AI Blocks

Putting the blocks together

This is taking longer than expected.

Try againBrowse the library
AI Blocks · All skills by job · Minds · Mini tools · How it works · From a source · Apps

AI Blocks › Test changes to your store

Know if your test won, then pick the next one

Give it your test numbers and dates. Get a ship call, ranked ideas and the next bold tests.

Read a finished store test and pick the next one is a free AI workflow for the job "Test changes to your store". It guides your AI through several skills in order, passing each step's output to the next.

Free · No account · Made by AI Blocks · Thinking: high

What it does

A test ends and you get a dashboard that says "95% chance to win". That banner can mislead. Stopping early, an uneven split or a sale in the middle can make a loss look like a win. After the call, most stores pick the next test by gut, or run another small tweak their traffic can never prove. The first step checks the split, how the test ended, tracking faults and other changes, then gives the lift as a range and in money, and checks order value and margin. The second takes what the test taught and writes each next idea as a hypothesis, scored on the evidence behind it. The third fits those ideas to your traffic: bold tests you can prove, one per page, laid out by month, with what not to test at your size.

You give it

You get

Use it when

Steps

  1. Store test verdict maker: Give it test numbers and dates. Get valid or not, the lift as a range, a ship call and a trust score.
  2. Test idea ranker: Paste your research findings. Get each test written as a hypothesis and ranked by evidence and profit.
  3. High-impact experiment planner: Give it your store size and page data. Get five bold tests your traffic can prove, in order.

How to use it

  1. Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
  2. Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
  3. Export the test numbers for both versions with dates. Say if anything else changed during the test, like a sale or an email.
  4. Add the research you already have, such as heatmap notes or survey answers, for step 2.
  5. Give your monthly orders and visits so step 3 can size tests to your traffic.

More for Test changes to your store

Every test changes to your store skill