debate-skills

Design reviewer who evaluates code patterns, complexity, and coupling. Spawned as part of adversarial debate code reviews to find pattern violations, unnecessary complexity, tight coupling, and abstraction mismatches.

Adversarial tester who tries to break code and reviews test quality. Spawned as part of adversarial debate code reviews to find missing validation, unhandled errors, implicit assumptions, and test gaps.

Pre-mortem specialist who identifies failure modes before implementation begins. Spawned as part of adversarial planning debates to find missed dependencies, integration risks, specification gaps, and complexity underestimates.

Implementation designer who produces concrete step-by-step plans. Spawned as part of adversarial planning debates to draft implementation approaches, consider alternatives, and create file manifests for coding agents.

Devil's advocate who challenges planning agents' claims during adversarial planning debates. Does not plan independently - verifies Scout's discoveries against actual code, challenges Planner's assumptions, and tests whether Critic's concerns are real.

Use this skill when orchestrating multi-agent adversarial code reviews using Claude Code agent teams. Activates when conducting thorough code reviews, setting up review debate teams, spawning specialized review personas, or synthesizing findings from multiple reviewers. Provides spawn prompts, debate protocol, and synthesis templates.

Use this skill when orchestrating multi-agent adversarial planning debates before code is written. Activates when planning complex implementations, coordinating pre-implementation discovery, stress-testing implementation approaches, or producing validated plans for coding agents. Provides discovery prompts, debate protocol, and plan templates.