llm-council-skill
🥈SilverA skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the implementation plan to the user
2000Updated 2mo ago
Intermediate30min to implementautomation
Saves ~60 min per use
Quick InstallView Source
git clone https://github.com/gcpdev/llm-council-skill.gitWorks with:
Claude
Overview
About This Skill
LLM Council Skill brings collaborative intelligence to your Claude workflow by querying ChatGPT and Gemini simultaneously for their perspectives on technical decisions. The skill analyzes responses from all three models, identifies valuable insights, and synthesizes a comprehensive implementation plan with attribution to each model's contributions. This approach helps teams avoid blind spots, explore alternatives, and make more robust architectural and design decisions by leveraging the distinct capabilities and training of multiple AI models. Simply ask Claude to "consult the council" followed by your question to activate multi-model brainstorming.
How to Use
Install the skill by uploading the llm-council.skill file to Claude. Set up API keys by copying .env.template to .env and adding your OpenAI and Gemini API keys. Use phrases like "Consult the council: How should I architect..." to trigger multi-model collaboration. Optionally customize which models to use by editing the OPENAI_MODEL and GEMINI_MODEL variables in your .env file.
Use Cases
Architecting microservices systems with input from multiple AI perspectives
Designing database schemas and evaluating tradeoffs between approaches
Planning React application structure and state management strategies
Technical decision-making on infrastructure and system design
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/gcpdev/llm-council-skillRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Act as a coordinator for a brainstorming session with other LLMs (ChatGPT, Gemini) to develop an implementation plan for [PROJECT]. First, gather ideas from each LLM on the best approach to [TASK]. Then, synthesize the most promising ideas into a cohesive plan. Finally, present the final implementation plan to me, including pros and cons of each approach.
Example Output
# Implementation Plan for [PROJECT] ## Brainstorming Session Summary ### ChatGPT's Approach - **Pros**: Focuses on scalability and modularity. - **Cons**: Requires more initial setup time. ### Gemini's Approach - **Pros**: Emphasizes user experience and simplicity. - **Cons**: May need more maintenance over time. ## Synthesized Plan ### Recommended Approach A hybrid of both approaches, combining scalability with a user-friendly interface. ### Implementation Steps 1. **Initial Setup**: Spend 2 weeks on modular architecture. 2. **User Interface**: Allocate 3 weeks for UI/UX design. 3. **Testing**: Plan for 1 week of user testing and feedback. ### Pros and Cons - **Pros**: Balanced approach, scalable, user-friendly. - **Cons**: Slightly longer initial timeline.
Apply to these tools
Browse all tools
Gemini
Google's multimodal AI model and assistant
Claude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan