← 返回 Skills 市场
Cool Agent Tools
作者
chuangyinbot-boop
· GitHub ↗
· v1.0.0
· MIT-0
147
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cool-agent-tools
功能描述
AI Agent 通用工具集 - 提供系统监控、日志分析、进程管理、文件处理、网络诊断等实用命令封装,帮助 agent 高效完成日常运维和数据处理任务。
使用说明 (SKILL.md)
agent-tools
AI Agent 通用工具集,让 CooL神 拥有瑞士军刀般的实用能力。
工具清单
🔍 系统监控
| 命令 | 说明 |
|---|---|
top |
查看系统进程/资源占用 |
htop |
交互式进程查看(需安装) |
df -h |
磁盘空间使用情况 |
du -sh * |
当前目录各文件夹大小 |
free -h |
内存使用情况 |
uptime |
系统运行时间和负载 |
🌐 网络诊断
| 命令 | 说明 |
|---|---|
curl -I \x3Curl> |
检查 URL 可达性(只取 header) |
ping -c 4 \x3Chost> |
测试网络连通性 |
nslookup \x3Cdomain> |
DNS 解析查询 |
netstat -tuln |
查看监听端口 |
ifconfig / ip addr |
查看网络接口 |
📁 文件处理
| 命令 | 说明 |
|---|---|
find . -name "*.log" -mtime -7 |
7天内修改过的日志文件 |
find . -size +100M |
查找大于 100MB 的文件 |
ls -laSh |
按大小排序显示文件 |
wc -l \x3Cfile> |
统计文件行数 |
grep -r "error" ./logs/ |
递归搜索日志中的错误 |
tail -f \x3Cfile> |
实时跟踪文件变化 |
tar -czvf archive.tar.gz ./dir/ |
压缩目录 |
tar -xzvf archive.tar.gz |
解压 tar.gz |
🐳 容器/Docker
| 命令 | 说明 |
|---|---|
docker ps |
查看运行中的容器 |
docker ps -a |
查看所有容器(含停止) |
docker logs --tail 100 \x3Ccontainer> |
查看容器最近日志 |
docker images |
查看镜像列表 |
docker system df |
磁盘使用情况 |
📊 日志分析
| 命令 | 说明 |
|---|---|
journalctl -u \x3Cservice> --since "1 hour ago" |
查看服务最近日志 |
dmesg | tail -50 |
内核日志 |
tail -n 100 /var/log/syslog |
系统日志 |
⚙️ 进程管理
| 命令 | 说明 |
|---|---|
pkill \x3Cname> |
按名称杀死进程 |
pgrep -f \x3Cname> |
查找进程 PID |
kill -9 \x3Cpid> |
强制终止进程 |
nohup \x3Ccmd> & |
后台运行(断开 SSH 仍保持) |
🛠️ Git 操作
| 命令 | 说明 |
|---|---|
git status |
查看工作区状态 |
git log --oneline -10 |
最近 10 次提交 |
git diff |
查看未暂存的修改 |
git branch -a |
查看所有分支 |
🔧 实用脚本
# 清理旧日志(保留最近 7 天)
find /var/log -name "*.log" -mtime +7 -delete
# 找出占用空间最大的目录(深度 2)
du -h --max-depth=2 / | sort -hr | head -20
# 杀掉所有名为 python 的进程
pkill -f python
# 实时查看 access.log 最新 50 行
tail -50f /var/log/nginx/access.log
# 检查 URL 是否返回 200
curl -s -o /dev/null -w "%{http_code}" https://example.com
使用方式
agent-tools 不需要特殊触发指令。在分析系统问题、执行运维任务时,直接调用对应命令即可。
示例场景:
- "帮我看看服务器负载" → 执行
uptime && free -h - "检查网站能不能访问" → 执行
curl -I https://example.com - "找出哪些文件占空间" → 执行
du -sh *按大小排序 - "清理 7 天前的日志" → 执行
find ... -mtime +7 -delete
让 CooL神 成为一个真正的全能助手
安全使用建议
This skill is coherent for system administration, but it contains high-impact commands (delete logs, kill processes) and omits declaring which system tools it needs. Before installing: (1) only allow human-in-the-loop invocation or require explicit confirmations for destructive actions; (2) run the agent in a restricted/test environment with limited privileges (avoid root) and backups available; (3) ask the author to document required binaries and to replace broad commands (e.g., pkill -f python, find ... -delete) with safer, interactive alternatives or add confirmation/whitelisting; (4) if you must allow autonomous runs, add strict policies/logging and limit which commands the agent may execute. If you cannot enforce these controls, treat the skill as risky and avoid installing it on production hosts.
功能分析
Type: OpenClaw Skill
Name: cool-agent-tools
Version: 1.0.0
The skill bundle 'agent-tools' (SKILL.md) provides the AI agent with a broad set of high-risk system administration capabilities, including process termination (kill -9, pkill), recursive file deletion (find ... -delete), and access to sensitive system logs (/var/log/syslog, dmesg). While these tools are aligned with the stated purpose of system maintenance, providing an AI agent with unrestricted shell-equivalent commands for destructive actions without safety guardrails or scoping is a high-risk configuration that could be easily exploited for system disruption.
能力评估
Purpose & Capability
Name/description match the provided commands (system monitoring, logs, processes, network). However, the skill declares no required binaries or config yet the instructions rely on many standard system tools (curl, docker, netstat/ifconfig/ip, journalctl, pkill/kill, tar, find, du, etc.). This omission is sloppy and should be clarified but is not inherently malicious.
Instruction Scope
SKILL.md directly instructs the agent to execute system-level commands including destructive operations (e.g., find /var/log -name "*.log" -mtime +7 -delete, pkill -f python, kill -9). There are no safeguards, confirmation steps, or policies about when to run destructive actions. The instructions give broad discretion to run commands on the host, which increases risk if the agent is allowed to act autonomously.
Install Mechanism
Instruction-only skill with no install spec or code files. This minimizes supply-chain risk because nothing is written or downloaded by the skill itself.
Credentials
The skill requests no credentials or environment variables, which is appropriate for local sysadmin tooling. Note: it does assume access to host filesystem and container runtime (docker) — reasonable for the stated purpose but should be acknowledged to users who expect limited agent permissions.
Persistence & Privilege
always:false (no forced presence). The skill permits model invocation (normal), which combined with the instruction scope (destructive commands) increases risk if the agent is allowed to act autonomously. The skill does not attempt to modify other skills or system-wide configurations.
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 cool-agent-tools - 安装完成后,直接呼叫该 Skill 的名称或使用
/cool-agent-tools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: system monitoring, network diagnostics, file processing, Docker management, log analysis, process management, Git operations
元数据
常见问题
Cool Agent Tools 是什么?
AI Agent 通用工具集 - 提供系统监控、日志分析、进程管理、文件处理、网络诊断等实用命令封装,帮助 agent 高效完成日常运维和数据处理任务。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 147 次。
如何安装 Cool Agent Tools?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cool-agent-tools」即可一键安装,无需额外配置。
Cool Agent Tools 是免费的吗?
是的,Cool Agent Tools 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Cool Agent Tools 支持哪些平台?
Cool Agent Tools 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 Cool Agent Tools?
由 chuangyinbot-boop(@chuangyinbot-boop)开发并维护,当前版本 v1.0.0。
推荐 Skills