skills.rest
seungwonme
seungwonmeCOMMUNITY
Explore all skills by this author →
Website𝕏@aidensystemsGitHub

agent-council

Gather and synthesize opinions from multiple AI agents into a final recommendation.

Updated Aug 27, 2026
Search Tags:#automation#cli#multi-agent#orchestration#synthesis#council#decision-support
One-click install
npx skills add https://github.com/seungwonme/.claude --skill agent-council-seungwonme
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-council
Source: https://github.com/seungwonme/.claude/tree/main/skills/agent-council
Command: npx skills add https://github.com/seungwonme/.claude --skill agent-council-seungwonme

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Agent Council helps teams gather diverse AI opinions from multiple CLIs (Codex, Gemini, Claude Code, etc.) and synthesize a final, actionable recommendation, saving time and reducing bias in decision making.

Core Features & Use Cases

  • Gather parallel opinions from installed AI agents
  • Synthesize a final recommendation using a configurable chairman
  • Supports script-driven execution and host UI integration for plan/todo updates
  • Use case: when evaluating competing options, designs, or architecture with input from multiple AI agents

Quick Start

Summon the council and ask Codex, Gemini, and Claude for their opinions on the best approach.

Frequently Asked Questions about agent-council

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

FAQPage Schema
How do I get opinions from multiple AI agents and synthesize a final recommendation?▼

You can synthesize multiple AI opinions by running parallel execution across installed CLIs like Codex and Gemini, then using a configurable chairman to aggregate diverse perspectives into a final recommendation. This reduces bias and saves time when evaluating competing options or designs.

What is multi-agent orchestration for decision support and when do I need it?▼

Multi-agent orchestration gathers diverse AI perspectives to help teams make informed decisions. You need it when evaluating competing architecture or design options and want to synthesize input from different models to reduce bias before committing.

Do I need Node.js and specific CLIs installed to run multi-agent orchestration?▼

Yes, multi-agent orchestration requires Node.js and installed AI CLIs such as Claude Code, Codex CLI, and Gemini. You also need a council.config.yaml file to configure the agents and the chairman for parallel execution.

What's the best way to evaluate competing architecture options using multiple AI models?▼

The best way is using a multi-agent council that gathers parallel opinions from installed CLIs like Codex and Gemini. A chairman synthesizes these diverse AI perspectives into a single actionable recommendation, reducing individual model bias.

How does a chairman synthesize opinions from different AI agents?▼

The chairman synthesizes opinions by aggregating parallel responses from multiple AI agents configured in a YAML file. It processes diverse outputs from CLIs like Claude Code and Codex to produce a final, unified recommendation.

Can I use a YAML configuration file to manage my multi-agent council setup?▼

Yes, a YAML configuration file is required to manage your multi-agent council setup. The council.config.yaml file defines the installed CLIs, agent roles, and chairman settings needed to orchestrate parallel execution and synthesis.

Related Skills

Explore More Software Engineering Skills→
hhopkins95hhopkins95
2

Backend Setup

Configure a Node.js agent-runtime backend with REST and WebSocket servers.

Community
Advanced
mkalhitti-cloudmkalhitti-cloud
2

antigravity-core

Coordinate multiple AI perspectives into structured decision trees and synthesized outputs.

Community
Basic
basilisk-labsbasilisk-labs
72

agentplane

Plan, execute, and verify AI agent tasks with git-native evidence.

Official
Advanced
devalexanderdazadevalexanderdaza

bmad-party-mode

Orchestrate multi-agent roundtable discussions by spawning independent BMAD subagent processes.

Community
Intermediate