Ab testing design
Skill Dragoon0x/everything-design-taste/skills/ab-testing-design
A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.
npx -y skills add Dragoon0x/everything-design-taste --skill ab-testing-designAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 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
A/B test design, experiment setup, variant design, and statistical analysis for designers.
SKILL.md
1.2 KB, as published. Nobody here has run it
Ab Testing Design
Experiment Design
What to Test
- High impact, easy to change: Copy, color, layout, CTA.
- Clear hypothesis: "Changing the CTA from 'Sign Up' to 'Start Free Trial' will increase conversions because it communicates zero commitment."
What Not to Test
- Preferences ("Do users prefer blue or green?").
- Everything at once (test one variable).
- Insignificant elements (button border-radius doesn't matter).
Variant Design
- Control (A) = current experience.
- Variant (B) = one change with a hypothesis.
- Don't create wildly different variants (you won't know what caused the difference).
Statistical Rigor
- Sample size calculator before starting.
- Run for full weeks (not 2 days — behavior varies by day).
- 95% confidence minimum before declaring a winner.
- Watch for novelty effects (new things get more clicks initially).
Reporting
- State the hypothesis.
- Show the numbers (conversion rate, confidence interval).
- State the winner with context.
- Document learnings for future tests.