What problem does it solve? Getting genuinely diverse perspectives from an AI is hard because a single voice tends to converge on safe consensus. This Skill runs a roundtable where multiple distinct personas argue, clash, and build on each other, surfacing angles no single voice would reach. ## Core Features & Use Cases - Multi-Persona Roundtables: Runs lively group discussions between installed BMAD agents or custom personas, with four execution modes (session, auto, subagent, agent-team) controlling whether personas are voiced inline or backed by independent agents. - Custom Party Authoring: Guides creation of custom personas and named party groups from ideas or raw customer data, including AI focus-group panels distilled from spreadsheets or interview notes. - Persistent Party Memory: Keeps an append-only per-party memlog so rooms remember past sessions, alliances, and callbacks across conversations. - Use Case: Run the built-in Code Review Crew to have a security engineer, an adversary, an edge-case hunter, a craftsman, and a pragmatist attack your code from independent lenses and argue about what actually matters before you ship. ## Quick Start Ask the AI to start party mode so the installed agents can debate your topic in a roundtable discussion.