What problem does it solve? Getting genuinely independent perspectives from an AI is hard: a single model voicing multiple viewpoints tends to blend them into bland consensus. This Skill runs a structured roundtable where distinct personas — installed BMAD agents or custom characters — argue, clash, and build on each other like real people, surfacing angles no single voice would reach. ## Core Features & Use Cases - Multi-persona roundtables: Run lively group discussions with installed agents or custom personas, each with a distinct voice, agenda, and quirks, in session, auto, subagent, or agent-team execution modes. - Custom party authoring: Create themed casts, one-off personas, or focus-group panels distilled from customer data, saved as TOML overrides with named groups, scenes, and per-party memory. - Persistent party memory: Append-only per-party memlogs let a room remember past sessions, so alliances, grudges, and callbacks carry forward across conversations. - Use Case: Run the built-in Code Review Crew — a security engineer, an adversary, an edge-case hunter, a craftsman, and a pragmatist — against a pull request in subagent mode so each lens reviews independently before they argue about what actually matters. ## Quick Start Ask the AI to start party mode with the Code Review Crew to review my latest changes and let the personas debate which issues actually matter.
