LLM Council skill
A skill that runs your question past five advisors with different lenses, has them peer-review each other anonymously, then a chairman delivers the final verdic
- 3,026 ★ on the repository
- Last commit
Extended access
Why this level
- Scans the workspace and reads project context files
- Spawns several sub-agents per query and uses more tokens
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/llm-councilDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Scans the workspace and reads project context files
- Spawns several sub-agents per query and uses more tokens
This is third-party code. Review the repository files before installing.
What it does
The skill turns one question into a five-angle review. On a trigger phrase the agent gathers context from workspace files, writes a neutral framing and spawns five advisors as parallel sub-agents: a contrarian hunts for flaws, a first-principles thinker reframes the task, an expansionist looks at the upside, an outsider reacts without your context, an executor checks feasibility. Their answers are anonymized and the advisors peer-review each other. A chairman then produces a structured verdict: where the council agrees, where it clashes, which blind spots surfaced, a recommendation and a first step. The method follows Andrej Karpathy's LLM Council idea, but sub-agents with different thinking lenses stand in for different models.
Who it is for. For founders, product managers and marketers who need to pressure-test a high-stakes decision from several angles at once.
Good fit when
- You face a fork with several options and a costly mistake
- You want positioning, pricing or a launch plan pressure-tested for weak spots
- You want a debate of perspectives with a final call, not a single answer
Not a fit when
- The question has one correct answer or is a factual lookup
- You need the work done, such as writing or summarizing, not a decision reviewed
Example request
Council this: launch a 97 dollar workshop or a 497 dollar courseLimitations
The skill gives judgment, not fact-checking: the verdict is only as good as the context you provide. It spawns several sub-agents per query, so it uses more tokens than a plain answer. It works where the agent can create sub-agents and read project files, such as Claude Code and claude.ai. The repository states no license.
How to disable. Remove the llm-council skill folder from the agent's skills directory, for example ~/.claude/skills/.
FAQ
Are these different models?
No. All five advisors are sub-agents inside one agent, each assigned a thinking angle. Different models, as in Karpathy's original, are not needed here.
Why anonymous review?
Responses are relabeled A to E so reviewers judge the content rather than the author's name and thinking style.
Discussion
No questions or reviews yet.
Related
SkillsThe /court skill puts an idea on trial: a prosecutor, a defense, 12 jurors and a judge instead of Claude’s usual agreement.
A skill that cross-examines a plan before work starts: numbered questions in rounds with a recommended answer and no changes until you confirm
A Claude Code skill that tests a business idea with a four-agent council and rules: build, fix first or kill.
LLM Wiki Manager keeps a personal Markdown wiki through an agent: it ingests sources, links pages and answers with citations
A Claude Code template that builds a knowledge base from articles and PDFs: five newsroom roles and contradiction checks.
Ten skills for Claude Code and Codex: a router diagnoses a stuck idea and runs the matching lateral thinking technique
README in short
The README explains that the skill runs a question through five independent advisors who peer-review each other anonymously, after which a chairman gives the final answer. It suits high-stakes decisions and is not meant for simple one-answer questions or creative tasks. You install it by asking the agent to fetch SKILL.md from the repository, or by downloading the file into the skills directory. It triggers on phrases like 'council this' or 'pressure-test this'. The method is adapted from Andrej Karpathy's LLM Council; the skill is by Ole Lehmann.
README badge
Original SKILL.md
--- name: llm-council description: "Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'." --- # LLM Council 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 fundamentally different angle. Then they review each other's work. Then a chairman synthesizes everything into a final recommendation that tells you where the advisors agree, where they clash, and what you should actually do. This is adapted from Andrej Karpathy's LLM Council. He dispatches queries to multiple models, has them peer-review each other anonymously, then a chairman produces the final answer. We do the same thing inside Claude using sub-agents with different thinking lenses instead of different models.