shopify-admin-agentic-metafields-setup

Name: shopify-admin-agentic-metafields-setup
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-agentic-metafields-setup?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-metafields-setup

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-metafields-setup

Installs into the current project.

Summary

Define and populate agentic-commerce metafields (material, attributes, key features, specs, sizing) so AI agents can filter and match products to specific shopper requirements.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	AI agents answer constrained queries — "squat-proof leggings under $60", "eucalyptus slip-ons", "machine-washable wool" — by filtering on structured attributes. If those attributes live only in prose (or nowhere), the agent can't filter and your products drop out of the result set. This skill establishes a small, standard set of agentic metafield definitions (material, key features, care, fit, specs) and populates them across the catalog from existing product signals, so agents can match products to requirements. Fixes `listing-metafields`, `variant-metadata`, and `sizing-specs-structured`.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session (`shopify auth login --store <domain>`)
6	- Required API scopes: `read_products`, `write_products`, `read_metaobject_definitions`, `write_metaobject_definitions` (for definitions)
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	\| namespace \| string \| no \| agentic \| Metafield namespace to create/populate under \|
22	\| keys \| string \| no \| material,features,care,fit,specs \| Comma list of metafield keys to ensure exist \|
23	\| collection_id \| string \| no \| — \| Limit population to a collection GID \|
24	\| tag \| string \| no \| — \| Limit population to a product tag \|
25	\| populate_from \| string \| no \| tags,options,description \| Sources to infer values from (no fabrication beyond these) \|
26
27	## Safety
28
29	> ⚠️ Step 2 (`metafieldDefinitionCreate`) and Step 4 (`metafieldsSet`) write store schema + product data. Definitions are cheap to add but clutter the admin if mis-namespaced; values written from inference can be wrong. Run `dry_run: true`, review the proposed definitions and the value preview, and only populate values inferred with high confidence — leave the rest blank for human fill.
30
31	## Workflow Steps
32
33	1. OPERATION: `metafieldDefinitions` — query
34	Inputs: `ownerType: PRODUCT`, `namespace: <namespace>`
35	Expected output: Which target keys already have definitions (skip those).
36
37	2. OPERATION: `metafieldDefinitionCreate` — mutation
38	Inputs: one per missing key: `{ namespace, key, name, ownerType: PRODUCT, type: "single_line_text_field" \| "list.single_line_text_field" }`
39	Expected output: Created definitions; collect `userErrors` (e.g. already-taken).
40
41	3. OPERATION: `products` — query
42	Inputs: `first: 250`, optional filter; fields `tags`, `options`, `descriptionHtml`, existing `metafields(namespace)`; paginate.
43	Expected output: Products + the signals to infer attribute values from.
44
45	4. OPERATION: `metafieldsSet` — mutation
46	Inputs: batches of `{ ownerId, namespace, key, value, type }` for confidently-inferred, currently-empty values.
47	Expected output: Set metafields; collect `userErrors`.
48
49	## GraphQL Operations
50
51	```graphql
52	# metafieldDefinitions:query — validated against api_version 2025-01
53	query AgenticMetafieldDefs($namespace: String!) {
54	metafieldDefinitions(first: 50, ownerType: PRODUCT, namespace: $namespace) {
55	edges { node { id namespace key name type { name } } }
56	}
57	}
58	```
59
60	```graphql
61	# metafieldDefinitionCreate:mutation — validated against api_version 2025-01
62	mutation AgenticMetafieldDefCreate($definition: MetafieldDefinitionInput!) {
63	metafieldDefinitionCreate(definition: $definition) {
64	createdDefinition { id namespace key }
65	userErrors { field message code }
66	}
67	}
68	```
69
70	```graphql
71	# products:query — validated against api_version 2025-01
72	query AgenticMetafieldProducts($first: Int!, $after: String, $query: String, $namespace: String!) {
73	products(first: $first, after: $after, query: $query) {
74	edges {
75	node {
76	id
77	title
78	tags
79	options { name values }
80	descriptionHtml
81	metafields(first: 20, namespace: $namespace) {
82	edges { node { key value } }
83	}
84	}
85	}
86	pageInfo { hasNextPage endCursor }
87	}

People who liked this also viewed

6 picks

Type

shopify-admin-agentic-metafields-setup

168stars17forks

View on GitHub

How to install shopify-admin-agentic-metafields-setup?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-metafields-setup

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-metafields-setup

Installs into the current project.

Summary

Define and populate agentic-commerce metafields (material, attributes, key features, specs, sizing) so AI agents can filter and match products to specific shopper requirements.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	AI agents answer constrained queries — "squat-proof leggings under $60", "eucalyptus slip-ons", "machine-washable wool" — by filtering on structured attributes. If those attributes live only in prose (or nowhere), the agent can't filter and your products drop out of the result set. This skill establishes a small, standard set of agentic metafield definitions (material, key features, care, fit, specs) and populates them across the catalog from existing product signals, so agents can match products to requirements. Fixes `listing-metafields`, `variant-metadata`, and `sizing-specs-structured`.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session (`shopify auth login --store <domain>`)
6	- Required API scopes: `read_products`, `write_products`, `read_metaobject_definitions`, `write_metaobject_definitions` (for definitions)
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	\| namespace \| string \| no \| agentic \| Metafield namespace to create/populate under \|
22	\| keys \| string \| no \| material,features,care,fit,specs \| Comma list of metafield keys to ensure exist \|
23	\| collection_id \| string \| no \| — \| Limit population to a collection GID \|
24	\| tag \| string \| no \| — \| Limit population to a product tag \|
25	\| populate_from \| string \| no \| tags,options,description \| Sources to infer values from (no fabrication beyond these) \|
26
27	## Safety
28
29	> ⚠️ Step 2 (`metafieldDefinitionCreate`) and Step 4 (`metafieldsSet`) write store schema + product data. Definitions are cheap to add but clutter the admin if mis-namespaced; values written from inference can be wrong. Run `dry_run: true`, review the proposed definitions and the value preview, and only populate values inferred with high confidence — leave the rest blank for human fill.
30
31	## Workflow Steps
32
33	1. OPERATION: `metafieldDefinitions` — query
34	Inputs: `ownerType: PRODUCT`, `namespace: <namespace>`
35	Expected output: Which target keys already have definitions (skip those).
36
37	2. OPERATION: `metafieldDefinitionCreate` — mutation
38	Inputs: one per missing key: `{ namespace, key, name, ownerType: PRODUCT, type: "single_line_text_field" \| "list.single_line_text_field" }`
39	Expected output: Created definitions; collect `userErrors` (e.g. already-taken).
40
41	3. OPERATION: `products` — query
42	Inputs: `first: 250`, optional filter; fields `tags`, `options`, `descriptionHtml`, existing `metafields(namespace)`; paginate.
43	Expected output: Products + the signals to infer attribute values from.
44
45	4. OPERATION: `metafieldsSet` — mutation
46	Inputs: batches of `{ ownerId, namespace, key, value, type }` for confidently-inferred, currently-empty values.
47	Expected output: Set metafields; collect `userErrors`.
48
49	## GraphQL Operations
50
51	```graphql
52	# metafieldDefinitions:query — validated against api_version 2025-01
53	query AgenticMetafieldDefs($namespace: String!) {
54	metafieldDefinitions(first: 50, ownerType: PRODUCT, namespace: $namespace) {
55	edges { node { id namespace key name type { name } } }
56	}
57	}
58	```
59
60	```graphql
61	# metafieldDefinitionCreate:mutation — validated against api_version 2025-01
62	mutation AgenticMetafieldDefCreate($definition: MetafieldDefinitionInput!) {
63	metafieldDefinitionCreate(definition: $definition) {
64	createdDefinition { id namespace key }
65	userErrors { field message code }
66	}
67	}
68	```
69
70	```graphql
71	# products:query — validated against api_version 2025-01
72	query AgenticMetafieldProducts($first: Int!, $after: String, $query: String, $namespace: String!) {
73	products(first: $first, after: $after, query: $query) {
74	edges {
75	node {
76	id
77	title
78	tags
79	options { name values }
80	descriptionHtml
81	metafields(first: 20, namespace: $namespace) {
82	edges { node { key value } }
83	}
84	}
85	}
86	pageInfo { hasNextPage endCursor }
87	}

People who liked this also viewed

6 picks

Type