What problem does it solve? Getting genuinely independent perspectives from an AI is hard: a single model voicing multiple roles tends to drift into agreement, producing flat panels instead of real debate. This Skill runs lively roundtable discussions where distinct agents or custom personas argue, clash, and build on each other, and it lets you author persistent custom parties such as review crews or customer focus groups. ## Core Features & Use Cases - Multi-persona roundtables: Run the installed BMAD agents or custom personas as a conversational room with distinct voices, scenes, and open-cast casting, in session, auto, subagent, or agent-team mode. - Party authoring: Create custom personas and named groups from an idea or distilled from raw customer data, written as sparse TOML overrides via the bmad-customize flow. - Per-party memory: Optional append-only memlogs let a party remember dynamics, callbacks, and outcomes across sessions. - Use Case: Run the built-in Code Review Crew so a security engineer, an adversary, an edge-case hunter, a craftsman, and a pragmatist independently attack your pull request and argue about what actually matters before it ships. ## Quick Start Start party mode and have the installed agents debate the tradeoffs of my proposed caching architecture.
