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 reviewer biased to disprove, 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 via an adversarial fresh-context reviewer, RECONCILE findings by precedence, and STOP within a bounded three-cycle loop. - Adversarial Review Prompting: Passes only the artifact and contract to the reviewer with an issues-only prompt, preventing the bias toward agreement that comes from sharing your conclusions. - Cross-Model Escalation: Offers optional second opinions through external CLIs like Gemini or Codex with read-only sandboxing and explicit per-invocation user authorization. - Use Case: Before committing a new caching layer you believe is thread-safe, run the doubt cycle so a fresh reviewer hunts for race conditions, unstated assumptions, and contract violations before the code ships. ## Quick Start Ask the agent to apply doubt-driven development to stress-test the architectural decision or code change you are about to commit.
