ab-testing

Design and run A/B tests for funnel pages and email sequences.

Updated May 21, 2026
One-click install
npx skills add https://github.com/jedmamosto/m-and-ms --skill ab-testing-jedmamosto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ab-testing
Source: https://github.com/jedmamosto/m-and-ms/tree/main/.agents/skills/ab-testing
Command: npx skills add https://github.com/jedmamosto/m-and-ms --skill ab-testing-jedmamosto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you design, launch, measure, and interpret A/B tests so you can confidently decide which funnel or email variant improves outcomes without gambling on underpowered results.

Core Features & Use Cases

  • Test design and brief writing: Turn an idea into a hypothesis, primary metric, guardrail metric, decision rule, and required sample plan.
  • Split routing setup: Configure page-level variant splits (Vercel Edge or middleware) and audience-level splits (GHL workflow tag/routing patterns).
  • Measurement and decision discipline: Use PostHog or GA4 with the right variant tracking, enforce minimum sample size, significance thresholds, and runtime to avoid premature conclusions.

Quick Start

Ask the AI to create an A/B test plan for your funnel headline by specifying the current and proposed headline, the primary conversion goal, the guardrail metric, and the traffic source you will split (page traffic or GHL audience).

Frequently Asked Questions about ab-testing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an A/B test for a funnel page or email sequence?

Design an A/B test by specifying a hypothesis, split mechanism, primary and guardrail metrics, and decision rules. Ensure one-variable testing with 50/50 splitting to confidently determine which funnel or email variant improves outcomes.

Can I use Vercel Edge routing and GHL workflows to split traffic for A/B tests?

Yes, you can configure page-level variant splits using Vercel Edge routing and audience-level splits using GHL workflow tags. These mechanisms enable precise 50/50 traffic allocation for your A/B test variants.

How do I measure A/B test variants with PostHog or GA4?

Measure A/B test variants by configuring PostHog or GA4 with correct variant attribution tracking. Enforce minimum sample size per variant, 95% confidence thresholds, and guardrail non-regression before calling a winner.

What is the minimum sample size and confidence level needed to call an A/B test winner?

Calling an A/B test winner requires a minimum sample size per variant, 95% confidence level, and verified guardrail non-regression. This prevents gambling on underpowered results and ensures statistical significance.

When should I not use A/B testing for my marketing funnel?

Avoid A/B testing when you cannot enforce one-variable testing, 50/50 splitting, or minimum sample size requirements. Running tests without these constraints leads to premature conclusions and underpowered results.