What problem does it solve? Before committing to full development, teams often discover too late that a design relies on unproven technology, fails performance targets, or breaks on third-party integrations. This Skill validates those risk points with minimal throwaway prototypes so design flaws surface early and cheaply. ## Core Features & Use Cases - Risk-Driven Validation: Automatically identifies technical feasibility, performance, integration, and alternative-scheme risks from a design document, then builds the smallest possible runnable prototype for each. - Clear Verdicts: Every risk point receives an explicit conclusion (pass / conditional pass / fail) with evidence, driving a continue / adjust / rollback decision. - Requirement Integration: When a .requirements/config exists, verification reports and demo code are persisted into the requirement directory via the req CLI. - Use Case: A design proposes Redis distributed locks and a 1000 QPS query endpoint. The Skill builds small prototypes in .demo-verify/, benchmarks them, and reports that the lock works but the query needs a cache layer before development proceeds. ## Quick Start Ask the AI to verify the risky parts of the current design document with a quick demo prototype before starting full development.