Designs product A/B tests by formulating testable hypotheses, calculating required sample sizes, and prioritizing experiments using ICE scoring. It also provides guidance on interpreting statistical results with practical business context.
Quality gate: PASS · better answers · measured 2026-10-23 Blind-judged against the bare model on 2 requests: average lift +3.0 points (specificity, structure, method, fit). won 2/2, lift +3.0, tokens ×32.25
Security scan: clean · 2026-10-24 · 4 files · ran in sandbox no network calls, shell tricks, credential access or instruction tampering found in its files.
Try asking
Say it in your own words; the assistant finds this recipe by itself. Examples:
“Jeg skal designe en A/B-test på vores pris-side. Kan du hjælpe mig med at formulere hypotesen og beregne den nødvendige stikprøvestørrelse?”
“Vi har en liste over 5 idéer til nye funktioner. Brug ICE-scoring til at prioritere dem, så vi ved hvilken vi skal bygge først.”
“Min test viste en statistisk signifikant forskel, men effekten er meget lille. Er det værd at rulle ud? Hjælp mig med at vurdere den praktiske betydning.”
“I want to test if changing the CTA button color from blue to green will increase sign-ups. Help me write a proper hypothesis and tell me how many users I need to test this.”
“We have three potential features to build next. Can you score them using the ICE framework based on the impact, confidence, and effort estimates I provide?”
“My A/B test ran for two weeks and the p-value is 0.04, but the confidence interval is very wide. Should I ship the change? Explain the practical significance.”
Try this skill from Claude, ChatGPT or a chat on your own page. Free plan, no credit card.Get started free
Do not use this skill for general data analysis tasks that do not involve controlled experiments, such as cohort analysis or funnel optimization without a test. It is not intended for implementing the technical infrastructure of A/B testing (e.g., writing code for traffic splitting) but rather for the statistical and strategic planning. For pure statistical theory questions unrelated to product decisions, a general statistics skill is more suitable.
Details
When it is the right choice
Use this skill when you need to plan a new product experiment, including defining the hypothesis, primary metrics, and guardrails. It is appropriate for calculating the required sample size to detect a specific effect size or for prioritizing a backlog of potential tests using ICE scores. It is also useful for interpreting the statistical output of a completed experiment to make a go/no-go decision.
The full recipe the assistant reads
Experiment Designer
Design, prioritize, and evaluate product experiments with clear hypotheses and defensible decisions.
When To Use
Use this skill for:
- A/B and multivariate experiment planning
- Hypothesis writing and success criteria definition
- Sample size and minimum detectable effect planning
- Experiment prioritization with ICE scoring
- Reading statistical output for product decisions
Core Workflow
Write hypothesis in If/Then/Because format
If we change [intervention]
Then [metric] will change by [expected direction/magnitude]