ab-testing

Designing an A/B test requires structuring hypotheses, selecting metrics, and planning sample sizes. This Skill builds rigorous test plans with traffic allocation, guardrail metrics, and significance expectations to ensure trustworthy conversion optimization decisions.

A/B/n split tests compare multiple variants against a control, while multivariate testing evaluates combinations of page elements. This Skill structures both experiment types by defining hypotheses, variants, and success criteria for measurable product changes.

Conversion optimization hypotheses map proposed product changes to expected metric outcomes. This Skill helps formulate clear hypotheses, define guardrail metrics, and establish testing duration to validate growth experimentation assumptions.

Yes, this Skill supports experiment program planning alongside individual test design. It provides documentation frameworks, statistical planning, and analysis guidance to structure multiple growth experiments across a team.

Reliable A/B testing requires sample size planning, significance expectations, and guardrail metrics. This Skill defines these statistical parameters upfront to prevent unreliable experiments and support measurable decision making.

Documenting A/B test results requires comparing variant performance against predefined success criteria. This Skill provides documentation frameworks to record hypotheses, metrics, and analysis steps, guiding whether a product change should be shipped.