shopify-admin-frequently-bought-together

Name: shopify-admin-frequently-bought-together
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-frequently-bought-together?

40rty-ai/shopify-admin-skills/shopify-admin-frequently-bought-together

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-frequently-bought-together

Installs into the current project.

Summary

Read-only: mines order history to find product pairs and triplets frequently purchased together, generating cross-sell and bundle recommendations.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Analyzes order history to discover which products are frequently purchased together. Calculates co-occurrence frequency, lift scores, and confidence metrics to generate data-driven cross-sell recommendations and bundle candidates. Read-only — no mutations.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session: `shopify store auth --store <domain> --scopes read_orders,read_products`
6	- API scopes: `read_orders`, `read_products`
7
8	## Parameters
9
10	\| Parameter \| Type \| Required \| Default \| Description \|
11	\|-----------\|------\|----------\|---------\|-------------\|
12	\| store \| string \| yes \| — \| Store domain \|
13	\| days_back \| integer \| no \| 180 \| Order lookback window \|
14	\| min_support \| integer \| no \| 3 \| Minimum co-occurrence count to report a pair \|
15	\| max_results \| integer \| no \| 25 \| Maximum product pairs to return \|
16	\| group_size \| integer \| no \| 2 \| Pair size: `2` for pairs, `3` for triplets \|
17	\| collection_filter \| string \| no \| — \| Limit to products in a specific collection \|
18	\| format \| string \| no \| human \| Output format: `human` or `json` \|
19
20	## Safety
21
22	> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time.
23
24	## Workflow Steps
25
26	1. OPERATION: `orders` — query
27	Inputs: `query: "created_at:>='<NOW - days_back days>'"`, `first: 250`, select `lineItems { product { id, title } }`, pagination cursor
28	Expected output: All orders with product-level line items
29
30	2. For each order with 2+ distinct products, generate all product pair combinations
31
32	3. Build co-occurrence matrix:
33	- Support = number of orders containing both products
34	- Confidence(A→B) = P(B\|A) = support(A,B) / support(A)
35	- Lift = confidence(A→B) / P(B) — lift > 1.0 means positive association
36
37	4. OPERATION: `products` — query (enrichment)
38	Inputs: Product IDs from top pairs for titles, images, prices
39	Expected output: Product details for display
40
41	5. Rank pairs by lift score (descending), filter by min_support
42
43	## GraphQL Operations
44
45	```graphql
46	# orders:query — validated against api_version 2025-01
47	query OrderLineItems($query: String!, $after: String) {
48	orders(first: 250, after: $after, query: $query) {
49	edges {
50	node {
51	id
52	lineItems(first: 50) {
53	edges {
54	node {
55	product { id title }
56	quantity
57	}
58	}
59	}
60	}
61	}
62	pageInfo { hasNextPage endCursor }
63	}
64	}
65	```
66
67	```graphql
68	# products:query — validated against api_version 2025-01
69	query ProductDetails($ids: [ID!]!) {
70	nodes(ids: $ids) {
71	... on Product {
72	id
73	title
74	vendor
75	productType
76	priceRangeV2 {
77	minVariantPrice { amount currencyCode }
78	maxVariantPrice { amount currencyCode }
79	}
80	totalInventory
81	status
82	}
83	}
84	}
85	```
86
87	## Session Tracking
88
89	Claude MUST emit the following output at each stage. This is mandatory.
90
91	On start, emit:
92	```
93	╔══════════════════════════════════════════════╗
94	║ SKILL: Frequently Bought Together ║
95	║ Store: <store domain> ║
96	║ Started: <YYYY-MM-DD HH:MM UTC> ║
97	╚══════════════════════════════════════════════╝
98	```
99
100	After each step, emit:
101	```
102	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
103	→ Params: <brief summary of key inputs>
104	→ Result: <count or outcome>
105	```
106
107	On completion, emit:
108
109	For `format: human` (default):
110	```
111	══════════════════════════════════════════════
112	FREQUENTLY BOUGHT TOGETHER (<days_back> days, <n> orders analyzed)
113	Unique product pairs found: <n>
114	Pairs meeting min_support: <n>
115
116	TOP PAIRS BY LIFT:
117	#1 "<product A>" + "<product B>"
118	Support: <n> orders Lift: <n>x Confidence: <pct>%
119
120	#2 "<product A>" + "<product B>"
121	Support: <n> orders Lift: <n>x Confidence: <pct>%
122
123	BUNDLE CANDIDATES (high support + high lift):
124	"<product A>" + "<product B>" → Suggested bundle price: $<n>
125
126	Output: fbt_pairs_<date>.csv
127	══════════════════════════════════════════════
128	```
129
130	## Output Format
131	CSV file `fbt_pairs_<YYYY-MM-DD>.csv` with columns:
132	`product_a_id`, `product_a_title`, `product_b_id`, `product_b_title`, `support`, `confidence_a_to_b`, `confidence_b_to_a`, `lift`, `combined_avg_price`
133
134	## Error Handling
135	\| Error \| Cause \| Recovery \|
136	\|-------\|-------\|----------\|
137	\| `THROTTLED` \| API rate limit exceeded \| Wait 2 seconds, retry up to 3 times \|
138	\| Single-item orders only \| Store with no multi-item orders \| Report empty — suggest longer lookback window \|
139	\| Too many products \| Combinatorial explosion \| Limit to top 500 products

People who liked this also viewed

6 picks

Type

shopify-admin-frequently-bought-together

168stars17forks

View on GitHub

How to install shopify-admin-frequently-bought-together?

40rty-ai/shopify-admin-skills/shopify-admin-frequently-bought-together

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-frequently-bought-together

Installs into the current project.

Summary

Read-only: mines order history to find product pairs and triplets frequently purchased together, generating cross-sell and bundle recommendations.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Analyzes order history to discover which products are frequently purchased together. Calculates co-occurrence frequency, lift scores, and confidence metrics to generate data-driven cross-sell recommendations and bundle candidates. Read-only — no mutations.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session: `shopify store auth --store <domain> --scopes read_orders,read_products`
6	- API scopes: `read_orders`, `read_products`
7
8	## Parameters
9
10	\| Parameter \| Type \| Required \| Default \| Description \|
11	\|-----------\|------\|----------\|---------\|-------------\|
12	\| store \| string \| yes \| — \| Store domain \|
13	\| days_back \| integer \| no \| 180 \| Order lookback window \|
14	\| min_support \| integer \| no \| 3 \| Minimum co-occurrence count to report a pair \|
15	\| max_results \| integer \| no \| 25 \| Maximum product pairs to return \|
16	\| group_size \| integer \| no \| 2 \| Pair size: `2` for pairs, `3` for triplets \|
17	\| collection_filter \| string \| no \| — \| Limit to products in a specific collection \|
18	\| format \| string \| no \| human \| Output format: `human` or `json` \|
19
20	## Safety
21
22	> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time.
23
24	## Workflow Steps
25
26	1. OPERATION: `orders` — query
27	Inputs: `query: "created_at:>='<NOW - days_back days>'"`, `first: 250`, select `lineItems { product { id, title } }`, pagination cursor
28	Expected output: All orders with product-level line items
29
30	2. For each order with 2+ distinct products, generate all product pair combinations
31
32	3. Build co-occurrence matrix:
33	- Support = number of orders containing both products
34	- Confidence(A→B) = P(B\|A) = support(A,B) / support(A)
35	- Lift = confidence(A→B) / P(B) — lift > 1.0 means positive association
36
37	4. OPERATION: `products` — query (enrichment)
38	Inputs: Product IDs from top pairs for titles, images, prices
39	Expected output: Product details for display
40
41	5. Rank pairs by lift score (descending), filter by min_support
42
43	## GraphQL Operations
44
45	```graphql
46	# orders:query — validated against api_version 2025-01
47	query OrderLineItems($query: String!, $after: String) {
48	orders(first: 250, after: $after, query: $query) {
49	edges {
50	node {
51	id
52	lineItems(first: 50) {
53	edges {
54	node {
55	product { id title }
56	quantity
57	}
58	}
59	}
60	}
61	}
62	pageInfo { hasNextPage endCursor }
63	}
64	}
65	```
66
67	```graphql
68	# products:query — validated against api_version 2025-01
69	query ProductDetails($ids: [ID!]!) {
70	nodes(ids: $ids) {
71	... on Product {
72	id
73	title
74	vendor
75	productType
76	priceRangeV2 {
77	minVariantPrice { amount currencyCode }
78	maxVariantPrice { amount currencyCode }
79	}
80	totalInventory
81	status
82	}
83	}
84	}
85	```
86
87	## Session Tracking
88
89	Claude MUST emit the following output at each stage. This is mandatory.
90
91	On start, emit:
92	```
93	╔══════════════════════════════════════════════╗
94	║ SKILL: Frequently Bought Together ║
95	║ Store: <store domain> ║
96	║ Started: <YYYY-MM-DD HH:MM UTC> ║
97	╚══════════════════════════════════════════════╝
98	```
99
100	After each step, emit:
101	```
102	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
103	→ Params: <brief summary of key inputs>
104	→ Result: <count or outcome>
105	```
106
107	On completion, emit:
108
109	For `format: human` (default):
110	```
111	══════════════════════════════════════════════
112	FREQUENTLY BOUGHT TOGETHER (<days_back> days, <n> orders analyzed)
113	Unique product pairs found: <n>
114	Pairs meeting min_support: <n>
115
116	TOP PAIRS BY LIFT:
117	#1 "<product A>" + "<product B>"
118	Support: <n> orders Lift: <n>x Confidence: <pct>%
119
120	#2 "<product A>" + "<product B>"
121	Support: <n> orders Lift: <n>x Confidence: <pct>%
122
123	BUNDLE CANDIDATES (high support + high lift):
124	"<product A>" + "<product B>" → Suggested bundle price: $<n>
125
126	Output: fbt_pairs_<date>.csv
127	══════════════════════════════════════════════
128	```
129
130	## Output Format
131	CSV file `fbt_pairs_<YYYY-MM-DD>.csv` with columns:
132	`product_a_id`, `product_a_title`, `product_b_id`, `product_b_title`, `support`, `confidence_a_to_b`, `confidence_b_to_a`, `lift`, `combined_avg_price`
133
134	## Error Handling
135	\| Error \| Cause \| Recovery \|
136	\|-------\|-------\|----------\|
137	\| `THROTTLED` \| API rate limit exceeded \| Wait 2 seconds, retry up to 3 times \|
138	\| Single-item orders only \| Store with no multi-item orders \| Report empty — suggest longer lookback window \|
139	\| Too many products \| Combinatorial explosion \| Limit to top 500 products

People who liked this also viewed

6 picks

Type