메뉴
Check system health (CPU, memory, disk, network, top processes) and report alarms on high usage
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Inspect or debug web pages in a headless browser — fill forms, click buttons, take screenshots, test web apps, review frontend UI/UX aesthetics. Use for headless browser automation. This skill should be used when user says "test web app interactively", "use a headless browser", "browser automation", "headless web test", "review frontend layout", "screenshot of this page", "frontend UI polish".
Peer-to-peer messaging between Claude Code sessions sharing a tmux server. Use when coordinating multiple simultaneous Claude sessions — e.g. "dm another claude", "list claude sessions", "peek peer claude", "spawn claude in tmux", "monitor remote claude", "orchestrate claude sessions".
Programmatic/headless Claude Code usage — CLI flags, stream-json protocol, Agent SDKs, session management. Use before spawning Claude as a subprocess, testing skill or agent behavior, running "claude -p", or building with the Agent SDK.
Audit agent-facing documentation (CLAUDE.md, SKILL.md, AGENTS.md, prompt markdown, agent reference doc, memory pages) for over-description and propose trims. Use proactively after writing or editing any agent-facing doc, or when the user says "trim this doc", "audit doc bloat", "this is over-explained".
Use MarkItDown to convert various files to Markdown. Use when converting PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs, Jupyter notebooks, RSS feeds, or Wikipedia pages to Markdown format. Also use for document processing pipelines, LLM preprocessing, or text extraction tasks.
Append a single bullet to staging memory. Use when a durable fact, knowledge, lesson, or pitfall (mistake-correction pattern) emerged mid-conversation that's potentially worth persisting into long-term memory. Also use when user corrected your mistake, says "remember X", "remember not to X", or "next time, do Y instead of X", "do not mistake on X again".
| name | system-monitor |
| description | Check system health (CPU, memory, disk, network, top processes) and report alarms on high usage |
| allowed-tools | ["Bash(top:*)","Bash(free:*)","Bash(df:*)","Bash(ps:*)","Bash(cat /proc/net/dev:*)","Bash(ip:*)"] |
| when_to_use | Use when the user asks to check system status, system health, or resource usage. Trigger phrases: "check system", "system status", "syscheck", "check CPU", "check memory", "check disk", "is the system OK?", "system health". |
| disable-model-invocation | true |
Check current system health and report alarms when any resource exceeds safe thresholds.
Present a single summary table of CPU, memory, disk, and network status with OK / Watch / ALARM indicators. List top resource-consuming processes. Flag any metric that exceeds its threshold.
| Resource | Watch | ALARM |
|---|---|---|
| CPU | > 60% | > 80% |
| Memory | > 60% | > 80% |
| Disk | > 70% | > 85% |
Run the following commands and parse their output:
top -bn1 | head -5 — extract user%, system%, idle%, and load averagesfree -h — extract total, used, availabledf -h --total -x tmpfs -x devtmpfs -x efivarfs — extract total, used, available, use%cat /proc/net/dev — extract RX/TX bytes for non-loopback interfacesps aux --sort=-%cpu | head -6 for CPU hogs, ps aux --sort=-%mem | head -6 for memory hogsCompare each metric against the threshold table above. Assign status:
Present results as:
Success criteria: User sees a clear, scannable health report and any alarms are immediately obvious.