ab-test-setup

Plan, run, and analyze A/B tests with statistical significance.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/gerald-ica/opencode-config-snapshot --skill ab-test-setup-gerald-ica
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ab-test-setup
Source: https://github.com/gerald-ica/opencode-config-snapshot/tree/main/opencode/skills/ab-test-setup
Command: npx skills add https://github.com/gerald-ica/opencode-config-snapshot --skill ab-test-setup-gerald-ica

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

A structured, repeatable framework to design, run, and interpret experiments that help teams decide between competing approaches with statistical confidence.

Core Features & Use Cases

  • Hypothesis framing and test-type selection (A/B, A/B/n, MVT, Split URL)
  • Sample size guidance and duration planning using the quick reference
  • Primary/secondary/guardrail metrics selection and interpretation
  • Variant design guidance and traffic allocation strategies
  • Full test lifecycle documentation templates and governance

Quick Start

Use the structured approach to define a hypothesis, determine baseline metrics and the minimum detectable effect, calculate required sample size, and launch a two-variant test on a high-traffic page.

Frequently Asked Questions about ab-test-setup

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

FAQPage Schema
How do I calculate sample size and duration for an A/B test?

To frame an A/B test hypothesis, define the expected change, the target metric, and the minimum detectable effect. This Skill guides you through structuring hypotheses for product, marketing, and UX experiments before variant design.

What is the difference between A/B/n testing and multivariate testing (MVT)?

A/B/n testing compares multiple independent variants against a control, while MVT evaluates interactions between multiple elements simultaneously. The Skill helps select the right test type based on your experimentation scope and traffic constraints.

How do I select primary, secondary, and guardrail metrics for experimentation?

Select primary metrics to measure the main test goal, secondary metrics for additional insights, and guardrail metrics to prevent negative impacts on user experience. The Skill provides a framework for choosing and interpreting all three metric types.

Can I use this framework for split URL testing and different traffic allocation strategies?

Yes, the framework supports split URL tests alongside A/B, A/B/n, and MVT tests. It provides variant design guidance and traffic allocation strategies to distribute visitors effectively across test variations.

How do I interpret statistical significance and document A/B test results?

Interpret statistical significance by evaluating whether the observed variant performance meets your predefined threshold. The Skill includes full test lifecycle documentation templates and governance to record outcomes comprehensively.