Customer Acquisition Cost By Source

Purpose

Estimates customer acquisition cost (CAC) for each traffic source by combining the number of new-customer orders attributed to a landing page / referrer with a configurable ad spend input per source. Output answers: "for every dollar spent on source X, how many new customers did we acquire and at what unit cost?" Read-only — no mutations. Provides the data foundation for paid-media budget reallocation.

Prerequisites

Parameters

Safety

> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time. Ad spend values are caller-provided; this skill does not pull from any ad platform.

Workflow Steps

Inputs: query: "created_at:>=''", first: 250, select customer { id, numberOfOrders }, customerJourneySummary { firstVisit { landingPage referrerUrl source } }, landingPageUrl, referrerUrl, totalPriceSet, pagination cursor

Expected output: All orders in the window with referral and customer attribution; paginate until hasNextPage: false

GraphQL Operations

# orders:query — validated against api_version 2025-01
query OrdersWithAttribution($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        name
        createdAt
        landingPageUrl
        referrerUrl
        customerJourneySummary {
          firstVisit {
            landingPage
            referrerUrl
            source
            sourceType
            utmParameters {
              source
              medium
              campaign
            }
          }
        }
        totalPriceSet {
          shopMoney {
            amount
            currencyCode
          }
        }
        customer {
          id
          numberOfOrders
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Customer Acquisition Cost by Source  ║
║  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):

══════════════════════════════════════════════
CAC BY SOURCE  (<days_back> days)
  Orders analyzed:        <n>
  New customers acquired: <n>
  Total ad spend (input): $<amount>
  Blended CAC:            $<amount>

  By Source (sorted by CAC ascending):
    google      Customers: <n>  Spend: $<n>   CAC: $<n>
    meta        Customers: <n>  Spend: $<n>   CAC: $<n>
    direct      Customers: <n>  Spend: —      CAC: organic
    referral    Customers: <n>  Spend: —      CAC: organic

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

For format: json, emit:

{
  "skill": "customer-acquisition-cost-by-source",
  "store": "<domain>",
  "period_days": 30,
  "orders_analyzed": 0,
  "new_customers": 0,
  "blended_cac": 0,
  "currency": "USD",
  "by_source": [],
  "output_file": "cac_by_source_<date>.csv"
}

Output Format

CSV file cac_by_source_.csv with columns:

source, orders_count, new_customers_count, revenue_attributed, ad_spend, cac, currency

Error Handling

Best Practices