Council

Generate multi-perspective debate transcripts with round-based expert deliberation.

1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/davdunc/pai-framework --skill council-davdunc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Council
Source: https://github.com/davdunc/pai-framework/tree/main/skills/Council
Command: npx skills add https://github.com/davdunc/pai-framework --skill council-davdunc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Council skill helps you make better decisions by generating a round-by-round, multi-perspective debate that surfaces real trade-offs and disagreements instead of generic opinions.

Core Features & Use Cases

  • Custom-composed council agents: Builds a small set of topic-specific agents using the Agents skill’s ComposeAgent tool (never built-in agent types).
  • Structured debate workflows: Runs a full 3-round process (positions → responses → synthesis) or a 1-round quick consensus check.
  • Engagement-focused outputs: Forces agents to reference each other’s arguments in later rounds and produces a convergence + remaining-disagreements summary.
  • Best for decision-quality deliberation: Useful when evaluating options, weighing pros/cons, or asking “what would experts say?”

Quick Start

Ask your AI: Run a Council debate on "Should we use WebSockets or SSE for our real-time updates?" and return a full transcript with synthesis.

Frequently Asked Questions about Council

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

FAQPage Schema
How do I generate a multi-agent debate transcript for decision-making?

Multi-perspective debate transcripts improve decision quality by structuring multi-agent deliberation into rounds of positions, responses, and synthesis. This process surfaces genuine disagreements and trade-offs instead of generic opinions for option evaluation.

How do I run a consensus check or pros-and-cons weighing using multiple agents?

You can run a consensus check or pros-and-cons weighing by initiating a 1-round quick consensus workflow. The skill composes a small set of custom agents to evaluate options and returns a structured summary of convergence and remaining disagreements.

Can I use built-in agent types for workflow orchestration in this skill?

No, you cannot use built-in agent types. The skill requires custom agent composition via the ComposeAgent tool to ensure that all deliberation agents are specifically tailored to the topic being evaluated.

What is the structured debate workflow process for option evaluation?

The structured debate workflow is a 3-round process consisting of positions, responses, and synthesis. Agents must reference each other’s arguments in later rounds, culminating in an engagement-focused output that summarizes convergence and remaining disagreements.

What are the limitations of using automated consensus checks for complex decisions?

A limitation is that the consensus check is only as effective as the custom agent composition. While it excels at revealing trade-offs and structuring disagreements, it requires predefined transcript context files and does not make final decisions automatically.