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 early by forcing every non-trivial decision through an adversarial fresh-context review while course-correction is still cheap. ## Core Features & Use Cases - Five-step doubt cycle: CLAIM the decision, EXTRACT the smallest reviewable artifact plus contract, DOUBT it with an adversarial fresh-context reviewer, RECONCILE findings by precedence, and STOP at a bounded condition (trivial findings, 3 cycles, or user override). - Cross-model escalation: In interactive sessions, always offers a second opinion via external CLIs such as Gemini or Codex, with PATH checks, read-only sandboxing, and stdin piping to avoid shell injection. - Use Case: Before committing a new caching layer claimed to be thread-safe, extract the diff and its contract, spawn an adversarial reviewer instructed to find issues rather than validate, classify each finding as contract misread, actionable, trade-off, or noise, and iterate until the stop condition is met. ## Quick Start Ask the agent to apply doubt-driven development to review the architectural decision in your current change before committing it.
