From shopify-admin-skills
Estimates customer acquisition cost per traffic source by joining Shopify order attribution data with configurable ad spend. Use for paid-media budget analysis.
How this skill is triggered — by the user, by Claude, or both
Slash command
/shopify-admin-skills:shopify-admin-customer-acquisition-cost-by-sourceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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 reall...
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.
shopify store auth --store <domain> --scopes read_orders,read_customersread_orders, read_customers| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| store | string | yes | — | Store domain (e.g., mystore.myshopify.com) |
| days_back | integer | no | 30 | Lookback window for orders to attribute |
| ad_spend | object | no | {} | Map of source name → spend in store currency, e.g. {"google": 4500, "meta": 3200, "tiktok": 1800} |
| new_customers_only | bool | no | true | Count only first-order customers as "acquired" |
| min_orders_per_source | integer | no | 5 | Minimum orders for a source to be reported |
| format | string | no | human | Output format: human or json |
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.
OPERATION: orders — query
Inputs: query: "created_at:>='<NOW - days_back days>'", 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
Group orders by normalized source. Resolution order:
customerJourneySummary.firstVisit.source if presentreferrerUrllandingPageUrl UTM params (utm_source)directIf new_customers_only: true, drop orders where customer.numberOfOrders > 1 so each customer is counted once
Aggregate per source: orders_count, new_customers_count, revenue_attributed
Join with ad_spend map: cac = ad_spend[source] / new_customers_count. Sources without spend data report cac: null (organic / unattributed)
Filter to sources with orders_count >= min_orders_per_source
# 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
}
}
}
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"
}
CSV file cac_by_source_<YYYY-MM-DD>.csv with columns:
source, orders_count, new_customers_count, revenue_attributed, ad_spend, cac, currency
| Error | Cause | Recovery |
|---|---|---|
THROTTLED | API rate limit exceeded | Wait 2 seconds, retry up to 3 times |
Empty ad_spend | No spend provided | Report orders / customers per source with cac: null |
Missing customerJourneySummary | Older orders or guest checkout | Fall back to referrerUrl → landingPageUrl → direct |
All orders from direct | No referrer captured | Likely tracking misconfiguration — surface as warning |
days_back — mismatched windows produce misleading CAC numbers.customer-cohort-analysis to validate that low-CAC sources also produce high-LTV customers.direct often hide attribution leakage — investigate UTM tagging and referrer policies before drawing conclusions.npx claudepluginhub 40rty-ai/shopify-admin-skills --plugin shopify-admin-skillsRead-only: parses each order's landing site and referrer URL to break down orders, revenue, and AOV by traffic source — direct, organic, paid, social, email, or referral domain.
Runs multi-touch attribution analysis comparing first-touch, last-touch, linear, time-decay, position-based, and data-driven models for marketing revenue allocation.
Interprets paid media dashboards, including attribution models, platform reporting quirks, ROAS vs LTV, multi-platform reconciliation, and incrementality testing. Useful when scaling, killing, or rebudgeting campaigns based on platform metrics.