Shopify Admin Frequently Bought Together

Purpose

Analyzes order history to discover which products are frequently purchased together. Calculates co-occurrence frequency, lift scores, and confidence metrics to generate data-driven cross-sell recommendations and bundle candidates. Read-only — no mutations.

Prerequisites

• Authenticated Shopify CLI session: shopify store auth --store --scopes read_orders,read_products
• API scopes: read_orders, read_products

Parameters

| Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | store | string | yes | — | Store domain | | daysback | integer | no | 180 | Order lookback window | | minsupport | integer | no | 3 | Minimum co-occurrence count to report a pair | | maxresults | integer | no | 25 | Maximum product pairs to return | | groupsize | integer | no | 2 | Pair size: 2 for pairs, 3 for triplets | | collection_filter | string | no | — | Limit to products in a specific collection | | format | string | no | human | Output format: human or json |

Safety

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

Workflow Steps

1. OPERATION: orders — query

Inputs: query: "created_at:>=''", first: 250, select lineItems { product { id, title } }, pagination cursor Expected output: All orders with product-level line items

1. For each order with 2+ distinct products, generate all product pair combinations

1. Build co-occurrence matrix:

• Support = number of orders containing both products
• Confidence(A→B) = P(B|A) = support(A,B) / support(A)
• Lift = confidence(A→B) / P(B) — lift > 1.0 means positive association

1. OPERATION: products — query (enrichment)

Inputs: Product IDs from top pairs for titles, images, prices Expected output: Product details for display

1. Rank pairs by lift score (descending), filter by min_support

GraphQL Operations

# orders:query — validated against api_version 2025-01
query OrderLineItems($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        lineItems(first: 50) {
          edges {
            node {
              product { id title }
              quantity
            }
          }
        }
      }
    }
    pageInfo { hasNextPage endCursor }
  }
}

# products:query — validated against api_version 2025-01
query ProductDetails($ids: [ID!]!) {
  nodes(ids: $ids) {
    ... on Product {
      id
      title
      vendor
      productType
      priceRangeV2 {
        minVariantPrice { amount currencyCode }
        maxVariantPrice { amount currencyCode }
      }
      totalInventory
      status
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Frequently Bought Together           ║
║  Store:                        ║
║  Started:              ║
╚══════════════════════════════════════════════╝

After each step, emit:

[N/TOTAL]   
          → Params: 
          → Result: 

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
FREQUENTLY BOUGHT TOGETHER  ( days,  orders analyzed)
  Unique product pairs found: 
  Pairs meeting min_support:  

  TOP PAIRS BY LIFT:
  #1  "" + ""
      Support:  orders  Lift: x  Confidence: %

  #2  "" + ""
      Support:  orders  Lift: x  Confidence: %

  BUNDLE CANDIDATES (high support + high lift):
    "" + ""  →  Suggested bundle price: $

  Output: fbt_pairs_.csv
══════════════════════════════════════════════

Output Format

CSV file fbt_pairs_.csv with columns: product_a_id, product_a_title, product_b_id, product_b_title, support, confidence_a_to_b, confidence_b_to_a, lift, combined_avg_price

Error Handling

| Error | Cause | Recovery | |-------|-------|----------| | THROTTLED | API rate limit exceeded | Wait 2 seconds, retry up to 3 times | | Single-item orders only | Store with no multi-item orders | Report empty — suggest longer lookback window | | Too many products | Combinatorial explosion | Limit to top 500 products by order count |

Best Practices

• Use days_back: 180 or 365 for sufficient sample size.
• Pairs with lift > 2.0 are strong bundle candidates.
• Use results to create manual product bundles or configure upsell apps.
• Cross-reference with top-product-performance to ensure paired items are high-performing.
• Products with high confidence A→B but low confidence B→A suggest directional upsells (show B when A is in cart).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: 40RTY-ai
• Source: 40RTY-ai/shopify-admin-skills
• License: MIT
• Homepage: http://skills.40rty.ai

Install and usage instructions live in the source repository linked above.