Product launch and retire manager

• Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
• Ask for the job in your own words. Your AI opens the skill when it fits.
• It works best when your AI can access your Shopify admin and change live store data.

Purpose

Queries products matching a tag, vendor, collection, or status filter and bulk-transitions them to a target status (DRAFT, ACTIVE, or ARCHIVED). Used for seasonal launches (DRAFT → ACTIVE), end-of-season sunsetting (ACTIVE → ARCHIVED), and pre-launch staging (creating as DRAFT, activating on a date).

Prerequisites

• Authenticated Shopify CLI session: shopify store auth --store <domain> --scopes read_products,write_products
• API scopes: read_products, write_products

Parameters

Safety

⚠️ ARCHIVED products are hidden from all sales channels and cannot be purchased. ACTIVE products are immediately visible to customers. Run with dry_run: true to review the product list before committing — especially for ARCHIVED transitions which are hard to reverse in bulk.

Workflow Steps

1. OPERATION: products — query Inputs: query: <filter>, first: 250, pagination cursor Expected output: Products with id, title, status, tags; paginate until hasNextPage: false

2. Filter to products NOT already in target_status — skip those already correct

3. OPERATION: productUpdate — mutation Inputs: id: <product_id>, status: <target_status> Expected output: product { id, title, status }, userErrors

GraphQL Operations

# products:query — validated against api_version 2025-01
query ProductsByFilter($query: String!, $after: String) {
  products(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        title
        status
        vendor
        tags
        publishedAt
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

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

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Product Lifecycle Manager            ║
║  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
  Products matched:    <n>
  Already at target:   <n> (skipped)
  Status updated:      <n>
  Errors:              <n>
  Output:              lifecycle_update_<date>.csv
══════════════════════════════════════════════

For format: json, emit:

{
  "skill": "product-lifecycle-manager",
  "store": "<domain>",
  "started_at": "<ISO8601>",
  "completed_at": "<ISO8601>",
  "dry_run": true,
  "filter": "<query>",
  "target_status": "ACTIVE",
  "outcome": {
    "matched": 0,
    "skipped_already_correct": 0,
    "updated": 0,
    "errors": 0,
    "output_file": "lifecycle_update_<date>.csv"
  }
}

Output Format

CSV file lifecycle_update_<YYYY-MM-DD>.csv with columns: product_id, title, previous_status, new_status, vendor, tags

Error Handling

Best Practices

• Use tags to mark seasonal batches before running (e.g., tag products with launch:2026-05 before activating them) so the filter is precise.
• ARCHIVED status removes products from all channels including the storefront, POS, and buy buttons — confirm this is the intent before running at scale.
• For large catalogs (500+ products), rate limiting will slow execution — the skill retries automatically but large batches may take several minutes.
• Pair with product-data-completeness-score before activating DRAFT products to ensure they have all required fields.