Shopify Admin Discount Roi Calculator

Purpose

Evaluates the true return on investment for each discount code and automatic discount by measuring revenue generated, number of orders, average order value with vs. without discount, customer acquisition attributed to discounts, and whether discounted orders cannibalized full-price sales. Goes beyond discount-hygiene-cleanup (which finds broken/unused codes) to answer "was this discount worth it?" Read-only — no mutations.

Prerequisites

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

Parameters

Safety

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

Workflow Steps

1. OPERATION: discountNodes — query Inputs: first: 250, select discount details (title, code, type, value, usageCount, startsAt, endsAt), pagination cursor Expected output: All discount codes and automatic discounts

2. Filter to discounts with usageCount >= min_uses and active within lookback window

3. OPERATION: orders — query Inputs: query: "created_at:>='<NOW - days_back days>' discount_code:<code>", first: 250 for each active discount code, select totalPriceSet, totalDiscountsSet, subtotalPriceSet, customer { id, numberOfOrders }, pagination cursor Expected output: All orders using each discount

4. Also query orders WITHOUT any discount in same period for baseline AOV comparison

5. For each discount, calculate:

   • Total Discount Cost = Σ(totalDiscountsSet for orders with this code)
   • Revenue Generated = Σ(totalPriceSet for orders with this code)
   • Discounted AOV = revenue / orders
   • Baseline AOV = AOV of non-discounted orders in same period
   • AOV Lift/Drop = discounted AOV - baseline AOV
   • New Customer % = orders where customer.numberOfOrders == 1 / total
   • Gross ROI = (revenue - discount_cost) / discount_cost × 100
   • Cannibalization Risk = high if discount AOV < baseline AOV and new customer % < 20%

GraphQL Operations

# discountNodes:query — validated against api_version 2025-01
query AllDiscounts($after: String) {
  discountNodes(first: 250, after: $after) {
    edges {
      node {
        id
        discount {
          ... on DiscountCodeBasic {
            title
            codes(first: 1) { edges { node { code } } }
            usageLimit
            asyncUsageCount
            startsAt
            endsAt
            customerGets {
              value {
                ... on DiscountPercentage { percentage }
                ... on DiscountAmount { amount { amount currencyCode } }
              }
            }
          }
          ... on DiscountCodeFreeShipping {
            title
            codes(first: 1) { edges { node { code } } }
            asyncUsageCount
            startsAt
            endsAt
          }
          ... on DiscountAutomaticBasic {
            title
            asyncUsageCount
            startsAt
            endsAt
            customerGets {
              value {
                ... on DiscountPercentage { percentage }
                ... on DiscountAmount { amount { amount currencyCode } }
              }
            }
          }
        }
      }
    }
    pageInfo { hasNextPage endCursor }
  }
}

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

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Discount ROI Calculator              ║
║  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):

══════════════════════════════════════════════
DISCOUNT ROI REPORT  (<days_back> days)
  Discounts analyzed:   <n>
  Total discount spend:  $<amount>
  Total attributed rev:  $<amount>
  ─────────────────────────────
  TOP PERFORMERS (by ROI):
    "<code>"  ROI: <n>%  Revenue: $<n>  Cost: $<n>  New customers: <pct>%

  UNDERPERFORMERS:
    "<code>"  ROI: <n>%  Revenue: $<n>  Cost: $<n>  ⚠️ Cannibalization risk

  BASELINE COMPARISON:
    Non-discount AOV: $<n>  |  Avg discount AOV: $<n>  |  Δ: $<n>

  Output: discount_roi_<date>.csv
══════════════════════════════════════════════

Output Format

CSV file discount_roi_<YYYY-MM-DD>.csv with columns: discount_id, code_or_title, type, uses, revenue, discount_cost, roi_pct, aov, baseline_aov, aov_delta, new_customer_pct, cannibalization_risk

Error Handling

Best Practices

• Discounts with ROI < 100% cost more than they generate — consider retiring them.
• High new-customer % with positive ROI = great acquisition tool — keep running.
• Low new-customer % with negative AOV lift = cannibalization — customers would have bought anyway.
• Cross-reference with discount-ab-analysis for split-test insights.
• Use with discount-hygiene-cleanup to find and remove underperforming codes.