Ab test
Full-stack Claude Code pack for marketers: FTC claim-substantiation, CAN-SPAM, deliverability, privacy & no-fabricated-metrics guardrails + skills for positioning, ad copy, landing pages, email, SEO, A/B tests & analytics, loops & review agents. Not legal advice.
npx -y skills add m-binimran/marketing-pack --skill ab-testAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Design an A/B test - hypothesis, single variable, variants, sample size/duration, and the metric - and interpret results honestly. Use when optimizing a page, ad, email, or funnel step.
SKILL.md
1.2 KB, as published. Nobody here has run it
ab-test
Test the high-leverage thing, change one variable, and read the result honestly.
Process
- Hypothesis: "Because [insight], changing [element] will [effect] on [metric]." Test the high-leverage element first (headline, offer, CTA, hero) - not the button colour.
- One variable between A and B; everything else equal.
- Metric & guardrail: the primary conversion metric, plus a guardrail metric you don't want to harm.
- Sample size & duration: estimate the needed sample for a meaningful result; run full weeks; don't peek and stop early.
- Interpret honestly: report sample size and whether the difference is actually significant - small or short tests often aren't. No declaring a winner from noise.
Output
- A test plan: hypothesis, variants, primary + guardrail metric, sample/duration, and a results-reading rule.
Guardrails
- Don't claim significance without the data (
truth-telling); report sample size + result honestly. - One variable; avoid stopping early on a lucky swing.