shopify-admin-return-fraud-detector
Installation
SKILL.md
Purpose
Surfaces customers whose return behavior deviates statistically from the store baseline so support and ops can review them before approving the next return. Three patterns are detected: (1) high return rate (≥40% of orders returned), (2) wardrobing — full-order returns shortly after delivery, (3) serial returners — many returns over time. Read-only. Output is a candidate list, not an automatic block list.
Prerequisites
- Authenticated Shopify CLI session:
shopify store auth --store <domain> --scopes read_orders,read_returns,read_customers - API scopes:
read_orders,read_returns,read_customers
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| store | string | yes | — | Store domain (e.g., mystore.myshopify.com) |
| format | string | no | human | Output format: human or json |
| days_back | integer | no | 365 | Lookback window for orders and returns |
| min_orders | integer | no | 3 | Minimum lifetime orders for a customer to be evaluated (avoid penalizing one-off accidents) |
| return_rate_threshold | float | no | 0.40 | Fraction of orders returned to flag as high (default 40%) |
| wardrobing_window_days | integer | no | 14 | Window between delivery and return-initiated to flag as wardrobing |
| serial_threshold | integer | no | 5 | Minimum total returns to flag as serial returner |