What problem does it solve? Confident answers are not always correct ones, and long coding sessions quietly turn assumptions into accepted facts. This Skill catches wrong directions early by forcing every non-trivial decision through an adversarial fresh-context review while course-correction is still cheap. ## Core Features & Use Cases - Structured Doubt Cycle: A five-step loop (CLAIM, EXTRACT, DOUBT, RECONCILE, STOP) that isolates the artifact and contract, then hands them to a reviewer biased to disprove rather than approve. - Cross-Model Escalation: Optionally routes the artifact to external CLI reviewers (Gemini CLI, Codex CLI) via stdin with read-only sandboxing to catch single-model blind spots. - Bounded Loop with Escalation: Stops after trivial findings, three cycles, or user override, and classifies findings as contract misread, actionable, trade-off, or noise. - 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, and surfaces a race condition before the code ships. ## Quick Start Ask the agent to apply doubt-driven development to review the architectural decision or non-trivial code change you are about to commit.
