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.
Related skills
Install
/lumen-abtest ships with the Lumen agent in Tonone for Claude Code.
1. Add to marketplace
2. Install Lumen
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
The metrics that matter, the funnels that leak, and the cohorts no one noticed were churning.
Growth systems that compound. Acquisition loops, activation funnels, and retention hooks that don't stop working.
What to build, in what order, and why: with frameworks that survive board-level scrutiny.