Enables multiple AI agents to collaborate on complex tasks through structured council sessions. Agents can pose questions, receive feedback from other participating agents, and work together toward solutions. Features atomic state management, agent name resolution, and configurable response formats (Markdown or JSON) for structured multi-agent discussions and decision-making.
Cognium trust score
98%
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 2026-09-19.
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.