Runs structured debates between multiple AI models (Claude, GPT, Gemini, Grok, DeepSeek) where each model argues independently in blind rounds, then deliberates and synthesizes findings. Outputs categorized into Strong Ground (agreement), Fault Lines (disagreements), Blind Spots (unique insights), and Your Call (human decisions needed). Offers free, pro, and enterprise tiers with a web console and CLI interface.
Cognium trust score
97%
Tier
Verified
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.