Enables multi-agent debates for code review where multiple language models analyze code changes through structured debate mechanics. Features severity-based scoring for issues, multiple debate modes including adversarial and consensus approaches, and deterministic point-based judging. Integrates with Claude Desktop, Claude CLI, and VS Code to provide collaborative code review workflows through agent competition.
Cognium trust score
85%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.