experiment-doc-builder

Validate experiment briefs for statistical significance and causal hypothesis validity.

5|Updated Mar 29, 2026

Search Tags:#experiment design #data analysis #hypothesis testing #statistical significance #product testing

Ready to run

npx skills add https://github.com/stefanoskarakasis/Product-Marketing-Skills --skill experiment-doc-builder

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: experiment-doc-builder
Source: https://github.com/stefanoskarakasis/Product-Marketing-Skills/tree/main/pmm-execution/skills/experiment-doc
Command: npx skills add https://github.com/stefanoskarakasis/Product-Marketing-Skills --skill experiment-doc-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you design and validate rigorous experiment briefs, ensuring your experiments are statistically sound and based on a strong hypothesis.

Core Features & Use Cases

Hypothesis Validation: Guides you through pressure-testing your hypothesis and ensures it's causally linked to the metric you're testing.
Statistical Significance: Calculates the required sample size and timeline to reach statistical significance.
Rigor Scoring: Scores your experiment on clarity, measurability, impact, feasibility, and learning value, with a minimum score of 70 required for approval.
Contextual Learning: Learns from past experiments to improve future ones.
Use Case: Whether you're a product manager, growth marketer, or designer, this Skill helps you design experiments that can prove or disprove your ideas.

Quick Start

Use the /formulate command to start building your experiment brief.

Frequently Asked Questions about experiment-doc-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I ensure my experiment design has statistical significance?▼

To ensure statistical significance, your experiment design must calculate the required sample size and timeline before launch. This Skill validates your experiment brief to guarantee it reaches statistical significance for reliable product testing results.

What is causal hypothesis validity in feature testing?▼

Causal hypothesis validity ensures your predicted outcome is directly linked to the metric you are testing. This Skill guides you through pressure-testing your hypothesis to confirm causal relationships rather than mere correlations in data analysis.

How do I build an experiment brief for user engagement analysis?▼

You build an experiment brief by scoring it on clarity, measurability, impact, feasibility, and learning value. A minimum rigor score of 70 is required for approval, ensuring high-quality data analysis for user engagement.

Do I need a background in statistics for product testing?▼

You need an understanding of statistical concepts and the ability to apply them practically. This Skill handles the complex calculations for sample size and statistical significance, but foundational knowledge is required for proper experiment design.

Why does my hypothesis testing lack rigor?▼

Your hypothesis testing lacks rigor if it fails to establish causal links or meet the minimum score across clarity, measurability, impact, feasibility, and learning value. This Skill scores your brief and requires a minimum of 70 for approval.