPageUrl` UTM params (utm_source)
33	- Else bucket as `direct`
34
35	3. If `new_customers_only: true`, drop orders where `customer.numberOfOrders > 1` so each customer is counted once
36
37	4. Aggregate per source: `orders_count`, `new_customers_count`, `revenue_attributed`
38
39	5. Join with `ad_spend` map: `cac = ad_spend[source] / new_customers_count`. Sources without spend data report `cac: null` (organic / unattributed)
40
41	6. Filter to sources with `orders_count >= min_orders_per_source`
42
43	## GraphQL Operations
44
45	```graphql
46	# orders:query — validated against api_version 2025-01
47	query OrdersWithAttribution($query: String!, $after: String) {
48	orders(first: 250, after: $after, query: $query) {
49	edges {
50	node {
51	id
52	name
53	createdAt
54	landingPageUrl
55	referrerUrl
56	customerJourneySummary {
57	firstVisit {
58	landingPage
59	referrerUrl
60	source
61	sourceType
62	utmParameters {
63	source
64	medium
65	campaign
66	}
67	}
68	}
69	totalPriceSet {
70	shopMoney {
71	amount
72	currencyCode
73	}
74	}
75	customer {
76	id
77	numberOfOrders
78	}
79	}
80	}
81	pageInfo {
82	hasNextPage
83	endCursor
84	}
85	}
86	}
87	```
88
89	## Session Tracking
90
91	Claude MUST emit the following output at each stage. This is mandatory.
92
93	On start, emit:
94	```
95	╔══════════════════════════════════════════════╗
96	║ SKILL: Customer Acquisition Cost by Source ║
97	║ Store: <store domain> ║
98	║ Started: <YYYY-MM-DD HH:MM UTC> ║
99	╚══════════════════════════════════════════════╝
100	```
101
102	After each step, emit:
103	```
104	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
105	→ Params: <brief summary of key inputs>
106	→ Result: <count or outcome>
107	```
108
109	On completion, emit:
110
111	For `format: human` (default):
112	```
113	══════════════════════════════════════════════
114	CAC BY SOURCE (<days_back> days)
115	Orders analyzed: <n>
116	New customers acquired: <n>
117	Total ad spend (input): $<amount>
118	Blended CAC: $<amount>
119
120	By Source (sorted by CAC ascending):
121	google Customers: <n> Spend: $<n> CAC: $<n>
122	meta Customers: <n> Spend: $<n> CAC: $<n>
123	direct Customers: <n> Spend: — CAC: organic
124	referral Customers: <n> Spend: — CAC: organic
125
126	Output: cac_by_source_<date>.csv
127	══════════════════════════════════════════════
128	```
129
130	For `format: json`,

People who liked this also viewed

6 picks

Type

shopify-admin-customer-acquisition-cost-by-source

168stars17forks

View on GitHub

How to install shopify-admin-customer-acquisition-cost-by-source?

40rty-ai/shopify-admin-skills/shopify-admin-customer-acquisition-cost-by-source

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-customer-acquisition-cost-by-source

Installs into the current project.

Summary

Read-only: estimates customer acquisition cost (CAC) per traffic source by joining order count per landing site / referrer with configurable ad spend.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Estimates customer acquisition cost (CAC) for each traffic source by combining the number of new-customer orders attributed to a landing page / referrer with a configurable ad spend input per source. Output answers: "for every dollar spent on source X, how many new customers did we acquire and at what unit cost?" Read-only — no mutations. Provides the data foundation for paid-media budget reallocation.
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 (e.g., mystore.myshopify.com) \|
13	\| days_back \| integer \| no \| 30 \| Lookback window for orders to attribute \|
14	\| ad_spend \| object \| no \| {} \| Map of source name → spend in store currency, e.g. `{"google": 4500, "meta": 3200, "tiktok": 1800}` \|
15	\| new_customers_only \| bool \| no \| true \| Count only first-order customers as "acquired" \|
16	\| min_orders_per_source \| integer \| no \| 5 \| Minimum orders for a source to be reported \|
17	\| format \| string \| no \| human \| Output format: `human` or `json` \|
18
19	## Safety
20
21	> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time. Ad spend values are caller-provided; this skill does not pull from any ad platform.
22
23	## Workflow Steps
24
25	1. OPERATION: `orders` — query
26	Inputs: `query: "created_at:>='<NOW - days_back days>'"`, `first: 250`, select `customer { id, numberOfOrders }`, `customerJourneySummary { firstVisit { landingPage referrerUrl source } }`, `landingPageUrl`, `referrerUrl`, `totalPriceSet`, pagination cursor
27	Expected output: All orders in the window with referral and customer attribution; paginate until `hasNextPage: false`
28
29	2. Group orders by normalized source. Resolution order:
30	- `customerJourneySummary.firstVisit.source` if present
31	- Else parse domain from `referrerUrl`
32	- Else parse `landingPageUrl` UTM params (utm_source)
33	- Else bucket as `direct`
34
35	3. If `new_customers_only: true`, drop orders where `customer.numberOfOrders > 1` so each customer is counted once
36
37	4. Aggregate per source: `orders_count`, `new_customers_count`, `revenue_attributed`
38
39	5. Join with `ad_spend` map: `cac = ad_spend[source] / new_customers_count`. Sources without spend data report `cac: null` (organic / unattributed)
40
41	6. Filter to sources with `orders_count >= min_orders_per_source`
42
43	## GraphQL Operations
44
45	```graphql
46	# orders:query — validated against api_version 2025-01
47	query OrdersWithAttribution($query: String!, $after: String) {
48	orders(first: 250, after: $after, query: $query) {
49	edges {
50	node {
51	id
52	name
53	createdAt
54	landingPageUrl
55	referrerUrl
56	customerJourneySummary {
57	firstVisit {
58	landingPage
59	referrerUrl
60	source
61	sourceType
62	utmParameters {
63	source
64	medium
65	campaign
66	}
67	}
68	}
69	totalPriceSet {
70	shopMoney {
71	amount
72	currencyCode
73	}
74	}
75	customer {
76	id
77	numberOfOrders
78	}
79	}
80	}
81	pageInfo {
82	hasNextPage
83	endCursor
84	}
85	}
86	}
87	```
88
89	## Session Tracking
90
91	Claude MUST emit the following output at each stage. This is mandatory.
92
93	On start, emit:
94	```
95	╔══════════════════════════════════════════════╗
96	║ SKILL: Customer Acquisition Cost by Source ║
97	║ Store: <store domain> ║
98	║ Started: <YYYY-MM-DD HH:MM UTC> ║
99	╚══════════════════════════════════════════════╝
100	```
101
102	After each step, emit:
103	```
104	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
105	→ Params: <brief summary of key inputs>
106	→ Result: <count or outcome>
107	```
108
109	On completion, emit:
110
111	For `format: human` (default):
112	```
113	══════════════════════════════════════════════
114	CAC BY SOURCE (<days_back> days)
115	Orders analyzed: <n>
116	New customers acquired: <n>
117	Total ad spend (input): $<amount>
118	Blended CAC: $<amount>
119
120	By Source (sorted by CAC ascending):
121	google Customers: <n> Spend: $<n> CAC: $<n>
122	meta Customers: <n> Spend: $<n> CAC: $<n>
123	direct Customers: <n> Spend: — CAC: organic
124	referral Customers: <n> Spend: — CAC: organic
125
126	Output: cac_by_source_<date>.csv
127	══════════════════════════════════════════════
128	```
129
130	For `format: json`,

People who liked this also viewed

6 picks

Type