REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
A skill to claude code that enables brainstorming with other LLMs (ChatGPT, Gemini) before presenting the implementation plan to the user
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/gcpdev-llm-council-skill)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 llm-council-skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | gcpdev | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 506 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年1月8日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
gcpdev 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
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。
开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor
GitHub account gcpdev (person), 12 years old
★ 506 stars · code last changed 2026年1月8日
1 scripts that can run on a computer: scripts/query_llms.py
Scripts that go online: scripts/query_llms.py
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 0f95431 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
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
Uploading to claude.ai would fail: the description is over 200 characters (390). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /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
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 llm-council 文件夹放到 ~/.agents/skills/llm-council
~ 是你的主文件夹($HOME)
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。
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”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
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
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
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
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
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。
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”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 llm-council
Checked against official docs 2026年11月12日 · Source: cursor.com
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。
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”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
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 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
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。
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
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
4,184 个字符 · 在 GitHub 打开完整文件
---
name: llm-council
description: Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.
---
# LLM Council
Consult multiple AI models (ChatGPT and Gemini) for their perspectives before presenting implementation plans to users.
## Workflow
When user requests consultation with other AI models, use phrases like:
- "Consult with ChatGPT and Gemini about..."
- "Ask other AI models what they think about..."
- "Get perspectives from the council on..."
- "Consult the LLM council: [your question]"
**Process:**
1. **Query external LLMs**: Run `scripts/query_llms.py` with the user's prompt to get perspectives from both ChatGPT and Gemini
2. **Analyze responses**: Review what each model suggests, identifying valuable insights, alternative approaches, and potential concerns
3. **Synthesize plan**: Create an implementation plan that incorporates the best ideas from all three models (Claude's own analysis + ChatGPT + Gemini)
4. **Present to user**: Show the final plan along with a brief summary of key contributions from each model
## Setup Requirements
The skill requires API keys and optional model configuration stored in a `.env` file in the working directory:
```
OPENAI_API_KEY=sk-...
GEMINI_API_KEY=...
# Optional: Specify which models to use (defaults shown below)
OPENAI_MODEL=gpt-5-nano
GEMINI_MODEL=gemini-3-flash-preview
```
**Default Models:**
- ChatGPT: `gpt-5-nano` (fastest, most cost-efficient - $0.05/1M input, $0.40/1M output)
- Gemini: `gemini-3-flash-preview` (balanced speed and intelligence)
**Upgrade Options for Better Collaboration:**
*OpenAI models (ordered by capability and cost):*
- `gpt-5-nano` - Fastest, most cost-efficient ($0.05/1M in, $0.40/1M out) - **DEFAULT**
- `gpt-5-mini` - Faster, cost-efficient for well-defined tasks ($0.25/1M in, $2.00/1M out)
- `gpt-5.2` - Best for coding and agentic tasks ($1.75/1M in, $14.00/1M out)
- `gpt-5.2-pro` - Smarter, more precise for complex problems ($21.00/1M in, $168.00/1M out)
All models support reasoning tokens, 400K context window, and image input.
*Gemini models (ordered by capability):*
- `gemini-2.5-flash-lite` - Ultra-fast, optimized for throughput
- `gemini-2.5-flash` - Best price-performance, large-scale processing
- `gemini-3-flash-preview` - Balanced speed and frontier intelligence (default)
- `gemini-3-pro-preview` - Most intelligent multimodal model, best for complex reasoning
Higher-tier models provide more sophisticated analysis but cost more per API call.
If the `.env` file doesn't exist or keys are missing, inform the user and provide setup instructions.
## Usage Example
**User input:** "Consult the council: How should I architect a real-time data pipeline for IoT sensors?"
**Claude's process:**
1. Execute: `python3 scripts/query_llms.py "How should I architect a real-time data pipeline for IoT sensors?"`
2. Parse JSON responses from ChatGPT and Gemini
3. Analyze their suggestions (e.g., ChatGPT suggests Kafka, Gemini recommends considering edge computing)
4. Synthesize final plan incorporating valuable insights from all models
5. Present the adapted plan to user with attribution
## Output Format
Present the final implementation plan naturally, mentioning key insights from other models inline where relevant. For example:
"Based on consultation with ChatGPT and Gemini, here's the recommended architecture:
[Implementation plan with inline references like "ChatGPT highlighted the importance of..." or "Gemini suggested..."]
Key contributions:
- ChatGPT: [brief summary]
- Gemini: [brief summary]"
## Error Handling
- If API keys are missing, inform user and provide setup instructions
- If an API call fails, note which model's perspective is unavailable and proceed with available responses
- If both APIs fail, inform user and offer to provide Claude's own analysis without external consultation提问、分享技巧或报告无法使用。按“有帮助”数量排序。