What problem does it solve? Confident answers are not always correct ones, and long sessions quietly turn assumptions into facts. This Skill catches wrong decisions while course-correction is still cheap by forcing every non-trivial decision through an adversarial fresh-context review before it stands. ## Core Features & Use Cases - Five-step doubt cycle: CLAIM the decision, EXTRACT the smallest reviewable artifact plus contract, DOUBT it with an adversarial reviewer, RECONCILE findings by precedence, and STOP at a bounded condition (trivial findings, 3 cycles, or user override). - Adversarial reviewer prompting: Passes only the artifact and contract to a fresh-context reviewer with an issues-only prompt, never the author's conclusion, avoiding validation bias. - Cross-model escalation: Optionally routes the artifact to an external CLI reviewer (Gemini CLI, Codex CLI) with read-only sandboxing, stdin piping, and explicit per-invocation user authorization. - Use Case: Before committing a caching layer claimed to be thread-safe, extract the diff and its contract, spawn a fresh-context reviewer instructed to find race conditions and unstated assumptions, then classify each finding as contract misread, actionable, trade-off, or noise. ## Quick Start Ask the assistant to apply doubt-driven development to the architectural decision or non-trivial code change you are about to commit.
