AI Blocks › Make an offer people want
Bought-together pair finder
Get the products customers most often buy together, ranked, to build bundles and cross-sell offers.
Bought-together pair finder is a free AI skill for the job "Make an offer people want". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by 40rty AI · Level: advanced
Made by 40rty AI. See the original on GitHub; we copied it as it is, with its licence.
What it does
Find which products your customers really buy together, ranked by strength, so you can build bundles and cross-sell offers on evidence. It reads your Shopify order history for a date range you choose. For every pair that appears in orders, it works out three numbers. Support is how often the pair shows up. Confidence is how likely a buyer of A also takes B. Lift is how much more likely that is than chance. You set minimum values so weak pairs are dropped. It needs a logged-in Shopify CLI session with order and product read access, and has a preview option.
You give it
- Your store domain
- A start and end date
- Minimum support, confidence and lift (optional)
- A logged-in Shopify CLI session
You get
- Ranked product pairs
- Support, confidence and lift for each
- A readable or JSON report
- Bundle and cross-sell ideas
Use it when
- You want to build bundles from real buying patterns.
- You need a frequently-bought-together section on product pages.
- You are planning cross-sell emails after a purchase.
- You want to see which pairs are just popular items, not true links.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can access your Shopify admin (read only).