ab-test
Skill1 starsChanged 5 months agoMITView on GitHub
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.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- ali-demirbas/ab-test-playbooktheir own version, first seen Oct 21, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
- sidchaudhary/gtm-skillstheir own version, first seen Aug 21, 2026
- Aetheria-Labs1/storefront-skillstheir own version, first seen Aug 7, 2026
- sergeeey/Claude-cod-top-2026their own version, first seen May 13, 2026
- BlackBlazeXXX/claude-skills-marketingtheir own version, first seen Mar 31, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- sergeeey/Claude-cod-top-2026★ 9same name
- Aetheria-Labs1/storefront-skills★ 8same name
- BlackBlazeXXX/claude-skills-marketing★ 1same name
- sidchaudhary/gtm-skills★ 1same name
- akachandan1/proofstack★ 0same name
- ali-demirbas/ab-test-playbook★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ad-copySkill
- campaign-briefSkill
- competitor-analysisSkill
- content-marketingSkill
- email-sequenceSkill
- icp-personaSkill
- landing-pageSkill
- lead-magnetSkill
- marketing-analyticsSkill
- positioningSkill
- seo-briefSkill
- social-adsSkill
- subject-linesSkill
- value-propSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Test the high-leverage thing, change one variable, and read the result honestly.
- Very specific: line 24
Don't claim significance without the data (truth-telling).
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.