LeoYeAI/agent-master-skills / skills/ab-test-architect
ab-test-architect
VerifiedPlan, prioritize, and design rigorous A/B tests using the Test Velocity Method. Use when a user wants to test a landing page, CTA, email, signup flow, pricing page, or any digital experience — this skill produces a complete, dev-ready test plan with hypothesis, sample size, duration, segmentation strategy, and guardrail metrics.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 19.7 KB |
| _meta.json | config | 291 B |
| listing-metadata.md | markdown | 1.8 KB |
listing-metadata.md
View on GitHub# ClawMart Listing: A/B Test Architect
**Product type:** skill
**Price:** $19
**Category:** Marketing
**Name:** A/B Test Architect
**Tagline:** Plan, prioritize, and ship rigorous A/B tests — no guesswork, no wasted sprints.
**About:**
Most CRO programs fail not because tests lose — they fail because teams test the wrong things in the wrong order with no clear success criteria. A/B Test Architect gives your AI assistant a complete framework for designing experiments that actually produce learning. Describe what you want to test and get a dev-ready test plan in minutes: structured hypothesis, sample size calculation, recommended duration, segmentation strategy, and guardrail metrics. Built around the Test Velocity Method — a five-step framework for shipping more tests, faster, with better signal. Whether you're running your first A/B test or managing a full experimentation roadmap, this skill keeps your program rigorous from hypothesis to results log.
**Capabilities:**
- Prioritizes test ideas using the PIE scoring matrix (Potential, Importance, Ease) so you always start with the highest-leverage test
- Writes structured hypotheses in the "Because / We believe / Will / For / Measured by" format — forces clarity before a single line of code is written
- Calculates estimated sample size and recommended test duration (always full weeks to account for weekly seasonality)
- Defines primary KPI and guardrail metrics to prevent shipping tests that win on one metric while quietly tanking another
- Guides segmentation decisions — who sees the test, traffic splits, and when to target vs. run full-traffic
- Produces complete dev handoff notes including variant descriptions, analytics instrumentation, QA checklist, and results log format
**Tags:** ab-testing, cro, conversion-rate-optimization, experimentation, marketing
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |