Shopify Admin Average Order Value Trends

Purpose

Calculates Average Order Value (AOV) over configurable time buckets (daily, weekly, monthly) and segments results by new vs. returning customers. Tracks AOV trends to measure the impact of upsell programs, bundle offers, or free shipping thresholds. Read-only — no mutations.

Prerequisites

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

Parameters

Safety

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

Workflow Steps

1. OPERATION: orders — query Inputs: query: "created_at:>='<NOW - days_back days>'", first: 250, select totalPriceSet, customer { id, numberOfOrders }, createdAt, pagination cursor Expected output: All orders in window; paginate until hasNextPage: false

2. Classify each order: if customer.numberOfOrders == 1 → new customer order; else → returning

3. OPERATION: customers — query (optional enrichment for cohort context) Inputs: Recent customers for new vs. repeat segmentation validation

4. Group orders by time bucket; calculate AOV per bucket and per customer segment

GraphQL Operations

# orders:query — validated against api_version 2025-01
query AOVData($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        name
        createdAt
        totalPriceSet {
          shopMoney {
            amount
            currencyCode
          }
        }
        customer {
          id
          numberOfOrders
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

# customers:query — validated against api_version 2025-01
query NewVsReturningCustomers($query: String!, $after: String) {
  customers(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        numberOfOrders
        createdAt
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Average Order Value Trends           ║
║  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):

══════════════════════════════════════════════
AOV TRENDS  (<days_back> days, bucket: <bucket>)
  Orders analyzed:   <n>
  Overall AOV:       $<amount>
  New customer AOV:  $<amount>
  Returning AOV:     $<amount>

  Period      Orders   AOV     New AOV  Returning AOV
  ────────────────────────────────────────────────────
  2026-W14    <n>      $<n>    $<n>     $<n>
  Output: aov_trends_<date>.csv
══════════════════════════════════════════════

For format: json, emit:

{
  "skill": "average-order-value-trends",
  "store": "<domain>",
  "period_days": 90,
  "overall_aov": 0,
  "new_customer_aov": 0,
  "returning_customer_aov": 0,
  "by_period": [],
  "output_file": "aov_trends_<date>.csv"
}

Output Format

CSV file aov_trends_<YYYY-MM-DD>.csv with columns: period, order_count, aov, new_customer_orders, new_customer_aov, returning_orders, returning_aov, currency

Error Handling

Best Practices

• A free shipping threshold increase or bundle introduction should show up as an AOV lift in the week/month it launched — use this report to measure the impact.
• Returning customer AOV is typically higher than new — a shrinking gap may indicate loyalty erosion.
• bucket: week is best for campaign measurement; bucket: month for long-term trend tracking.
• Guest checkout orders cannot be segmented as new vs. returning — for stores with high guest checkout rates, the segmentation will under-count new customers.