Shopify Admin Product Data Completeness Score

Purpose

Calculates a data completeness score (0–100) for each active product based on the presence of key fields: description, images, SEO title, SEO description, variant weight, barcode, cost, and specified metafields. Produces a ranked list of products needing the most data work. Read-only — no mutations. Catalog health report in a single pass.

Prerequisites

• Authenticated Shopify CLI session: shopify store auth --store --scopes read_products
• API scopes: read_products

Parameters

| Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | store | string | yes | — | Store domain (e.g., mystore.myshopify.com) | | statusfilter | string | no | active | Product status to score: active, draft, or all | | requiredmetafields | array | no | [] | List of namespace.key metafields that are required (e.g., ["custom.material"]) | | format | string | no | human | Output format: human or json |

Safety

> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time.

Scoring Rubric

| Field | Points | |-------|--------| | Description present (non-empty) | 15 | | At least 1 image | 15 | | SEO title present | 10 | | SEO description present | 10 | | At least 1 variant with barcode | 10 | | At least 1 variant with cost | 10 | | At least 1 variant with weight | 10 | | All required metafields present | 20 (split evenly) | | Total | 100 |

Workflow Steps

1. OPERATION: products — query

Inputs: query: "status:", first: 250, select all completeness fields, pagination cursor Expected output: Products with all scored fields; paginate until hasNextPage: false

1. Score each product per rubric; rank ascending by score

GraphQL Operations

# products:query — validated against api_version 2025-01
query ProductCompleteness($query: String!, $after: String) {
  products(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        title
        handle
        descriptionHtml
        images(first: 1) {
          edges {
            node {
              id
            }
          }
        }
        seo {
          title
          description
        }
        variants(first: 10) {
          edges {
            node {
              id
              barcode
              weight
              inventoryItem {
                unitCost {
                  amount
                }
              }
            }
          }
        }
        metafields(first: 20) {
          edges {
            node {
              namespace
              key
              value
            }
          }
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Session Tracking

Claude MUST emit the following output at each stage. This is mandatory.

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Product Data Completeness Score      ║
║  Store:                        ║
║  Started:              ║
╚══════════════════════════════════════════════╝

After each step, emit:

[N/TOTAL]   
          → Params: 
          → Result: 

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
PRODUCT DATA COMPLETENESS REPORT
  Products scored:  
  Avg score:        /100
  Score  products (need urgent attention)
  Score 50–79:       products
  Score ≥ 80:        products

  Lowest scoring products:
    ""  Score: /100  Missing: description, SEO title
  Output: completeness_.csv
══════════════════════════════════════════════

For format: json, emit:

{
  "skill": "product-data-completeness-score",
  "store": "",
  "products_scored": 0,
  "avg_score": 0,
  "below_50_count": 0,
  "output_file": "completeness_.csv"
}

Output Format

CSV file completeness_.csv with columns: product_id, title, score, has_description, image_count, has_seo_title, has_seo_description, has_barcode, has_cost, has_weight, missing_metafields

Error Handling

| Error | Cause | Recovery | |-------|-------|----------| | THROTTLED | API rate limit exceeded | Wait 2 seconds, retry up to 3 times | | No products match filter | Empty catalog or wrong filter | Exit with 0 results |

Best Practices

• Use this skill as a pre-launch gate — run before activating DRAFT products to ensure all required fields are filled.
• Tune required_metafields to your store's specific needs (e.g., custom.material for apparel, custom.ingredients for food).
• A score below 50 typically means a product is missing foundational content (description or images) and should be deprioritized from launch until fixed.
• Run monthly to track catalog quality trends over time; improvements after a content sprint should be visible in the average score.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: 40RTY-ai
• Source: 40RTY-ai/shopify-admin-skills
• License: MIT
• Homepage: http://skills.40rty.ai

Install and usage instructions live in the source repository linked above.