Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mohitagw15856/ab-test-planner
Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments.
Passed 22 of 25 test cases with the skill, and 13 of 25 without it.
and 10 more in the full report
9 fixed13 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our onboarding completion baseline rate is 40%, and we aim to detect a 10% relative MDE. Estimate sample size per variant.
| Checked | Without skill | With skill |
|---|---|---|
| Estimates the required sample size at approximately 9,500 per variant. | Missed | Passed |
| Includes a disclaimer recommending precision tools like Evan Miller or Statsig. | Missed | Passed |
The instructions your model reads when the skill loads.
Diseña experimentos que producen resultados confiables — no solo señales direccionales. Cada output del test incluye hipótesis, métricas de éxito, tamaño de muestra, duración y una guía de interpretación de resultados.
Pregunta al usuario por estos datos si no están proporcionados:
Antes de ejecutar cualquier test, confirma:
"Creemos que [cambio] causará que [métrica primaria] se [incremente/disminuya] en un [X%] para [segmento de usuarios], porque [razonamiento basado en datos o insight]."
Nunca ejecutes un test sin una hipótesis direccional. "Veamos qué pasa" no es una hipótesis.
Usa esta fórmula (proporciona el output, no la fórmula, al usuario):
Para escenarios comunes, proporciona estimaciones pre-calculadas:
test cases passed, vs 13 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.