What problem does it solve?
Planning experimentation is messy and risky when teams skip context, fail to measure the right metrics, or stop tests early; this Skill compiles the right questions about hypotheses, context notes, traffic, and constraints so you only launch tests that answer meaningful questions.
Core Features & Use Cases
- Hypothesis framework: Guides you to turn observations into experiments with clear predictions, expected audiences, and metric-based success criteria while encouraging you to review product marketing context before asking.
- Sample sizing, traffic, and execution planning: Connects baseline rates with lifts, references the included sample-size guide, and reminds you to budget traffic splits, durations, peeking safeguards, and implementation approaches for client- or server-side setups.
- Metrics and results discipline: Clarifies primary, secondary, and guardrail metrics, documents pre-launch checklists, and links to test templates so you can log learnings, interpret significance, and decide whether to ship.
Quick Start
Ask the skill to design a hypothesis and test plan for the change you want to evaluate on your page.
