Experiment Tracker

Overview

This skill turns messy validation history into a usable decision state. The goal is to track what was actually learned, separate strong from weak signals, and recommend the next best experiment.

Load references/signal-quality.md when weighing evidence. Load references/decision-states.md when deciding whether to continue, narrow, pivot, or stop.

When to use

• When multiple validation tests have been run
• When the user has conflicting or noisy evidence
• When a next experiment should build on prior evidence rather than restarting

Do NOT use when: