LLM Council Skill

A Claude skill that enables collaborative brainstorming with multiple AI models (ChatGPT and Gemini) before presenting implementation plans.

What It Does

When you ask Claude to consult with other AI models, Claude will:

1. Query both ChatGPT and Gemini for their perspectives

2. Analyze their responses and identify valuable insights

3. Synthesize a comprehensive implementation plan incorporating ideas from all three models

4. Present the final plan with attribution to each model's contributions

How to Use

Simply ask Claude to consult with other AI models using phrases like:

• "Consult the council: How should I architect a microservices system?"
• "Ask ChatGPT and Gemini what they think about my database design"
• "Get perspectives from other AI models on this technical decision"
• "Consult with other LLMs: What's the best approach for..."

Example:

User: Consult the council: How should I structure my React app for scalability?

Claude will then:
- Query ChatGPT and Gemini about React architecture
- Analyze their suggestions on components, state management, and organization
- Present a synthesized plan incorporating insights from all three models

Installation

1. Install the skill in Claude by uploading the llm-council.skill file
2. Set up API keys and model preferences:
   • Copy .env.template to create a .env file in your working directory
   • Add your OpenAI API key (get it at https://platform.openai.com/api-keys)
   • Add your Gemini API key (get it at https://aistudio.google.com/app/apikey)
   • Optionally customize which models to use (see Model Options below)

Model Options

Default Models (Fast & Cost-Effective):

• ChatGPT: gpt-5-nano-2025-08-07 (highly cost-effective)
• Gemini: gemini-3-flash-preview (balanced speed and intelligence)

Upgrade Options for Better Collaboration:

OpenAI models (ordered by capability):

• gpt-5-nano - Fastest, cheapest version of GPT-5. It's great for summarization and classification tasks. (Default)
• gpt-5-mini - Balanced cost and quality
• gpt-5.2 - Smart model, capable of most tasks
• gpt-5.2-pro - State-of-the-art for professional knowledge work

Gemini models (ordered by capability):

• gemini-2.5-flash-lite - Ultra-fast, optimized for throughput
• gemini-2.5-flash - Best price-performance
• gemini-3-flash-preview - Balanced (default)
• gemini-3-pro-preview - Most intelligent, best reasoning

How to Configure: Add these lines to your .env file:

OPENAI_MODEL=gpt-5-nano
GEMINI_MODEL=gemini-3-flash-preview

Recommended Configurations:

• Balanced: Defaults (gpt-5-nano + gemini-3-flash-preview)
• Budget: gpt-5-nano + gemini-2.5-flash
• High Quality: gpt-5 + gemini-3-flash-preview
• Premium Reasoning: gpt-5.2 + gemini-3-pro-preview
• Professional Work: gpt-5.2-pro + gemini-3-pro-preview

Benefits

• Diverse perspectives: Get insights from three different AI models with different training and capabilities
• Better decisions: Identify potential issues or alternatives you might have missed with a single model
• Comprehensive planning: Combine strengths of multiple models for more robust implementation plans

API Costs

Both OpenAI and Gemini APIs have usage costs that vary significantly by model:

OpenAI Cost Tiers (approximate, check current pricing):