council

Coordinate parallel consultations across Claude, Codex, and Gemini for structured comparison.

24|6|Updated Dec 19, 2025
One-click install
npx skills add https://github.com/johnlindquist/claude --skill council
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: council
Source: https://github.com/johnlindquist/claude/tree/main/skills/council
Command: npx skills add https://github.com/johnlindquist/claude --skill council

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @anthropic-ai/claude-cli, @openai/codex-cli, google-generativeai, and includes scripts (resource) components.

What problem does it solve?

This Skill provides diverse AI viewpoints on complex problems, helping you compare approaches and find consensus among different models.

Core Features & Use Cases

  • Multi-Agent Consultation: Query Claude, Gemini, and Codex in parallel for comprehensive analysis.

Quick Start

Ask the AI council for perspectives on implementing microservices vs monolith architecture.

Frequently Asked Questions about council

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

FAQPage Schema
How do I get multiple AI perspectives on a single question?

Multi-agent consultation queries Claude, Codex, and Gemini in parallel to gather diverse perspectives on one question. Each model analyzes the problem independently, then results are labeled and compared side-by-side so you can evaluate different approaches and reach consensus.

What's the best way to decide between microservices and monolithic architecture?

Multi-agent consultation coordinates perspectives from Claude, Codex, and Gemini on architecture trade-offs. Each model provides structured analysis of scalability, complexity, and maintenance implications, helping you synthesize consensus across viewpoints before committing to a design.

Can I use multiple AI models together for code reviews?

Yes, this Skill orchestrates Claude, Codex, and Gemini for parallel code review consultation. Role-based prompts structure each model's analysis, temporary storage collects responses, and results are labeled for comparison so you evaluate feedback across multiple perspectives.

How does multi-agent consultation help with debugging complex problems?

Parallel agent invocation sends your debugging question to Claude, Codex, and Gemini simultaneously. Each model analyzes the issue independently, responses are labeled and stored temporarily, then structured comparison reveals different root cause hypotheses and solution approaches.

Do I need to configure Claude, Codex, and Gemini separately before using this?

The Skill requires dependencies on @anthropic-ai/claude-cli, @openai/codex-cli, and google-generativeai. These must be installed and accessible in your environment; the Skill handles parallel orchestration and response labeling once dependencies are in place.