Use Cases
A SaaS team notices their pricing page converts at 3% and wants to test a larger CTA button. Using this skill, they frame a hypothesis, calculate that they need ~12k visitors/variant for a 20% lift, define primary and guardrail metrics, and launch a 50/50 A/B test. The skill prevents early peeking and documents results into a playbook, giving them a validated, reusable conversion insight.
A growth lead wants to run experiments as a continuous engine, not one-offs. The skill helps build an experiment backlog from analytics and support tickets, score with ICE, set a cadence of 4-8 tests/month, and document winners into a playbook. This systematizes learning, improves experiment velocity, and compounds cumulative lift across the funnel.
Skill File
Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
When a user wants to plan, design, or implement an A/B test, split test, multivariate test, or build a growth experimentation program. Also triggered by mentions of hypothesis, statistical significance, ICE score, experiment backlog, or comparing two approaches to measure performance.
A statistically rigorous test plan or a systematic experimentation program: hypothesis, variants, metrics, sample size, and a documented playbook of reusable growth patterns.
