Repeat Purchase Rate

Purpose

Calculates the repeat purchase rate — the percentage of customers who return to place at least one more order within a defined window — and segments it by first-purchase product or collection. Identifies which products drive the highest repeat purchase behavior. Read-only — no mutations.

Prerequisites

Parameters

Safety

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

Workflow Steps

Inputs: query: "created_at:>=''", first: 250, select id, numberOfOrders, createdAt

Expected output: Customers acquired in window

Inputs: query: "created_at:>=''", first: 250, select customer { id }, createdAt, lineItems { product { id, title } }, pagination cursor

Expected output: Orders to build per-customer purchase history and first-product mapping

GraphQL Operations

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

# orders:query — validated against api_version 2025-01
query CustomerOrderHistory($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        createdAt
        customer {
          id
        }
        lineItems(first: 5) {
          edges {
            node {
              product {
                id
                title
              }
            }
          }
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Repeat Purchase Rate                 ║
║  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):

══════════════════════════════════════════════
REPEAT PURCHASE RATE
  Acquisition window:  <days_back> days
  Repeat window:       <repeat_window> days
  Customers acquired:  <n>
  Repeat purchasers:   <n>
  Repeat rate:         <pct>%

  By First Product:
    "<product>"  Acquired: <n>  Repeat: <pct>%
  Output: repeat_purchase_<date>.csv
══════════════════════════════════════════════

For format: json, emit:

{
  "skill": "repeat-purchase-rate",
  "store": "<domain>",
  "acquisition_days": 90,
  "repeat_window_days": 90,
  "customers_acquired": 0,
  "repeat_purchasers": 0,
  "repeat_rate_pct": 0,
  "by_product": [],
  "output_file": "repeat_purchase_<date>.csv"
}

Output Format

CSV file repeat_purchase_.csv with columns:

customer_id, first_order_date, first_product, total_orders, is_repeat, days_to_repeat, total_spent

Error Handling

Best Practices