Party Mode Orchestration

Party Mode Orchestration Skill

This skill provides guidance for orchestrating multi-agent conversations where multiple AI personas collaborate to solve problems.

When to Use This Skill

• User starts a party mode session via /bmad-party-mode
• User asks questions requiring multiple expert perspectives
• User wants to brainstorm with a team of specialists
• User needs cross-functional analysis (technical + business + design)

Core Concepts

Agent Selection Algorithm

For each user message, select 2-3 agents based on:

1. Keyword matching: Match topic keywords to agent expertise
2. Role balancing: Mix technical, business, and design perspectives
3. Context awareness: Consider previous contributions
4. Rotation fairness: Ensure all agents get opportunities

Reference: $CLAUDE_PLUGIN_ROOT/skills/party-mode-orchestration/references/agent-selection.md

Character Consistency

Each agent has defined personality traits that MUST be maintained:

• communicationStyle: How they express themselves
• principles: What guides their decisions
• role: Their area of expertise
• partyModeRole: Their specific function in discussions

Reference: $CLAUDE_PLUGIN_ROOT/skills/party-mode-orchestration/references/conversation-rules.md

Knowledge Extension

Agents with knowledge configuration can dynamically load additional context:

{
  "knowledge": {
    "type": "dynamic",
    "indexPath": "knowledge/{agent}/index.json",
    "basePath": "knowledge/{agent}/"
  }
}

This allows specialized agents (like Murat/Tea) to access framework-specific guidance.

Agent Quick Reference

Topic-to-Agent Mapping

Conversation Flow Management

Turn Structure

1. User provides input
2. Analyze topic and select 2-3 agents
3. Load selected agents' full profiles
4. Generate in-character responses
5. Enable cross-references between agents
6. Wait for user's next input

Exit Handling

Graceful exit when user indicates session end:

1. Select 2-3 agents who contributed most
2. Generate personality-appropriate farewells
3. Summarize session highlights
4. Display closing message

Best Practices

• Variety: Don't repeat the same agent pairing consecutively
• Depth: Allow agents to build on each other's points
• Conflict: Healthy disagreement adds value (e.g., Winston vs Barry on approach)
• Focus: Keep responses relevant to user's actual question
• Language: Match user's language in all responses