Skip to main content
Back to the field guide

A field guide to the /lumen-abtest skill

AI A/B Test Design with MDE and Sample Size

Most A/B tests ship before they are designed. /lumen-abtest defines hypothesis, MDE, sample size, primary + guardrail metrics, run time, and decision criteria.

Lumen · Product Analytics5 min readDecember 17, 2025

A/B tests run without proper design produce inconclusive results that everyone interprets to fit their bias. Without a defined MDE, the test never reaches significance. Without guardrails, the team ships a winning variant that hurt a metric nobody was watching.

The /lumen-abtest skill designs the test before launch: hypothesis in testable form, sample size required for statistical power, primary metric and guardrail metrics, minimum detectable effect, required run time, and explicit success/failure criteria.

Tonone's /lumen-abtest skill designs A/B tests with hypothesis, MDE, sample size, primary + guardrail metrics, run time, and decision criteria.

Install

/lumen-abtest ships with the Lumen agent in Tonone for Claude Code.

1. Add to marketplace

$ claude plugin marketplace add tonone-ai/tonone

2. Install Lumen

$ claude plugin install lumen@tonone-ai

Frequently asked questions

What does /lumen-abtest do?
It designs A/B tests with hypothesis, MDE, sample size, metrics, run time, and decision criteria.
How do I install /lumen-abtest?
Install Tonone for Claude Code via tonone.ai/get-started.

Pairs well with