ab-split-test-engineering

# A/B Split Test Engineering

## Overview
This skill provides a structured approach to A/B split test engineering, enabling users to systematically improve their marketing campaigns and website performance. By leveraging Neil Patel's proven methodologies, this skill guides users through the entire testing process, from prioritizing tests to analyzing results and calculating conversion lift.

**Keywords**: A/B testing, split testing, conversion rate optimization, CRO, Neil Patel, ICE score, statistical significance, hypothesis testing, multivariate testing, landing page optimization, ad optimization, email optimization.

## Discovery & Planning Questions
1. What is the specific URL of the page, a description of the ad, or the subject of the email you want to A/B test?
2. What is the single most important metric you want to improve with this test? (e.g., increase click-through rate, reduce bounce rate, boost sales, increase form submissions)
3. Who is the target audience for this test? Please describe their demographics, interests, and online behavior.
4. Do you have any existing data, user feedback, or analytics (like heatmaps, scroll maps, or user recordings) that suggest a problem or opportunity?
5. What is your initial hypothesis? What specific element do you want to change, and why do you believe it will improve performance?
6. What is the typical weekly traffic to the page or the number of recipients for the email you plan to test? This helps in calculating the required sample size and test duration.
7. Are there any technical limitations, platform constraints, or specific A/B testing tools I should be aware of?
8. Are there any brand guidelines, such as specific colors, fonts, or messaging tones, that must be maintained in the test variation?
9. What is your timeline for this test, from implementation to conclusion?
10. What do you consider a successful outcome? Is there a specific percentage lift or target goal you are aiming for?

## Core Frameworks
This agen