Claude Skills LLM Council — AI skill for Claude Code
LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review.
How to install Claude Skills LLM Council
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open aiwithremy/claude-skills-llm-council and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Skills LLM Council does
LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review.
Alternatives in AI
- Orkas — Open-source multi-agent AI desktop client — build and command your AI agent team through conversation 1.5k ★
- LLM Council Skill — A skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the impl 416 ★
- Pi Claude CLI — Pi coding agent extension that routes LLM calls through the Claude Code CLI 98 ★
README
LLM Council
A Claude skill that turns one question into five expert opinions, plus a final verdict.
Built by [Ole Lehmann](https://x.com/itsolelehmann). Based on Andrej Karpathy's [LLM Council](https://github.com/karpathy/llm-council) methodology.
Works in **Claude Code** and **Claude Cowork** (claude.ai).
*What's GitHub?*
Think of GitHub as Google Drive, but for code. Instead of sharing photos and files, people use GitHub to share code and snippets like this skill. You're on a GitHub page right now.
What's a skill?
A skill is a small set of instructions you give to your AI. Think of it like a job description for a specific task. Once installed, you can trigger it with a phrase and Claude knows exactly how to handle it.
This particular skill teaches Claude how to run a "council" for you. When you ask a hard question or face a tough decision, Claude spins up 5 different advisors who each think about it from a fundamentally different angle, peer-review each other's takes, and deliver a final synthesized answer.
What it does
You ask one AI a question, you get one answer. That answer might be great. It might be mid. You have no way to tell because you only saw one perspective.
The council fixes this. It runs your question through 5 independent advisors, each thinking from a different angle. They review each other's work. A chairman synthesizes everything into a final recommendation that tells you where the advisors agree, where they clash, and what you should actually do.
When to use it
Good council questions:
- "Should I launch a $97 workshop or a $497 course?"
- "Which of these 3 positioning angles is strongest?"
- "I'm thinking of pivoting from X to Y. Am I crazy?"
- "Here's my landing page copy. What's weak?"
- "Should I hire a VA or build an automation first?"
Bad council questions:
- "What's the capital of France?" (one right answer, no need for perspectives)
- "Write me a tweet" (creation task, not a decision)
- "
Related Skills
LLM Council
A Claude Code skill that pressure-tests any decision through 5 AI advisors with anonymous peer review and a ch
Peer Review
Multi-LLM peer review skill for Claude Code — send plans to Codex and Gemini for structured feedback with cros
Skills Travel Planner
开源 AI 路书生成工具 · Cursor/Claude Agent Skill:简版行程表 → tripData.json → 可交付 HTML/PDF。小红书配图、LLM 润色、飞猪酒店数据。Open-source
Slb
Two-person rule CLI for AI coding agents: peer review and approval required before running potentially destruc
Ensemble
Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group
Gemini Peer Review
Claude Code plugin for AI peer review validation using Google Gemini CLI. Two AI perspectives catch more issue
Related Agents
Council Orchestrator
Coordinates the LLM Council — spawns five parallel advisors, collects blind responses, and synthesizes through
Peer Reviewer Computational
A simulated peer reviewer specializing in computational social science methods — NLP/text-as-data, machine lea
Council Chairman
Chief arbiter of the LLM Council that synthesizes multi-model responses. MUST BE INVOKED after council members