← 返回 Skills 市场
Model Council
作者
aiwithabidi
· GitHub ↗
· v1.0.0
291
总下载
0
收藏
3
当前安装
1
版本数
在 OpenClaw 中安装
/install model-council
功能描述
Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win...
安全使用建议
This skill is coherent with its stated purpose, but remember it will send whatever you type to external LLMs via OpenRouter and incur API costs. Do not submit sensitive secrets or private data to the council. Verify your OpenRouter account limits and billing, and consider testing with a throwaway question first. If you are uncertain about the publisher, review the included script yourself (it is short and uses only the OpenRouter endpoints) and rotate the API key if you decide to stop using the skill. Finally, monitor usage after enabling the skill to detect unexpected calls or charges.
功能分析
Type: OpenClaw Skill
Name: model-council
Version: 1.0.0
The 'model-council' skill is a legitimate multi-model consensus tool that queries several LLMs via the OpenRouter API and uses a judge model to synthesize the best answer. The implementation in `scripts/model_council.py` uses standard Python libraries (urllib, concurrent.futures) to handle parallel requests and properly manages the `OPENROUTER_API_KEY` via environment variables. There is no evidence of data exfiltration, malicious execution, or prompt-injection attacks within the documentation or code.
能力评估
Purpose & Capability
Name/description ask for multi-model consensus via OpenRouter and the package only requires OPENROUTER_API_KEY and contains a script that calls OpenRouter endpoints for chat completions and (optionally) generation-cost info. The default model list and judge selection align with the stated purpose.
Instruction Scope
SKILL.md tells the agent to run the included Python script with the question and optional flags. The script only reads the OPENROUTER_API_KEY environment variable and does network calls to openrouter.ai; it does not read other files, credentials, or unexpected system paths.
Install Mechanism
No install spec is provided (instruction-only + included script). The script uses only Python stdlib (urllib, threading), so nothing is downloaded or written during install. This is a low-risk install model.
Credentials
Only OPENROUTER_API_KEY is required and declared as primaryEnv. The key is necessary and sufficient for forwarding requests to OpenRouter. No other secrets or unrelated env vars are requested or accessed by the code.
Persistence & Privilege
The skill does not request or require always:true and does not attempt to modify other skills or system-wide settings. It runs on-demand and only uses the API key at runtime.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install model-council - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-council触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of Model Council.
- Query multiple LLMs (3+) via OpenRouter simultaneously.
- Judge model evaluates all responses, selects a winner, provides reasoning, and synthesizes the best answer.
- Designed for important decisions, code review, research verification, and creative comparison.
- Flexible options for custom models, judge, output format, and token limits.
- Requires OPENROUTER_API_KEY for operation.
元数据
常见问题
Model Council 是什么？
Multi-model consensus system — send a query to 3+ different LLMs via OpenRouter simultaneously, then a judge model evaluates all responses and produces a win... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 291 次。
如何安装 Model Council？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-council」即可一键安装，无需额外配置。
Model Council 是免费的吗？
是的，Model Council 完全免费（开源免费），可自由下载、安装和使用。
Model Council 支持哪些平台？
Model Council 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Model Council？
由 aiwithabidi（@aiwithabidi）开发并维护，当前版本 v1.0.0。
推荐 Skills