What problem does it solve? Long coding sessions accumulate context that quietly turns assumptions into facts, and confident answers are not always correct ones. This Skill catches wrong directions early by cross-examining every non-trivial decision with a fresh-context adversarial reviewer 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 limit of three cycles. - Cross-model escalation: Optionally routes the artifact and contract to external CLI reviewers such as Gemini CLI or Codex CLI through read-only sandboxed invocations, with explicit user authorization for every run. - Use Case: Before committing a new caching layer claimed to be thread-safe, the Skill extracts the diff and its contract, spawns an adversarial reviewer instructed to find issues rather than validate, classifies each finding as actionable, trade-off, or noise, and loops until findings are trivial. ## Quick Start Ask the agent to apply doubt-driven development to stress-test the architectural decision or code change you are about to commit.