原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

claude-skills-llm-council Skill

代码仓库 ↗

作者:aiwithremy★ 3,1741 个 skill

安装

能做什么

LLM Council 是一个 Claude Code 技能,可让五位 AI 顾问对您的决策进行分析,并通过同行评审的方式给出结论。

根据作者的说明自动翻译 · 团队尚未核对

  • 连接方式 供 AI 读取的指令文件
  • 账号或密钥 README 和 SKILL.md 中未发现密钥
  • 分类 写代码
作者的原始说明
LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/aiwithremy-claude-skills-llm-council.svg)](https://mcp.popnx.com/en/skills/aiwithremy-claude-skills-llm-council)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

作者:morluto广泛使用↓ 38.9万/周★ 47万今天更新

MCP · 连接服务在你的电脑上运行

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

作者:fallow-rs广泛使用↓ 244.1万/周★ 5387今天更新

MCP · 连接服务在你的电脑上运行

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
claude-skills-llm-council
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
作者aiwithremymorlutomultica-aiGraphify-Labsharry0703
Skill 数11111
GitHub 星标3,174470,165234,528150,695144,727
最近代码更新2026年4月26日2026年11月20日2026年4月20日2026年11月20日2026年11月19日
许可证–MIT–Apache-2.0MIT

aiwithremy 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude CodeClaude (เว็บ/แอป)

依据开发者 README 和 repo 中的文件夹

安装

安全吗?

  • 作者

    GitHub 账号 aiwithremy(个人),已创建 1 年

  • 使用与维护

    ★ 3,174 星 · 代码最近更新 2026年4月26日

  • 有脚本吗?

    没有,都是纯文本文件,由 AI 阅读后照做

  • 会联网吗?

    没有脚本,所以不会自己联网

  • 会修改整台电脑的设置吗?

    没有发现 hook 或写入电脑设置的操作

根据仓库 commit 55ee36e 中的文件自动检查(只读取文件,没有运行任何内容)。这不是安全保证,请自己阅读后再决定

第一步:你用哪个 AI?

选择你用的应用,本页只显示该应用的安装方法

方式 1上传到 claude.ai(网页和应用)

  1. 从 GitHub 下载

    这个 Skill 没有说明许可证,所以我们不在网站上提供 ZIP。请从 GitHub 下载并自己整理文件夹,或者用上面的"让 AI 帮你安装",更简单

    从 GitHub 下载(整个仓库)↗

    解压后,只把 claude-skills-llm-council 文件夹重新压缩。ZIP 的最上层必须是包含 SKILL.md 的 llm-council 文件夹,不能直接放散乱的文件

  2. 打开 claude.ai 的 Skills 页面并上传

    +Create skillUpload a skill选择文件 llm-council.zip

    打开 claude.ai/customize/skills ↗

  3. 看不到 Upload 按钮?请先开启创建文件的权限

    SettingsCapabilitiesCode execution and file creation

    Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free

Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)

Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)

Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com

方式 1让 Claude Code 帮你安装

复制这句话,粘贴到 Claude Code 的对话中

安装到哪里
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) for all my projects, at ~/.claude/skills/llm-council. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) into the project this chat is open in (at .claude/skills/llm-council). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径

AI 会先说明要做什么,每一步都会征求你的同意

重新打开 Claude Code,输入 /claude-skills-llm-council,或直接提出相关任务,Claude 会自动选用

Checked against official docs 2026年11月12日 · Source: code.claude.com

适合使用 Terminal 的人

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.claude/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    git clone --depth 1 https://github.com/aiwithremy/claude-skills-llm-council.git /tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e/.' ~/.claude/skills/claude-skills-llm-council
  3. 重新打开 Claude Code,输入 /claude-skills-llm-council,或直接提出相关任务,Claude 会自动选用

自己安装的 Skill 可用于 ChatGPT 桌面应用、Codex CLI 和 IDE 中的 Codex 扩展 · 网页版和手机版 ChatGPT 不能使用自己安装的 Skill,只能使用目录中插件自带的 Skill

ChatGPT 桌面应用

ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill

方式 1让 ChatGPT 帮你安装

在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中

安装到哪里
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) for all my projects, at ~/.agents/skills/llm-council. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) into the project this chat is open in (at .agents/skills/llm-council). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

AI 在安装前一定会先告诉你路径

AI 会先说明要做什么,每一步都会征求你的同意

方式 2自己放入文件夹

把 llm-council 文件夹放到 ~/.agents/skills/llm-council

~ 是你的主文件夹($HOME)

适合使用 Terminal 的人

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.agents/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    git clone --depth 1 https://github.com/aiwithremy/claude-skills-llm-council.git /tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e/.' ~/.agents/skills/claude-skills-llm-council

安装之后

  • ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
  • 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
  • Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

网页版和手机版 ChatGPT

不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill

想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

方式 1让 Codex 帮你安装

复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展

安装到哪里
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) for all my projects, at ~/.agents/skills/llm-council. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) into the project this chat is open in (at .agents/skills/llm-council). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径

AI 会先说明要做什么,每一步都会征求你的同意

Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

适合使用 Terminal 的人

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.agents/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    git clone --depth 1 https://github.com/aiwithremy/claude-skills-llm-council.git /tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e/.' ~/.agents/skills/claude-skills-llm-council
  3. 重新打开 Codex 并提出相关任务,Codex 会列出这个 skill

方式 1让 Cursor 帮你安装

复制这句话,粘贴到 Cursor 的对话中

安装到哪里
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) for all my projects, at ~/.cursor/skills/llm-council. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill llm-council from https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) into the project this chat is open in (at .cursor/skills/llm-council). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径

AI 会先说明要做什么,每一步都会征求你的同意

在 Cursor 的 Agent 聊天中输入 / 并选择 claude-skills-llm-council

Checked against official docs 2026年11月12日 · Source: cursor.com

适合使用 Terminal 的人

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.cursor/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    git clone --depth 1 https://github.com/aiwithremy/claude-skills-llm-council.git /tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-aiwithremy-claude-skills-llm-council-55ee36e/.' ~/.cursor/skills/claude-skills-llm-council
  3. 在 Cursor 的 Agent 聊天中输入 / 并选择 claude-skills-llm-council

方式 1让 AI 帮你安装

适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · 复制这句话,粘贴到应用的对话中

安装到哪里
请帮我从 https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) 安装名为 llm-council 的 Skill,供我所有项目使用,放在 ~/.claude/skills/llm-council(Codex 用 ~/.agents/skills/llm-council,Cursor 用 ~/.cursor/skills/llm-council)。请先把所有文件给我看,告诉我有没有脚本或会不会修改电脑设置,再告诉我要安装的完整路径,等我同意后再继续。
请帮我从 https://github.com/aiwithremy/claude-skills-llm-council(commit 55ee36e) 安装名为 llm-council 的 Skill,安装到这个对话当前打开的项目中(放在 .claude/skills/llm-council;Codex 用 .agents/skills/llm-council,Cursor 用 .cursor/skills/llm-council)。请先把所有文件给我看,告诉我有没有脚本或会不会修改电脑设置,再告诉我项目名称和要安装的完整路径,等我同意后再继续。

如果只用于一个项目,请粘贴到在该项目文件夹中打开的对话里 · AI 在安装前一定会先告诉你路径

AI 会先说明要做什么,每一步都会征求你的同意

Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com

适合使用 Terminal 的人

其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。

在 GitHub 上查看 ↗

已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹

✓ 命令已检查 2026年11月19日

查看原始 SKILL.md

以下文字来自开发者的 repo,不是 PopNx MCP 的指令

显示前 8,000 个字符 · 在 GitHub 打开完整文件

---

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'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles."

---


# 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.


---


## when to run the council


The council is for questions where being wrong is expensive.


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)

- "Summarize this article" (processing task, not judgment)


The council shines when there's genuine uncertainty and the cost of a bad call is high. If you already know the answer and just want validation, the council will likely tell you things you don't want to hear. That's the point.


---


## the five advisors


Each advisor thinks from a different angle. They're not job titles or personas. They're thinking styles that naturally create tension with each other.


### 1. The Contrarian

Actively looks for what's wrong, what's missing, what will fail. Assumes the idea has a fatal flaw and tries to find it. If everything looks solid, digs deeper. The Contrarian is not a pessimist. They're the friend who saves you from a bad deal by asking the questions you're avoiding.


### 2. The First Principles Thinker

Ignores the surface-level question and asks "what are we actually trying to solve here?" Strips away assumptions. Rebuilds the problem from the ground up. Sometimes the most valuable council output is the First Principles Thinker saying "you're asking the wrong question entirely."


### 3. The Expansionist

Looks for upside everyone else is missing. What could be bigger? What adjacent opportunity is hiding? What's being undervalued? The Expansionist doesn't care about risk (that's the Contrarian's job). They care about what happens if this works even better than expected.


### 4. The Outsider

Has zero context about you, your field, or your history. Responds purely to what's in front of them. This is the most underrated advisor. Experts develop blind spots. The Outsider catches the curse of knowledge: things that are obvious to you but confusing to everyone else.


### 5. The Executor

Only cares about one thing: can this actually be done, and what's the fastest path to doing it? Ignores theory, strategy, and big-picture thinking. The Executor looks at every idea through the lens of "OK but what do you do Monday morning?" If an idea sounds brilliant but has no clear first step, the Executor will say so.


**Why these five:** They create three natural tensions. Contrarian vs Expansionist (downside vs upside). First Principles vs Executor (rethink everything vs just do it). The Outsider sits in the middle keeping everyone honest by seeing what fresh eyes see.


---


## how a council session works


### step 1: frame the question (with context enrichment)


When the user says "council this" (or any trigger phrase), do two things before framing:


**A. Scan the workspace for context.** The user's question is often just the tip of the iceberg. Their Claude setup likely contains files that would dramatically improve the council's output. Before framing, quickly scan for and read any relevant context files:


- `CLAUDE.md` or `claude.md` in the project root or workspace (business context, preferences, constraints)

- Any `memory/` folder (audience profiles, voice docs, business details, past decisions)

- Any files the user explicitly referenced or attached

- Recent council transcripts in this folder (to avoid re-counciling the same ground)

- Any other context files that seem relevant to the specific question (e.g., if they're asking about pricing, look for revenue data, past launch results, audience research)


Use `Glob` and quick `Read` calls to find these. Don't spend more than 30 seconds on this. You're looking for the 2-3 files that would give advisors the context they need to give specific, grounded advice instead of generic takes.


**B. Frame the question.** Take the user's raw question AND the enriched context and reframe it as a clear, neutral prompt that all five advisors will receive. The framed question should include:


1. The core decision or question

2. Key context from the user's message

3. Key context from workspace files (business stage, audience, constraints, past results, relevant numbers)

4. What's at stake (why this decision matters)


Don't add your own opinion. Don't steer it. But DO make sure each advisor has enough context to give a specific, grounded answer rather than generic advice.


If the question is too vague ("council this: my business"), ask one clarifying question. Just one. Then proceed.


Save the framed question for the transcript.


### step 2: convene the council (5 sub-agents in parallel)


Spawn all 5 advisors simultaneously as sub-agents. Each gets:


1. Their advisor identity and thinking style (from the descriptions above)

2. The framed question

3. A clear instruction: respond independently. Do not hedge. Do not try to be balanced. Lean fully into your assigned perspective. If you see a fatal flaw, say it. If you see massive upside, say it. Your job is to represent your angle as strongly as possible. The synthesis comes later.


Each advisor should produce a response of 150-300 words. Long enough to be substantive, short enough to be scannable.


**Sub-agent prompt template:**


```

You are [Advisor Name] on an LLM Council.


Your thinking style: [advisor description from above]


A user has brought this question to the council:


---

[framed question]

---


Respond from your perspective. Be direct and specific. Don't hedge or try to be balanced. Lean fully into your assigned angle. The other advisors will cover the angles you're not covering.


Keep your response between 150-300 words. No preamble. Go straight into your analysis.

```


### step 3: peer review (5 sub-agents in parallel)


This is the step that makes the council more than just "ask 5 times." It's the core of Karpathy's insight.


Collect all 5 advisor responses. Anonymize them as Response A through E (randomize which advisor maps to which letter so there's no positional bi

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
3,174
开发者
aiwithremy
许可证
未注明许可证 此 repo 未注明许可证,默认作者保留所有权利;转发或商用前请先询问作者。
最近代码更新
2026年4月26日
repo 中的 SKILL.md 文件(含译本和模板)
1