Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

LLM Council

Consults ChatGPT and Gemini in parallel and merges their views with Claude's own into a single attributed implementation plan.

AutomationIntermediate★ 405⑂ 56AI score 9/10Last updated: Jan 8, 2026

What it does

  • Triggers when you explicitly ask to "consult the council", "ask other models", or get perspectives from other AIs before a plan.
  • Runs the bundled scripts/query_llms.py to send your prompt to the OpenAI (ChatGPT) and Google Gemini APIs.
  • Analyzes each response, blends the best ideas with Claude's own analysis, and presents one implementation plan with inline attribution plus a per-model contribution summary.
  • Handles missing keys and failed API calls gracefully, telling you which perspective is unavailable.

Who it's for

  • Engineers and architects who don't want a single model's opinion driving a big design decision.
  • Anyone doing technology trade-off reviews (queueing, storage, refactor strategy).
  • Users who already hold paid OpenAI and Gemini API keys and accept per-call costs.

Example uses

  1. "Consult the council: how should I architect a real-time data pipeline for IoT sensors?" — ChatGPT proposes Kafka, Gemini raises edge computing, Claude synthesizes the final architecture.
  2. "Ask ChatGPT and Gemini about my payment module refactor plan" — you get a step-by-step plan cross-checked by three models.
  3. Set OPENAI_MODEL=gpt-5.2 in .env to escalate to a stronger model only for hard problems.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/gcpdev/llm-council-skill/HEAD/llm-council/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the llm-council folder from the GitHub repo gcpdev/llm-council-skill into my ~/.claude/skills/llm-council/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/gcpdev/llm-council-skill.git /tmp/llm-council-skill && mkdir -p ~/.claude/skills && cp -r /tmp/llm-council-skill/llm-council ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Clone the repo: git clone https://github.com/gcpdev/llm-council-skill.git
  2. Copy the skill folder into place: mkdir -p ~/.claude/skills && cp -r llm-council-skill/llm-council ~/.claude/skills/
  3. Make sure Python 3 and the needed SDKs are installed; if the repo ships a requirements.txt, run pip install -r requirements.txt.
  4. Create a .env file in your working directory with OPENAI_API_KEY=sk-... and GEMINI_API_KEY=...; optionally set OPENAI_MODEL and GEMINI_MODEL.
  5. Add .env to .gitignore so your keys never get committed.
  6. Restart Claude Code and test with: "Consult the council: [your question]".
View source on GitHub ↗License: MIT