ask-council

直接通过 Telegram/chat 向 LLM 委员会提出问题 — 获取主席的综合报告 无需打开 Web UI 即可回答。快速、无头访问多模型共识。

# Ask Council — Quick Headless Access

Get LLM Council's synthesized answer without leaving your chat.

## Usage

```
/council Should I invest in Tesla right now?
```

Returns the **Chairman's synthesized answer** after all models have debated.

## How It Works

1. Sends your question to the LLM Council backend
2. Waits for Stage 1 (all models respond)
3. Waits for Stage 2 (models rank each other)
4. Returns Stage 3 (Chairman's final synthesis)

**Takes 30-60 seconds** — models need time to deliberate.

## Prerequisites

LLM Council backend must be running:
```
/install-llm-council
```

## Two Ways to Use LLM Council

| Mode | Best For | Command |
|------|----------|---------|
| **Quick answer** (this skill) | Fast decisions, mobile, casual questions | `/council "question"` |
| **Full discussion** (web UI) | Deep research, exploring disagreements, seeing all model responses | `/install-llm-council` then open browser |

## Example

**Input:**
```
/council Is Python or Go better for a new microservice?
```

**Output:**
```
Council is deliberating... (this may take 30-60s)
................

═══════════════════════════════════════════════════════════════
                    CHAIRMAN'S ANSWER
═══════════════════════════════════════════════════════════════

Based on the council's deliberation, Python is recommended for rapid 
prototyping and team velocity, while Go excels for high-throughput 
services where performance is critical...

═══════════════════════════════════════════════════════════════

View full discussion: http://10.0.1.184:5173
```

## Agent Instructions

When user says `/council <question>` or "ask council":

```bash
bash ~/.openclaw/skills/ask-council/ask-council.sh "<question>"
```

The script handles:
- Creating a conversation
- Starting the council run
- Polling until complete
- Extracting the chairman's answer
- Showing progress dots while waiting

## Files

| File | Purpose |
|------|---------|
| `SKILL.md` | Documentation |
| `ask-council.sh` | Main script — queries API and returns answer |
| `_meta.json` | Skill metadata |

## Notes

- Timeout: 120 seconds
- If backend isn't running, suggests starting it
- Always includes link to full web UI for detailed exploration
- Creates a new conversation each time (no history)

---

## 中文说明

# Ask Council — 快速无头访问

无需离开聊天即可获取 LLM Council 的综合答案。

## 用法

```
/council Should I invest in Tesla right now?
```

在所有模型辩论之后，返回**主席的综合答案**。

## 工作原理

1. 将你的问题发送到 LLM Council 后端
2. 等待第 1 阶段（所有模型作出回应）
3. 等待第 2 阶段（模型相互排名）
4. 返回第 3 阶段（主席的最终综合）

**耗时 30-60 秒** — 模型需要时间进行审议。

## 前置条件

LLM Council 后端必须正在运行：
```
/install-llm-council
```

## 使用 LLM Council 的两种方式

| 模式 | 最适合 | 命令 |
|------|----------|---------|
| **快速答案**（本技能） | 快速决策、移动端、随意提问 | `/council "question"` |
| **完整讨论**（Web UI） | 深度研究、探究分歧、查看所有模型回应 | `/install-llm-council` 然后打开浏览器 |

## 示例

**输入：**
```
/council Is Python or Go better for a new microservice?
```

**输出：**
```
Council is deliberating... (this may take 30-60s)
................

═══════════════════════════════════════════════════════════════
                    CHAIRMAN'S ANSWER
═══════════════════════════════════════════════════════════════

Based on the council's deliberation, Python is recommended for rapid 
prototyping and team velocity, while Go excels for high-throughput 
services where performance is critical...

═══════════════════════════════════════════════════════════════

View full discussion: http://10.0.1.184:5173
```

## 代理指令

当用户说 `/council <question>` 或 "ask council" 时：

```bash
bash ~/.openclaw/skills/ask-council/ask-council.sh "<question>"
```

该脚本负责：
- 创建一个会话
- 启动 council 运行
- 轮询直到完成
- 提取主席的答案
- 等待时显示进度点

## 文件

| 文件 | 用途 |
|------|---------|
| `SKILL.md` | 文档 |
| `ask-council.sh` | 主脚本 — 查询 API 并返回答案 |
| `_meta.json` | 技能元数据 |

## 注意事项

- 超时：120 秒
- 如果后端未运行，则建议启动它
- 始终包含完整 Web UI 的链接，以便详细探究
- 每次都创建一个新会话（无历史记录）