roundtable-debate

Orchestrate multi-agent structured debates with persona dispatch and artifact channels.

1|Updated May 21, 2026
One-click install
npx skills add https://github.com/hiddink-ai/hiddink-harness --skill roundtable-debate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: roundtable-debate
Source: https://github.com/hiddink-ai/hiddink-harness/tree/main/templates/skills/roundtable-debate
Command: npx skills add https://github.com/hiddink-ai/hiddink-harness --skill roundtable-debate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill prevents cognitive biases like anchoring and groupthink in multi-agent systems by enforcing independent analysis and structured adversarial debate.

Core Features & Use Cases

  • Anti-Groupthink Protocols: Forces independent parallel analysis before agents share opinions to prevent anchoring.
  • Devil's Advocate Integration: Dedicated persona slot ensures critical perspectives are always represented.
  • Use Case: Use this when making high-stakes architectural decisions or evaluating design tradeoffs where consensus-seeking behavior would lead to suboptimal outcomes.

Quick Start

Invoke the roundtable-debate skill to analyze the proposed system architecture with four specialized personas.

Frequently Asked Questions about roundtable-debate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent groupthink during multi-agent architectural reviews?

To prevent groupthink during multi-agent architectural reviews, use a structured debate skill that enforces independent parallel analysis before agents share opinions, ensuring divergent perspectives are preserved.

What is the best way to evaluate design tradeoffs without anchoring bias in AI agents?

Evaluating design tradeoffs without anchoring bias requires an anti-groupthink protocol that forces agents into independent analysis before opinion sharing, integrating a dedicated devil's advocate persona for critical perspectives.

Can I use structured debate for contested specification risk assessment?

Yes, you can use structured multi-agent debate for contested specification risk assessment by dispatching specialized personas to rigorously evaluate contested points and mitigate consensus-seeking behavior.

How does a multi-agent debate orchestrator manage discussion cycles?

A multi-agent debate orchestrator manages discussion cycles by handling persona dispatch and artifact channel communication, applying a two-round hard cap on discussion cycles to strictly bound the debate duration.

When should I not use a devil's advocate approach for decision-making?

You should not use a devil's advocate approach for straightforward decisions lacking complex tradeoffs, as the overhead of orchestrating a multi-agent structured debate is designed for high-stakes architectural scenarios.

Do I need an orchestrator to manage multi-agent debate personas?

Yes, you need an orchestrator to manage multi-agent debate personas, as the system requires an orchestrator to handle persona dispatch, artifact channel communication, and enforce the two-round discussion cap.