Riskiest-Assumption Test

Convert the beliefs captured in the validation-canvas Stress Tests into falsifiable hypotheses with explicit test methods, success criteria, and kill criteria. Ship a 1-page Assumption Test Plan plus an interactive risk × impact matrix.

This skill's job is experimental: what have we proven, and what's the cheapest experiment that would invalidate the next belief? It's the bridge between the canvas (declarative beliefs) and the pitch deck (story you can defend).

What this skill produces

Every run produces exactly two files, both in the resolved RAT root (see Phase 0 Step 0.0 for path resolution; default is docs/rat/ for solo runs, docs/startup-kit/rat/ when invoked via orchestrator):