This walks you through proper A/B test design from hypothesis to analysis. It pushes you to write structured hypotheses (the "Because X, we believe Y will cause Z" format), calculate sample sizes before you start, and pick one primary metric instead of getting lost in dashboards. The statistical rigor section is solid on common mistakes like peeking at results early or testing multiple things at once. Includes sample size tables, traffic allocation strategies, and the difference between client-side and server-side testing. It's opinionated about doing this right rather than just shipping tests fast, which is probably what you need if you keep launching experiments that run forever without reaching significance.
npx skills add https://github.com/davila7/claude-code-templates --skill ab-test-setup