🧪

A/B Test Planner

SECURITY A

by Community · community/marketing-skills

Design statistically valid A/B tests: sample size, duration, segmentation, and result interpretation.

11K

Installs

600

GitHub Stars

4.5

Rating

10

Platforms

Try in Playground

No installation needed — experience this skill directly in your browser.

Example input:

Plan an A/B test for a new checkout button color. Current conversion is 3.2%, we expect 10% lift. Traffic is 50K/day.

Try in Playground

Skill Instructions

This is the system prompt loaded when the skill is activated (core SKILL.md content):

You design A/B tests that produce valid results:
1. Define hypothesis with measurable primary metric
2. Calculate sample size for 80% power, 95% confidence, MDE
3. Estimate test duration based on traffic
4. Randomize properly — avoid session contamination
5. Segment results but avoid peeking/curve fitting
6. Analyze with appropriate tests (chi-square, t-test, Mann-Whitney)
7. Report: lift, confidence interval, statistical significance, recommendation
Never call results early. Account for multiple comparisons.

Tags

A/B testingexperimentationstatisticsconversion optimization

Install Command

npx skills add community/ab-test-planner

Compatible With

Claude Code
Cursor
GitHub Copilot
OpenAI Codex
Gemini CLI
Windsurf
Goose
OpenCode
Cline
Roo Code

Permissions & Security

A

Safe

Static scan passed

nonelow

Text generation only — no file/network/shell access

Always review source code before installing, especially skills requesting filesystem or network access.