A/B Test Setup

A/B Test Setup is an AI Engineering skill for Claude Code, published by minhnv0807 in ai-business-skills.

553 stars222 forkson minhnv0807/ai-business-skillsAdded 2026/08/25+2% in starsRepository updated 2026/08/17

agent-skillsai-agentsai-avataranthropicchatgptclaude-codeclaude-plugincontent-marketingcopilotcursordropshippinggeminiglobal-marketingllm-promptsmarketing-automationmarketing-skillspersonal-brandprompt-engineeringtiktok-marketingvietnam

Install in seconds

Install A/B Test Setup

Copy A/B Test Setup into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/minhnv0807/ai-business-skills/tree/master/skills/en/19-ab-test-setup-global ~/.claude/skills/19-ab-test-setup-global

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/minhnv0807/ai-business-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/en/19-ab-test-setup-global/SKILL.md in minhnv0807/ai-business-skills
Installs to: ~/.claude/skills/19-ab-test-setup-global
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What A/B Test Setup does

A/B Test Setup helps you design valid experiments with one variable, a hypothesis, sample size, runtime, and significance checks. Use it when you need to compare variants, estimate how long a test should run, or interpret whether a result is real.

A/B Test Setup is cataloged under AI Engineering on DirSkills. A/B Test Setup comes from a repository tagged agent-skills, ai-agents, ai-avatar, anthropic and chatgpt.

Documentation

README

Excerpt

A/B Test Setup (Global)

Run experiments that produce decisions, not noise. Most "A/B tests" in marketing are underpowered, peeked-at, and badly hypothesized — meaning the team learns nothing and ships the louder variant.

For Newbies

A valid A/B test answers one question: "Did this change cause a real improvement, or am I seeing noise?"

To answer it credibly you need four things:

A specific hypothesis with a numeric prediction
One variable changed (everything else identical)
Enough sample to detect the effect you care about
Statistical significance before you call a winner (typically p < 0.05)

If any one of these is missing, you don't have an A/B test — you have a coin flip with extra steps.

This is the opening of the README. Read the full README on GitHub.

Commands A/B Test Setup provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/landing-a
/landing-b

Frequently asked about A/B Test Setup

What else does minhnv0807 publish alongside A/B Test Setup?
A/B Test Setup is one of 25 skills that DirSkills catalogs from minhnv0807/ai-business-skills, the repository it ships in. Its siblings there include AI Business Skills, Ad Copy Global and Ads Audit Global. Each one is a separate skill with its own page in this directory, installs the same way A/B Test Setup does, and is maintained by minhnv0807 in that same repository. The rest of the collection is listed on the minhnv0807/ai-business-skills page.
How does A/B Test Setup compare to other AI Engineering skills?
A/B Test Setup ranks #2034 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of A/B Test Setup against them. Open each page to compare what they document and how they install.