What problem does it solve? Getting genuinely diverse perspectives from multiple AI agents is hard when a single model roleplays every voice, since the opinions tend to converge and feel performative. This Skill solves that by spawning each BMAD agent as an independent subagent so every participant thinks for itself. ## Core Features & Use Cases - Independent Subagent Spawning: Each selected agent runs as its own subagent process via the Agent tool, producing authentic disagreement and domain-specific insight. - Dynamic Roster Resolution: Loads the available agent roster from layered TOML config files using a resolver script, so the discussion always reflects the agents actually installed. - Flexible Modes: Supports a --model flag to control subagent model choice and a --solo flag to roleplay all agents in a single response when subagents are unavailable. - Use Case: A product team debating a trade-off (e.g., escrow contract design vs. backend reconciliation) can ask for a roundtable and receive unfiltered takes from an architect, a PM, and a QA agent, then direct follow-up questions at specific agents. ## Quick Start Start party mode and have the installed agents discuss the trade-offs of our current escrow release flow.
