ab-testing

Design statistically rigorous A/B tests for marketing campaigns and landing pages.

1|Updated Feb 26, 2026

Search Tags:#conversion optimization #experimentation #a/b testing #sample size #confidence interval #statistical significance

Ready to run

npx skills add https://github.com/webrix-ai/agent-skills --skill ab-testing-webrix-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ab-testing
Source: https://github.com/webrix-ai/agent-skills/tree/main/skills/ab-testing
Command: npx skills add https://github.com/webrix-ai/agent-skills --skill ab-testing-webrix-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams avoid guesswork by turning campaign, landing page, and product changes into statistically sound experiments with clear success criteria.

Core Features & Use Cases

Experiment Design: Define hypotheses, control and variant setups, traffic splits, and primary metrics.
Sample Size Planning: Estimate how many visitors or users are needed to reach valid results with the desired confidence and power.
Results Analysis: Interpret lift, confidence intervals, and statistical significance to support launch decisions.
Use Case: A marketing team can test two pricing page layouts to see which version increases trial signups without risking an underpowered experiment.

Quick Start

Ask the A/B testing skill to design an experiment for your page or campaign, including the hypothesis, target metric, and current conversion rate.

Frequently Asked Questions about ab-testing

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

FAQPage Schema

How do I calculate sample size for an A/B test on a landing page?▼

To calculate A/B test sample size, you must provide your current conversion rate, desired confidence interval, and statistical power. This ensures your landing page experiment receives enough visitors to produce reliable, statistically significant results.

How do I design a statistically rigorous A/B test for a marketing campaign?▼

Designing a rigorous A/B test requires framing a clear hypothesis, defining control and variant setups, planning traffic splits, and establishing primary success metrics. This process turns campaign changes into statistically sound experiments with clear success criteria.

What metrics do I need to run a conversion optimization experiment?▼

Running a conversion optimization experiment requires success metrics, traffic assumptions, confidence intervals, and power calculations. Providing these inputs allows you to accurately measure lift and determine statistical significance for your variants.

Can I analyze A/B test results and confidence intervals without an underpowered experiment?▼

Analyzing A/B test results requires interpreting lift and confidence intervals to support launch decisions. By applying proper sample size planning and power calculations beforehand, you avoid underpowered experiments and ensure valid, statistically significant outcomes.

When do I need statistical significance for product feature experimentation?▼

You need statistical significance for product feature experimentation when you want to avoid guesswork and make data-driven launch decisions. It confirms that observed changes in success metrics are genuine rather than random variations.