What problem does it solve? Getting genuinely diverse perspectives from AI agents is hard when a single model roleplays multiple personas, since the opinions tend to converge and feel performative. This Skill solves that by spawning each BMAD agent as a real, independent subagent so every voice 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. - Roster-Driven Voice Selection: Reads the agent manifest to pick 2-4 relevant experts per round, with support for user-directed cross-talk between specific agents. - Solo and Model Control Modes: Supports --solo to roleplay all agents in one response and --model to force a specific model for all subagents. - Use Case: A product team debating a new feature architecture can ask for a roundtable where the architect, UX designer, and security-focused agents each weigh in independently, then follow up by asking one agent to react to another's position. ## Quick Start Ask the assistant to start party mode and discuss your project topic with the available BMAD agents.
