Plan A/B, A/B/n, and multivariate experiments with sample-size calculations.
npx skills add https://github.com/scanbott/claude-skills --skill ab-test-setup-scanbott
Please help me install this Agent Skill. Skill: ab-test-setup Source: https://github.com/scanbott/claude-skills/tree/main/ab-test-setup Command: npx skills add https://github.com/scanbott/claude-skills --skill ab-test-setup-scanbott
Designing and executing rigorous growth experiments to determine which changes drive measurable improvements, while avoiding wasted effort on unproven ideas.
Outline a test idea and craft a formal hypothesis and test plan using the standard A/B framework.
High-intent search queries and answers about installing and using this skill.
To calculate sample size for an A/B test, you apply statistical power analysis based on your expected effect size and variance. This skill enforces statistical rigor by computing the required sample size and appropriate test duration before execution.
The best way to plan an A/B/n test for a marketing funnel is using a hypothesis-driven framework that defines primary, secondary, and guardrail metrics. This approach provides templates to structure multi-variant experiments and document resulting winning patterns.
You need multivariate experiments instead of standard A/B testing when evaluating multiple variable combinations simultaneously across product pages or onboarding flows. This skill plans MVT designs alongside split URL tests to determine which specific changes drive measurable improvements.
Defining guardrail metrics for a growth experimentation program involves identifying baseline thresholds that must not degrade during testing. This skill provides metrics guidance to set primary, secondary, and guardrail parameters ensuring experiments remain statistically valid.
Yes, you can document and scale winning test patterns using the provided playbook guidance and comprehensive templates. The skill generates standardized repositories for planning, running, and reporting tests to institutionalize successful growth experiments.
product-on-purposeDesign end-to-end experiment plans with hypotheses, variants, metrics, and guardrails.
spandiosAnalyze A/B test results for statistical significance and actionable recommendations.
huiferMap customer journey data into a visual cross-channel funnel from awareness to advocacy.
sefllessPlan A/B tests with hypotheses, sample size calculations, and variant design.
