Skills

A/B Testing

verified
Updated May 13, 2026

What this skill does

Helps design statistically rigorous A/B tests for marketing campaigns, landing pages, and product features. Calculates required sample sizes, defines success metrics, sets up test variants, and analyzes results with confidence intervals. Prevents common testing mistakes like peeking and underpowered tests.

Example

PROMPT

Design an A/B test for our pricing page. Goal: increase trial signups by 15%. Current conversion rate: 3.2%.

OUTPUT
A/B Test Plan — Pricing Page HYPOTHESIS Simplifying the pricing page from 4 tiers to 3 will increase trial signups by 15% (from 3.2% to 3.68%). TEST DESIGN Control (A): Current 4-tier pricing page Variant (B): Simplified 3-tier pricing page Metric: Trial signup rate Traffic Split: 50/50 SAMPLE SIZE Required: 12,400 visitors per variant Duration: ~18 days (at 1,400 visitors/day) Confidence: 95% Power: 80% RESULTS (after 18 days) Control: 3.2% (398/12,438) Variant: 3.9% (487/12,487) Lift: +21.9% ✅ Statistically significant (p=0.003)

Required Tools

Google AnalyticsGoogle Analytics

Compatible Agents

ClaudeClaude
CursorCursor
WindsurfWindsurf
ChatGPTChatGPT
Any MCP-compatible agentAny MCP-compatible agent

Add to your agent

Download Skill

Or install via CLI:

$ npx skills add webrix-ai/agent-skills --skill ab-testing

Deploy Org-wide

Provision to teams via RBAC
Identity-aware execution
Signed & verified skills
Full audit trail
Auto-bundled with required MCP servers
Use withwillow

Free for up to 5 users

Your agents are already in the wild.

Give them a Basecamp. Go from AI chaos to AI work, in minutes.

A/B Testing | Willow Marketplace