← 返回 Skills 市场
fainaltn

Gpu Check

作者 fainaltn · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
383
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install gpu-check
功能描述
Automatically polls and displays memory usage and online status of RTX 3090 and 4090 AI compute nodes in the local network.
使用说明 (SKILL.md)

GPU 状态检查 (gpu_check)

实时获取局域网内分布式 AI 算力节点的显存占用情况。

功能

  • 自动轮询 3090 (192.168.2.236) 和 4090 (192.168.2.164) 的显存状态
  • 输出带进度条的 Markdown 表格
  • 监控各节点 API 服务在线情况

依赖

  • Node.js 环境(已内置)
  • axios 库(需安装)

安装

  1. 在技能目录安装依赖:
    cd ~/.openclaw/workspace/skills/gpu_check
    npm init -y
    npm install axios
    
  2. 确保 GPU 节点 API 已启动(需在 192.168.2.236 和 192.168.2.164 运行支持 /gpu 端点的服务)

使用

在聊天中发送:

  • /gpu
  • @机器人 显卡状态
  • 查看 GPU 占用
安全使用建议
This skill appears to do only what it claims: poll two local IPs for GPU memory usage. Before installing, verify the two IP addresses (192.168.2.236 and 192.168.2.164) are your intended GPU nodes. Note small inconsistencies (a Python implementation is included but not documented; package.json points to index.js which is missing). Run npm install only in a controlled environment (or inspect gpu_check.js/gpu_check.py yourself). If you don't use Python, you can ignore or remove gpu_check.py; if you don't want Node dependencies, avoid running npm install. If these nodes are unknown or unexpected on your network, do not install or run the skill.
功能分析
Type: OpenClaw Skill Name: gpu-check Version: 1.0.0 The skill `gpu-check` is designed to monitor GPU memory usage on specific internal network nodes (192.168.2.236 and 192.168.2.164) as described in `SKILL.md`. Both `gpu_check.js` and `gpu_check.py` implement this functionality by making HTTP GET requests to these hardcoded private IP addresses. The installation instructions in `SKILL.md` involve standard `npm` commands (`npm init -y`, `npm install axios`) necessary for the Node.js version of the skill. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts to subvert the agent for harmful purposes. All observed behaviors align with the stated benign purpose.
能力评估
Purpose & Capability
Name/description say it polls local RTX 3090/4090 nodes; the code (JS and Python) specifically queries the two private IPs on port 5000 and renders usage—this aligns with the stated purpose. Dependency on axios (for Node) is appropriate.
Instruction Scope
SKILL.md instructs installing axios and describes Node usage which matches gpu_check.js. Minor inconsistencies: a Python implementation (gpu_check.py) is included but SKILL.md does not mention Python or the requests library; package.json lists main:index.js which does not exist. These are quality issues but do not indicate malicious behavior.
Install Mechanism
No automated install/spec is provided (instruction-only). The package.json and package-lock.json reference npm packages from the public registry (axios and its deps), which is standard and expected.
Credentials
The skill requests no environment variables, no credentials, and only accesses two local private IP endpoints that match the stated purpose. Network access to those IPs is necessary for functionality.
Persistence & Privilege
Skill does not request always:true or other elevated platform privileges and does not modify other skills or system-wide config. Autonomous invocation is allowed by default (normal).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install gpu-check
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /gpu-check 触发
  4. 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
gpu-check 1.0.0 - Added real-time monitoring of GPU memory usage for distributed AI nodes (3090 and 4090) on the local network. - Output includes a progress bar in a Markdown table format. - Automatically checks API service availability for each monitored node. - Simple chat commands supported for querying GPU status. - Requires Node.js and axios library for operation.
元数据
Slug gpu-check
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Gpu Check 是什么?

Automatically polls and displays memory usage and online status of RTX 3090 and 4090 AI compute nodes in the local network. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 383 次。

如何安装 Gpu Check?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install gpu-check」即可一键安装,无需额外配置。

Gpu Check 是免费的吗?

是的,Gpu Check 完全免费(开源免费),可自由下载、安装和使用。

Gpu Check 支持哪些平台?

Gpu Check 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 Gpu Check?

由 fainaltn(@fainaltn)开发并维护,当前版本 v1.0.0。

💬 留言讨论