shopify-admin-agentic-product-taxonomy

Name: shopify-admin-agentic-product-taxonomy
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-agentic-product-taxonomy?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-product-taxonomy

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-product-taxonomy

Installs into the current project.

Summary

Assign every product a Shopify Standard Product Taxonomy category so AI agents can map a shopper's intent to the right category and surface the store's products.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	AI shopping agents resolve a query ("running shoes", "office chair", "sustainable sneakers") to a taxonomy node, then retrieve products in that node. Products with no Standard Product Taxonomy category are invisible to that mapping — they only surface on exact keyword luck. This skill finds uncategorized (or mis-categorized) products and assigns the correct Shopify standard taxonomy category, inferred from title/type/tags and confirmed against the live taxonomy tree. Fixes `category-taxonomy-api` and lifts `catalog-intent-alignment`.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session (`shopify auth login --store <domain>`)
6	- Required API scopes: `read_products`, `write_products`
7
8	## Parameters
9	All skills accept these universal parameters:
10
11	\| Parameter \| Type \| Required \| Default \| Description \|
12	\|-----------\|--------\|----------\|---------\|-------------\|
13	\| store \| string \| yes \| — \| Store domain (e.g., mystore.myshopify.com) \|
14	\| format \| string \| no \| human \| Output format: `human` (default) or `json` \|
15	\| dry_run \| bool \| no \| false \| Preview mutations without executing \|
16
17	Skill-specific parameters:
18
19	\| Parameter \| Type \| Required \| Default \| Description \|
20	\|-----------\|------\|----------\|---------\|-------------\|
21	\| collection_id \| string \| no \| — \| Limit to a collection GID \|
22	\| tag \| string \| no \| — \| Limit to a product tag \|
23	\| only_missing \| bool \| no \| true \| If true, only assign products with no category; if false, also review mismatches \|
24	\| confidence_floor \| float \| no \| 0.7 \| Skip products whose best taxonomy match scores below this \|
25
26	## Safety
27
28	> ⚠️ Step 4 (`productUpdate`) sets the `category` on live products, which affects storefront facets, marketplaces, and tax. A wrong category mis-files a product everywhere. Run `dry_run: true`, review the proposed `product → category` mapping, and only auto-assign matches above `confidence_floor`; queue the rest for human review.
29
30	## Workflow Steps
31
32	1. OPERATION: `products` — query
33	Inputs: `first: 250`, optional filter; fields `title`, `productType`, `tags`, `category{ id fullName }`; paginate.
34	Expected output: Products with their current category (or null).
35
36	2. OPERATION: `taxonomy` — query
37	Inputs: search the standard taxonomy tree by candidate terms derived from each product's type/title.
38	Expected output: Candidate taxonomy category nodes (id + fullName) to match against.
39
40	3. COMPUTE (no API): score each product against candidate nodes; pick the best ≥ `confidence_floor`. Emit the proposed mapping.
41
42	4. OPERATION: `productUpdate` — mutation
43	Inputs: `{ id, category: <taxonomyCategoryId> }` per confident match.
44	Expected output: Updated product category; collect `userErrors`.
45
46	## GraphQL Operations
47
48	```graphql
49	# products:query — validated against api_version 2025-01
50	query TaxonomyProducts($first: Int!, $after: String, $query: String) {
51	products(first: $first, after: $after, query: $query) {
52	edges {
53	node {
54	id
55	title
56	productType
57	tags
58	category { id fullName }
59	}
60	}
61	pageInfo { hasNextPage endCursor }
62	}
63	}
64	```
65
66	```graphql
67	# taxonomy:query — validated against api_version 2025-01
68	query TaxonomySearch($search: String) {
69	taxonomy {
70	categories(first: 20, search: $search) {
71	edges { node { id fullName isLeaf level } }
72	}
73	}
74	}
75	```
76
77	```graphql
78	# productUpdate:mutation — validated against api_version 2025-01
79	mutation TaxonomyAssign($input: ProductInput!) {
80	productUpdate(input: $input) {
81	product { id category { id fullName } }
82	userErrors { field message }
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: <skill name> ║
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	If `dry_run: true`, prefix every mutation step with `[DRY RUN]` and do not execute it.
108
109	On completion, emit:
110
111	For `format: human` (default):
112	```
113	══════════════════════════════════════════════
114	OUTCOME SUMMARY
115	<Metric label>: <value>
116	Errors: 0

People who liked this also viewed

6 picks

Type

shopify-admin-agentic-product-taxonomy

168stars17forks

View on GitHub

How to install shopify-admin-agentic-product-taxonomy?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-product-taxonomy

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-product-taxonomy

Installs into the current project.

Summary

Assign every product a Shopify Standard Product Taxonomy category so AI agents can map a shopper's intent to the right category and surface the store's products.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	AI shopping agents resolve a query ("running shoes", "office chair", "sustainable sneakers") to a taxonomy node, then retrieve products in that node. Products with no Standard Product Taxonomy category are invisible to that mapping — they only surface on exact keyword luck. This skill finds uncategorized (or mis-categorized) products and assigns the correct Shopify standard taxonomy category, inferred from title/type/tags and confirmed against the live taxonomy tree. Fixes `category-taxonomy-api` and lifts `catalog-intent-alignment`.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session (`shopify auth login --store <domain>`)
6	- Required API scopes: `read_products`, `write_products`
7
8	## Parameters
9	All skills accept these universal parameters:
10
11	\| Parameter \| Type \| Required \| Default \| Description \|
12	\|-----------\|--------\|----------\|---------\|-------------\|
13	\| store \| string \| yes \| — \| Store domain (e.g., mystore.myshopify.com) \|
14	\| format \| string \| no \| human \| Output format: `human` (default) or `json` \|
15	\| dry_run \| bool \| no \| false \| Preview mutations without executing \|
16
17	Skill-specific parameters:
18
19	\| Parameter \| Type \| Required \| Default \| Description \|
20	\|-----------\|------\|----------\|---------\|-------------\|
21	\| collection_id \| string \| no \| — \| Limit to a collection GID \|
22	\| tag \| string \| no \| — \| Limit to a product tag \|
23	\| only_missing \| bool \| no \| true \| If true, only assign products with no category; if false, also review mismatches \|
24	\| confidence_floor \| float \| no \| 0.7 \| Skip products whose best taxonomy match scores below this \|
25
26	## Safety
27
28	> ⚠️ Step 4 (`productUpdate`) sets the `category` on live products, which affects storefront facets, marketplaces, and tax. A wrong category mis-files a product everywhere. Run `dry_run: true`, review the proposed `product → category` mapping, and only auto-assign matches above `confidence_floor`; queue the rest for human review.
29
30	## Workflow Steps
31
32	1. OPERATION: `products` — query
33	Inputs: `first: 250`, optional filter; fields `title`, `productType`, `tags`, `category{ id fullName }`; paginate.
34	Expected output: Products with their current category (or null).
35
36	2. OPERATION: `taxonomy` — query
37	Inputs: search the standard taxonomy tree by candidate terms derived from each product's type/title.
38	Expected output: Candidate taxonomy category nodes (id + fullName) to match against.
39
40	3. COMPUTE (no API): score each product against candidate nodes; pick the best ≥ `confidence_floor`. Emit the proposed mapping.
41
42	4. OPERATION: `productUpdate` — mutation
43	Inputs: `{ id, category: <taxonomyCategoryId> }` per confident match.
44	Expected output: Updated product category; collect `userErrors`.
45
46	## GraphQL Operations
47
48	```graphql
49	# products:query — validated against api_version 2025-01
50	query TaxonomyProducts($first: Int!, $after: String, $query: String) {
51	products(first: $first, after: $after, query: $query) {
52	edges {
53	node {
54	id
55	title
56	productType
57	tags
58	category { id fullName }
59	}
60	}
61	pageInfo { hasNextPage endCursor }
62	}
63	}
64	```
65
66	```graphql
67	# taxonomy:query — validated against api_version 2025-01
68	query TaxonomySearch($search: String) {
69	taxonomy {
70	categories(first: 20, search: $search) {
71	edges { node { id fullName isLeaf level } }
72	}
73	}
74	}
75	```
76
77	```graphql
78	# productUpdate:mutation — validated against api_version 2025-01
79	mutation TaxonomyAssign($input: ProductInput!) {
80	productUpdate(input: $input) {
81	product { id category { id fullName } }
82	userErrors { field message }
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: <skill name> ║
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	If `dry_run: true`, prefix every mutation step with `[DRY RUN]` and do not execute it.
108
109	On completion, emit:
110
111	For `format: human` (default):
112	```
113	══════════════════════════════════════════════
114	OUTCOME SUMMARY
115	<Metric label>: <value>
116	Errors: 0

People who liked this also viewed

6 picks

Type