Refund Rate Analysis

Purpose

Analyzes orders with refunds to calculate refund rates by product, time period, and channel. Surfaces which products or product groups generate the most refund activity. 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 refunds { refundLineItems }, lineItems, pagination cursor

Expected output: All orders with refund data; paginate until hasNextPage: false

GraphQL Operations

# orders:query — validated against api_version 2025-01
query OrdersWithRefunds($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        name
        createdAt
        lineItems(first: 50) {
          edges {
            node {
              id
              quantity
              product {
                id
                title
                vendor
              }
              variant {
                id
                sku
              }
            }
          }
        }
        refunds {
          id
          createdAt
          totalRefundedSet {
            shopMoney {
              amount
              currencyCode
            }
          }
          refundLineItems(first: 50) {
            edges {
              node {
                quantity
                lineItem {
                  product {
                    id
                    title
                    vendor
                  }
                  variant {
                    id
                    sku
                  }
                }
              }
            }
          }
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Refund Rate Analysis                 ║
║  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):

══════════════════════════════════════════════
REFUND RATE ANALYSIS  (<days_back> days)
  Orders analyzed:       <n>
  Orders with refunds:   <n>
  Overall refund rate:   <pct>%
  Total refunded:        $<amount>

  By <group_by>:
    "<name>"   Sold: <n>  Refunded: <n>  Rate: <pct>%
  Output: refund_rate_<date>.csv
══════════════════════════════════════════════

For format: json, emit:

{
  "skill": "refund-rate-analysis",
  "store": "<domain>",
  "period_days": 30,
  "orders_analyzed": 0,
  "orders_with_refunds": 0,
  "overall_refund_rate_pct": 0,
  "total_refunded": 0,
  "currency": "USD",
  "output_file": "refund_rate_<date>.csv"
}

Output Format

CSV file refund_rate_.csv with columns:

group, group_name, total_units_sold, refunded_units, refund_rate_pct, total_refund_amount, currency

Error Handling

Best Practices