What problem does it solve? Single-agent conversations tend toward one perspective and quick agreement. This Skill runs a moderated roundtable where multiple distinct personas — installed BMAD agents or user-defined characters — debate, clash, and react to each other, surfacing angles no single voice would reach. ## Core Features & Use Cases - Multi-persona roundtables: Run lively group discussions with distinct voices, rivalries, and callbacks, in session, auto, subagent, or agent-team execution modes. - Custom party authoring: Create personas and named groups (code review crews, focus-group panels, open-cast themed rooms) via TOML customization, including distilling customer data into focus-group personas. - Per-party memory: Optional append-only memlogs let a party remember past sessions, alliances, and running jokes 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 so each lens attacks the change 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.
