council

Coordinates three AI agents to jointly evaluate complex questions and produce cited advisory answers.

437|45|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/ZaxbyHub/opencode-swarm --skill council-zaxbyhub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: council
Source: https://github.com/ZaxbyHub/opencode-swarm/tree/main/.opencode/skills/council
Command: npx skills add https://github.com/ZaxbyHub/opencode-swarm --skill council-zaxbyhub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Single AI responses to complex questions often suffer from unstated biases, knowledge gaps, and lack of diverse perspective, leading to incomplete or unbalanced advice. This Skill eliminates that gap by coordinating a specialized council of three distinct AI agents to deliberate on your question and produce a balanced, evidence-backed advisory answer.

Core Features & Use Cases

  • Parallel Multi-Agent Deliberation: Dispatches a generalist, skeptic, and domain expert agent to analyze your question from complementary angles simultaneously.
  • Grounded Research Integration: Runs pre-deliberation web research to ensure all advice is rooted in current, verified sources for time-sensitive queries.
  • Transparent Disagreement Handling: Automatically reconciles conflicting positions between agents and clearly surfaces any remaining disagreements in the final output, rather than hiding conflicting views.
  • Use Case: For example, when evaluating whether to adopt a new frontend framework for your team, use this Skill to get balanced input on performance, maintainability, and ecosystem fit from multiple expert perspectives.

Quick Start

Use the council skill to get a balanced, evidence-backed advisory answer to your complex question about the tradeoffs of adopting a microservices architecture for your SaaS product.

Frequently Asked Questions about council

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

FAQPage Schema
How do I get multi-expert advisory consensus for complex technical tradeoff analysis?

Multi-expert advisory consensus is achieved by dispatching a generalist, skeptic, and domain expert agent to analyze technical tradeoffs in parallel. This multi-agent deliberation surfaces transparent disagreement reconciliation and source-cited outputs for a balanced consensus response.

What is multi-agent deliberation for spec review?

Multi-agent deliberation for spec review coordinates isolated AI agents to evaluate specifications from complementary angles simultaneously. The council protocol ensures transparent advisory consensus by automatically reconciling conflicting positions and surfacing remaining disagreements in the final output.

How do I eliminate unbalanced single-perspective advice on complex software engineering questions?

Unbalanced single-perspective advice is eliminated by running parallel multi-agent deliberation across specialized agents. This coordinates a generalist, skeptic, and domain expert to produce consensus-weighted advisory responses with isolated agent dispatch and source-cited evidence.

Can I use web research integration for time-sensitive technical tradeoff evaluation?

Web research integration supports time-sensitive technical tradeoff evaluation through pre-deliberation web research. This grounds the multi-agent deliberation process in current, verified sources before the advisory consensus is generated.

Does multi-agent deliberation work for research synthesis and advisory consensus?

Multi-agent deliberation works for research synthesis by applying parallel dispatch to evaluate evidence from complementary angles. The council protocol generates evidence-backed advisory consensus with transparent disagreement handling and source-cited outputs.

When should I not use a multi-agent council protocol for technical advice?

The multi-agent council protocol should not be used for simple queries lacking complex technical tradeoffs or multi-perspective dimensions. It requires advisory use cases involving specification review, research synthesis, or technical tradeoff evaluation to justify parallel multi-agent deliberation.