菜单
Monitor system health: CPU, memory, disk, network, processes, services, and logs. Present data naturally. Correlate issues across subsystems. Alert on thresholds. Diagnose root causes.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/bolivian-peru/os-moda --skill system-monitor命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Generate a concise daily infrastructure briefing. Covers: service health, resource usage, security events, overnight incidents, and cost tracking. Designed for Telegram/chat delivery.
Multi-perspective risk analysis using structured persona debate before deploying changes
Build software via spec-driven development (github/spec-kit). Whenever the user asks for a feature larger than a one-line tweak, scaffold a spec-kit project, capture WHAT + WHY, declare tech stack, break into tasks, then iterate the implementation until tests pass.
基于 SOC 职业分类
正在显示 SKILL.md
| name | system-monitor |
| description | Monitor system health: CPU, memory, disk, network, processes, services, and logs. Present data naturally. Correlate issues across subsystems. Alert on thresholds. Diagnose root causes. |
| tools | ["system_query","system_health","memory_recall","memory_store","teach_context","teach_patterns"] |
| activation | auto |
You can monitor every aspect of the system in real time.
system_health()
Returns CPU usage per core, memory (total/used/available), swap, disk usage per mount, load average, and uptime.
system_query({ query: "processes", args: { sort: "cpu", limit: 20 } })
system_query({ query: "processes", args: { sort: "memory", limit: 20 } })
system_query({ query: "processes", args: { name: "firefox" } })
system_query({ query: "disk" })
Returns per-mount: filesystem type, total/used/available space, usage percentage.
When the user reports a problem:
system_health() for the overviewmemory_recall({ query: "similar problem description" })memory_store({ summary: "...", detail: "...", category: "diagnosis" })Always diagnose before suggesting fixes. Explain what you found. Store diagnoses for future reference — next time the same issue occurs, you'll recall it instantly.
Flag these to the user proactively: