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

Parameters

Safety

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

Scoring Rubric

Workflow Steps

Inputs: query: "status:", first: 250, select all completeness fields, pagination cursor

Expected output: Products with all scored fields; paginate until hasNextPage: false

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: <store domain>                       ║
║  Started: <YYYY-MM-DD HH:MM UTC>             ║
╚══════════════════════════════════════════════╝

After each step, emit:

[N/TOTAL] <QUERY|MUTATION>  <OperationName>
          → Params: <brief summary of key inputs>
          → Result: <count or outcome>

On completion, emit:

For format: human (default):

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

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

For format: json, emit:

{
  "skill": "product-data-completeness-score",
  "store": "<domain>",
  "products_scored": 0,
  "avg_score": 0,
  "below_50_count": 0,
  "output_file": "completeness_<date>.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

Best Practices