Agentic Product Taxonomy

Purpose

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.

Prerequisites

Parameters

All skills accept these universal parameters:

Skill-specific parameters:

Safety

> ⚠️ 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.

Workflow Steps

Inputs: first: 250, optional filter; fields title, productType, tags, category{ id fullName }; paginate.

Expected output: Products with their current category (or null).

Inputs: search the standard taxonomy tree by candidate terms derived from each product's type/title.

Expected output: Candidate taxonomy category nodes (id + fullName) to match against.

Inputs: { id, category: } per confident match.

Expected output: Updated product category; collect userErrors.

GraphQL Operations

# products:query — validated against api_version 2025-01
query TaxonomyProducts($first: Int!, $after: String, $query: String) {
  products(first: $first, after: $after, query: $query) {
    edges {
      node {
        id
        title
        productType
        tags
        category { id fullName }
      }
    }
    pageInfo { hasNextPage endCursor }
  }
}

# taxonomy:query — validated against api_version 2025-01
query TaxonomySearch($search: String) {
  taxonomy {
    categories(first: 20, search: $search) {
      edges { node { id fullName isLeaf level } }
    }
  }
}

# productUpdate:mutation — validated against api_version 2025-01
mutation TaxonomyAssign($input: ProductInput!) {
  productUpdate(input: $input) {
    product { id category { id fullName } }
    userErrors { field message }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: <skill name>                         ║
║  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>

If dry_run: true, prefix every mutation step with [DRY RUN] and do not execute it.

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
OUTCOME SUMMARY
  <Metric label>:   <value>
  Errors:           0
  Output:           <filename or "none">
══════════════════════════════════════════════

For format: json, emit:

{
  "skill": "<skill-slug>",
  "store": "<domain>",
  "started_at": "<ISO8601>",
  "completed_at": "<ISO8601>",
  "dry_run": false,
  "steps": [
    {
      "step": 1,
      "operation": "<OperationName>",
      "type": "query",
      "params_summary": "<string>",
      "result_summary": "<string>",
      "skipped": false
    }
  ],
  "outcome": {
    "metric_key": 0,
    "errors": 0,
    "output_file": null
  }
}

Output Format

human: count categorized + a CSV (product, old_category, new_category, confidence) and a "needs review" list below the floor. json: { categorized, needs_review, errors, output_file }.

Error Handling

Best Practices