Most code review happens after you've already committed to an approach. This flips that: before any non-trivial decision stands (architectural choices, production deploys, cross-boundary logic), you spawn a fresh-context reviewer with an explicit adversarial prompt to disprove it. Not validate, disprove. The skill defines what counts as non-trivial, gives you a five-step checklist (CLAIM, EXTRACT, DOUBT, RECONCILE, STOP), and includes cross-model escalation hooks so you can throw the same artifact at Gemini or another model to catch blind spots your first reviewer shared with you. Use it when correctness matters more than speed, when working in unfamiliar code, or any time debugging later would cost more than verification now.
npx skills add https://github.com/addyosmani/agent-skills --skill doubt-driven-development