shopify-admin-agentic-product-jsonld-backfill

Name: shopify-admin-agentic-product-jsonld-backfill
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-agentic-product-jsonld-backfill?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-product-jsonld-backfill

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

Installs into the current project.

Summary

Backfill the structured product/variant fields that power Product JSON-LD — barcode (GTIN), SKU, vendor, product type, weight — so AI agents can quote exact, in-stock items instead of guessing.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	AI shopping agents read a product's structured data (the fields Shopify themes emit as `schema.org/Product` JSON-LD) to confirm price, availability, and identity. Missing barcodes (GTIN), SKUs, vendor, or product type leave the listing ambiguous — so the agent skips it or recommends a competitor whose data is complete. This skill finds products/variants with those gaps and backfills them: vendor and product type at the product level, barcode/SKU at the variant level. Fixes the agentiq.report findings `product-schema-jsonld`, `gtin-sku-pdp`, and `variant-metadata`.
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 (else whole catalog) \|
22	\| tag \| string \| no \| — \| Limit to a product tag \|
23	\| set_vendor \| string \| no \| — \| Vendor to apply where missing (else only reports) \|
24	\| set_product_type \| string \| no \| — \| Product type to apply where missing \|
25	\| barcodes_csv \| string \| no \| — \| Path to a CSV of `sku,barcode` to map GTINs onto matching variants \|
26	\| fields \| string \| no \| all \| Comma list of fields to backfill: `vendor,product_type,barcode,sku` \|
27
28	## Safety
29
30	> ⚠️ Step 3 (`productUpdate`) and Step 4 (`productVariantsBulkUpdate`) write live product/variant data. Barcodes and SKUs are matched from your `barcodes_csv`; a wrong mapping mislabels a product's identity to every agent. Always run `dry_run: true` first and verify the change set CSV. This skill never overwrites a field that already has a value — it only fills blanks.
31
32	## Workflow Steps
33
34	1. OPERATION: `products` — query
35	Inputs: `first: 250`, optional `query: "tag:'<tag>'"` or collection filter; fields `vendor`, `productType`, `variants{ id sku barcode }`; paginate until `hasNextPage: false`.
36	Expected output: Products/variants with missing target fields.
37
38	2. COMPUTE (no API): build the change set — only blank fields, joined to `barcodes_csv` by SKU for barcodes. Emit the preview CSV.
39
40	3. OPERATION: `productUpdate` — mutation
41	Inputs: per product `{ id, vendor?, productType? }` (only where blank and a value is supplied).
42	Expected output: Updated product; collect `userErrors`.
43
44	4. OPERATION: `productVariantsBulkUpdate` — mutation
45	Inputs: per product `productId` + `variants: [{ id, barcode?, inventoryItem: { sku? } }]` for blank variant fields.
46	Expected output: Updated variants; collect `userErrors` across batches.
47
48	## GraphQL Operations
49
50	```graphql
51	# products:query — validated against api_version 2025-01
52	query BackfillProducts($first: Int!, $after: String, $query: String) {
53	products(first: $first, after: $after, query: $query) {
54	edges {
55	node {
56	id
57	title
58	vendor
59	productType
60	variants(first: 100) {
61	edges { node { id sku barcode } }
62	}
63	}
64	}
65	pageInfo { hasNextPage endCursor }
66	}
67	}
68	```
69
70	```graphql
71	# productUpdate:mutation — validated against api_version 2025-01
72	mutation BackfillProductFields($input: ProductInput!) {
73	productUpdate(input: $input) {
74	product { id vendor productType }
75	userErrors { field message }
76	}
77	}
78	```
79
80	```graphql
81	# productVariantsBulkUpdate:mutation — validated against api_version 2025-01
82	mutation BackfillVariantFields($productId: ID!, $variants: [ProductVariantsBulkInput!]!) {
83	productVariantsBulkUpdate(productId: $productId, variants: $variants) {
84	productVariants { id sku barcode }
85	userErrors { field message }
86	}
87	}
88	```
89
90	## Session Tracking
91
92	Claude MUST emit the following output at each stage. This is mandatory.
93
94	On start, emit:
95	```
96	╔══════════════════════════════════════════════╗
97	║ SKILL: <skill name> ║
98	║ Store: <store d

People who liked this also viewed

6 picks

Type

shopify-admin-agentic-product-jsonld-backfill

168stars17forks

View on GitHub

How to install shopify-admin-agentic-product-jsonld-backfill?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-product-jsonld-backfill

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

Installs into the current project.

Summary

Backfill the structured product/variant fields that power Product JSON-LD — barcode (GTIN), SKU, vendor, product type, weight — so AI agents can quote exact, in-stock items instead of guessing.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	AI shopping agents read a product's structured data (the fields Shopify themes emit as `schema.org/Product` JSON-LD) to confirm price, availability, and identity. Missing barcodes (GTIN), SKUs, vendor, or product type leave the listing ambiguous — so the agent skips it or recommends a competitor whose data is complete. This skill finds products/variants with those gaps and backfills them: vendor and product type at the product level, barcode/SKU at the variant level. Fixes the agentiq.report findings `product-schema-jsonld`, `gtin-sku-pdp`, and `variant-metadata`.
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 (else whole catalog) \|
22	\| tag \| string \| no \| — \| Limit to a product tag \|
23	\| set_vendor \| string \| no \| — \| Vendor to apply where missing (else only reports) \|
24	\| set_product_type \| string \| no \| — \| Product type to apply where missing \|
25	\| barcodes_csv \| string \| no \| — \| Path to a CSV of `sku,barcode` to map GTINs onto matching variants \|
26	\| fields \| string \| no \| all \| Comma list of fields to backfill: `vendor,product_type,barcode,sku` \|
27
28	## Safety
29
30	> ⚠️ Step 3 (`productUpdate`) and Step 4 (`productVariantsBulkUpdate`) write live product/variant data. Barcodes and SKUs are matched from your `barcodes_csv`; a wrong mapping mislabels a product's identity to every agent. Always run `dry_run: true` first and verify the change set CSV. This skill never overwrites a field that already has a value — it only fills blanks.
31
32	## Workflow Steps
33
34	1. OPERATION: `products` — query
35	Inputs: `first: 250`, optional `query: "tag:'<tag>'"` or collection filter; fields `vendor`, `productType`, `variants{ id sku barcode }`; paginate until `hasNextPage: false`.
36	Expected output: Products/variants with missing target fields.
37
38	2. COMPUTE (no API): build the change set — only blank fields, joined to `barcodes_csv` by SKU for barcodes. Emit the preview CSV.
39
40	3. OPERATION: `productUpdate` — mutation
41	Inputs: per product `{ id, vendor?, productType? }` (only where blank and a value is supplied).
42	Expected output: Updated product; collect `userErrors`.
43
44	4. OPERATION: `productVariantsBulkUpdate` — mutation
45	Inputs: per product `productId` + `variants: [{ id, barcode?, inventoryItem: { sku? } }]` for blank variant fields.
46	Expected output: Updated variants; collect `userErrors` across batches.
47
48	## GraphQL Operations
49
50	```graphql
51	# products:query — validated against api_version 2025-01
52	query BackfillProducts($first: Int!, $after: String, $query: String) {
53	products(first: $first, after: $after, query: $query) {
54	edges {
55	node {
56	id
57	title
58	vendor
59	productType
60	variants(first: 100) {
61	edges { node { id sku barcode } }
62	}
63	}
64	}
65	pageInfo { hasNextPage endCursor }
66	}
67	}
68	```
69
70	```graphql
71	# productUpdate:mutation — validated against api_version 2025-01
72	mutation BackfillProductFields($input: ProductInput!) {
73	productUpdate(input: $input) {
74	product { id vendor productType }
75	userErrors { field message }
76	}
77	}
78	```
79
80	```graphql
81	# productVariantsBulkUpdate:mutation — validated against api_version 2025-01
82	mutation BackfillVariantFields($productId: ID!, $variants: [ProductVariantsBulkInput!]!) {
83	productVariantsBulkUpdate(productId: $productId, variants: $variants) {
84	productVariants { id sku barcode }
85	userErrors { field message }
86	}
87	}
88	```
89
90	## Session Tracking
91
92	Claude MUST emit the following output at each stage. This is mandatory.
93
94	On start, emit:
95	```
96	╔══════════════════════════════════════════════╗
97	║ SKILL: <skill name> ║
98	║ Store: <store d

People who liked this also viewed

6 picks

Type