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

A/B test results reader

Paste counts for two versions. Get the percentage gap, a luck check, a keep, rerun or stop call and a lesson.

A/B test results reader is a free AI skill for the job "Read your ad results". Add it to Claude, ChatGPT, Gemini or Codex as a skill, or paste it into any chat.

Free · No account · Made by AI Blocks

What it does

A test ends with a few numbers, and it is easy to see what you hoped to see. Ten more replies on one side feels like a win. It may only be noise. A version can win on replies and lose on sales if the item people replied to was free. This skill states the gap the way an ad buyer would: version A pulled 30 percent more than B. It then checks that gap against the size of the counts, looks at whether the test stayed fair, follows replies through to sales, and works out cost per reply and per sale. It ends with one call: keep, rerun or stop. It writes what the test taught into a record you can reuse, and it names the next test in the order that usually pays most.

You give it

Audience, replies, sales and spend for each version
The test plan, if you have it (optional)
Notes on anything odd that happened (optional)
Plan (optional)

You get

A table of both versions and the gap as a percentage
A luck check with the sum shown
Sales per hundred replies and cost per reply and per sale
A keep, rerun or stop call with its reason
A record of what the test taught, and the next test to run

Use it when

A test of two ads, emails or pages has finished and you have the counts.
You are not sure whether the gap you see is real.
You keep running tests and forgetting what each one taught.

How to use it

Start a chat with the skill. Open it if you added it to your AI, or copy it and paste it in.
Paste the counts for each version, or attach your export.
Paste the test plan if you have it, and note anything odd.
Save the lesson record to your file of past tests.
Run the next test it names.