riskiest-assumption-testlisted

Walks the founder through assumption dump, risk × impact ranking, falsifiable hypothesis rewriting, and test-method selection — produces a 1-page Assumption Test Plan with the top-3 ranked hypotheses, success/kill criteria, and an interactive HTML risk × impact matrix. Use after `validation-canvas` and BEFORE `pitch-deck` — pitching on untested assumptions is sales theater. Triggers on "test my assumptions", "riskiest assumption", "RAT", "what should I validate first", "assumption mapping", "experiment design", "how do I de-risk this", "Wizard of Oz test", "fake door test", "concierge MVP", "smoke test", "5-interview rule", or when `validation-canvas.md` has populated Stress Tests and the user asks what's next. Job — "what have we proven?". Upstream half of validation closure; the downstream half loops results back into the canvas. NOT a discussion of testing in general (use `team-composer`); NOT a generic experiment platform. Produces a plan, not the experiments.
sorawit-w/agent-skills · ★ 1 · Testing & QA · score 75

Install: claude install-skill sorawit-w/agent-skills

# 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): 1. **`assumption-test-plan.md`** — canonical, editable Markdown with sections: `## Assumptions Dump`, `## Ranking Matrix`, `## Top 3 Hypotheses`, `## Test Plan`, `## Kill Criteria`, `## Results`. Headings are load-bearing — `pitch-deck` and `startup-grill` grep them. `## Results` is initially empty; the founder fills it in as tests complete, which triggers the loop-back protocol. 2. **`test-matrix.html`** — interactive risk × impact matrix. Single self-contained HTML file. Each assumption is a draggable card on a 2D plane; click to expand the hypothesis, success criteria, kill criteria, and chosen test method. Color-coded by category (desirability / viability / feasibility). Print-clean for inclusion in boar