ab-test-planner

1# A/B Test Planner Skill
2 
3Design experiments that produce trustworthy results — not just directional signals. Every test output includes hypothesis, success metrics, sample size, duration, and a results interpretation guide.
4 
5## Required Inputs
6 
7Work from what is given. If any of these is missing, still produce the complete output: fill each gap with a reasonable assumption marked *(assumed, confirm)* and list those assumptions at the end. Ask a question first only when the core subject itself is missing (there is nothing to write about).
8- **What is being tested** (feature, UI change, copy, pricing, onboarding step)
9- **Hypothesis** (or ask to help formulate one)
10- **Primary metric** (conversion rate, click-through, completion rate, etc.)
11- **Baseline rate** and **minimum detectable effect** (MDE)
12- **Daily eligible users** (to calculate duration)
13 
14## Experiment Design Checklist
15 
16Before running any test, confirm:
17- [ ] Clear hypothesis with predicted direction
18- [ ] Single primary metric (plus up to 2 guardrail metrics)
19- [ ] Minimum detectable effect (MDE) defined
20- [ ] Sample size calculated
21- [ ] Test duration estimated
22- [ ] Segment isolated (no overlap with other running tests)
23- [ ] Rollback plan defined
24 
25## Hypothesis Template
26 
27> "We believe that [change] will cause [primary metric] to [increase/decrease] by [X%] for [user segment], because [rationale based on data or insight]."
28…