claude-monitor
Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.
About this skill
The 'claude-monitor' skill empowers an AI agent to act as a system health and performance diagnostic tool. Specifically designed to assess the operational efficiency of 'Claude Code' environments, it extends its monitoring capabilities to the local system resources, including CPU, RAM, and disk utilization. This skill is crucial for identifying and troubleshooting performance bottlenecks, such as slowdowns or lag, by providing detailed metrics and insights. It checks API latency for Claude Code interactions, allowing agents to pinpoint connectivity or response time issues. Ultimately, it synthesizes this data into actionable system health reports, enabling the AI agent to proactively address or recommend solutions for performance degradation.
Best use case
An AI agent can utilize this skill when a user reports a slow or unresponsive development environment, particularly when working with Claude Code. It's ideal for proactive system health checks, debugging performance issues, or generating routine reports on system resource utilization and API responsiveness to maintain optimal operational efficiency.
Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.
The user will receive a clear, concise report detailing the performance metrics of their system and Claude Code environment. This report will include CPU, RAM, and disk usage, Claude API latency, and a diagnosis of any detected slowdowns or performance issues, potentially with actionable recommendations or insights for resolution.
Practical example
Example input
My coding environment feels really sluggish today, especially when I'm using Claude Code. Can you run a diagnostic?
Example output
Running a comprehensive performance diagnostic now... **System Health Report - 2024-05-15 10:30 AM** **CPU Usage:** 85% (Peak: 92%) **RAM Usage:** 14.2 GB / 16 GB (89% utilization) **Disk I/O:** High activity (75 MB/s read, 50 MB/s write) **Claude Code API Latency:** - Average Response Time: 450 ms - Max Response Time: 820 ms - Min Response Time: 210 ms **Diagnosis:** Your system is experiencing high CPU and RAM utilization, likely contributing to the perceived sluggishness. Disk I/O is also elevated. Claude Code API latency is within acceptable limits but slightly higher than average. **Recommendations:** 1. Close any unnecessary applications or browser tabs to free up RAM and CPU. 2. Check background processes for resource-intensive tasks. 3. Consider optimizing your development environment settings or code for better efficiency. Would you like me to investigate specific processes or applications further?
When to use this skill
- When the user expresses concern about 'lento' (slow) or general system sluggishness.
- When the user mentions 'lentidao' (slowness) or 'lag' in their coding environment.
- When troubleshooting performance issues related to Claude Code API interactions.
- To generate a comprehensive report on the health of the local system's CPU, RAM, and disk.
When not to use this skill
- When the user's request is unrelated to system performance or resource monitoring.
- When the problem is a code logic error, rather than a system or environment performance issue.
- If the issue is external network connectivity that this skill cannot directly diagnose (e.g., internet outage not related to API latency from the local machine).
- When the focus is on creative tasks, content generation, or general knowledge queries.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/claude-monitor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How claude-monitor Compares
| Feature / Agent | claude-monitor | Standard Approach |
|---|---|---|
| Platform Support | Claude, Cursor, Gemini, Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.
Which AI agents support this skill?
This skill is designed for Claude, Cursor, Gemini, Codex.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Claude Monitor — Diagnóstico de Performance ## Overview Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema. ## When to Use This Skill - When the user mentions "lento" or related topics - When the user mentions "lentidao" or related topics - When the user mentions "lag" or related topics - When the user mentions "lagado" or related topics - When the user mentions "travando" or related topics - When the user mentions "claude lento" or related topics ## Do Not Use This Skill When - The task is unrelated to claude monitor - A simpler, more specific tool can handle the request - The user needs general-purpose assistance without domain expertise ## How It Works Skill para diagnosticar e resolver problemas de lentidão no Claude Code e no sistema. Determina se o gargalo é local (PC) ou remoto (API Claude) e sugere ações corretivas. ## Quando Usar - Usuário reclama que o Claude Code está lento ou travando - Troca de sessões de conversa demora para carregar - Respostas do Claude demoram muito - PC parece lento enquanto usa o Claude Code - Qualquer menção a performance, lag, lentidão ## 1. Diagnóstico Rápido (Health_Check.Py) Rode SEMPRE como primeiro passo: ```bash python C:\Users\renat\skills\claude-monitor\scripts\health_check.py ``` O script analisa em ~3 segundos: - **CPU**: Uso atual e por core. >80% = gargalo provável - **RAM**: Total, usada, disponível. >85% = pressão de memória - **Browsers**: Processos e RAM por browser. >5GB total = excesso de abas - **Claude Code**: Processos e RAM consumida - **Disco**: Espaço livre. <10% = impacto em swap/performance - **Rede**: Latência ao endpoint da API Claude - **Diagnóstico**: Classificação automática do problema com sugestões ## 2. Interpretar O Resultado O script retorna um JSON com `diagnosis` contendo: - `bottleneck`: "cpu" | "ram" | "browsers" | "disk" | "network" | "claude_api" | "ok" - `severity`: "critical" | "warning" | "ok" - `suggestions`: Lista de ações recomendadas - `summary`: Resumo em português para mostrar ao usuário **Mostre o `summary` ao usuário** e ofereça executar as sugestões. ## 3. Ações Corretivas Automáticas Baseado no diagnóstico, ofereça ao usuário: #### Se CPU alta (>80%): - Listar processos consumindo mais CPU - Sugerir fechar processos pesados desnecessários - Verificar se Windows Update está rodando em background #### Se browsers pesados (>5GB RAM ou >40 processos): ```bash python C:\Users\renat\skills\claude-monitor\scripts\health_check.py --browsers-detail ``` Mostra RAM por browser e sugere quais fechar. **Nunca fechar processos sem permissão explícita do usuário.** #### Se disco cheio (>85%): - Mostrar pastas maiores - Sugerir limpeza de Temp, cache de browsers, lixeira #### Se rede lenta (latência >500ms): - Testar conexão com api.anthropic.com - Sugerir verificar VPN, proxy, ou conexão WiFi ## 4. Monitor Contínuo (Opcional) Se o usuário quiser monitoramento em background: ```bash python C:\Users\renat\skills\claude-monitor\scripts\monitor.py --interval 30 --duration 300 ``` Parâmetros: - `--interval`: Segundos entre cada amostra (default: 30) - `--duration`: Duração total em segundos (default: 300 = 5 min) - `--output`: Caminho do arquivo de log (default: monitor_log.json) - `--alert-cpu`: Threshold de CPU para alerta (default: 80) - `--alert-ram`: Threshold de RAM % para alerta (default: 85) O monitor salva snapshots periódicos e gera um relatório ao final com: - Picos de CPU e RAM - Tendência (melhorando/piorando/estável) - Eventos de alerta detectados - Recomendação final ## 5. Benchmark Da Api Claude (Opcional) Para testar se a lentidão é da API: ```bash python C:\Users\renat\skills\claude-monitor\scripts\api_bench.py ``` Mede o tempo de resposta do processo Claude Code local (não faz chamadas à API). Compara com tempos típicos e indica se está dentro do esperado. ## Thresholds De Referência | Métrica | OK | Warning | Critical | |---------|-----|---------|----------| | CPU % | <60% | 60-85% | >85% | | RAM usada % | <70% | 70-85% | >85% | | RAM browsers | <3 GB | 3-6 GB | >6 GB | | Processos browser | <30 | 30-60 | >60 | | Disco livre | >15% | 10-15% | <10% | | Latência rede | <200ms | 200-500ms | >500ms | ## Dicas Para O Usuário Quando apresentar o diagnóstico, inclua estas dicas contextuais: - **Muitas abas = muito CPU/RAM**: Cada aba de browser é um processo separado. 50 abas = 50 processos competindo por recursos. - **Claude Code é pesado**: Ele roda vários processos Electron. É normal consumir 3-5 GB. Mas se estiver usando >6 GB com várias sessões, considere fechar sessões antigas. - **Troca de sessão lenta**: Geralmente causada por CPU alta ou muitos processos competindo. A sessão precisa carregar o histórico da conversa, e se o CPU está ocupado, demora. - **Disco quase cheio**: Afeta a velocidade do swap (memória virtual) e pode causar lentidão generalizada. ## Dependências - Python 3.10+ - psutil (instalado automaticamente pelo script se não disponível) - Nenhuma API key necessária ## Best Practices - Provide clear, specific context about your project and requirements - Review all suggestions before applying them to production code - Combine with other complementary skills for comprehensive analysis ## Common Pitfalls - Using this skill for tasks outside its domain expertise - Applying recommendations without understanding your specific context - Not providing enough project context for accurate analysis
Related Skills
datadog-automation
Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.
linear-claude-skill
Manage Linear issues, projects, and teams
claude-speed-reader
-Speed read Claude's responses at 600+ WPM using RSVP with Spritz-style ORP highlighting
claude-d3js-skill
This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
azure-monitor-query-py
Azure Monitor Query SDK for Python. Use for querying Log Analytics workspaces and Azure Monitor metrics.
azure-monitor-opentelemetry-py
Azure Monitor OpenTelemetry Distro for Python. Use for one-line Application Insights setup with auto-instrumentation.
azure-monitor-opentelemetry-exporter-py
Azure Monitor OpenTelemetry Exporter for Python. Use for low-level OpenTelemetry export to Application Insights.
azure-monitor-ingestion-py
Azure Monitor Ingestion SDK for Python. Use for sending custom logs to Log Analytics workspace via Logs Ingestion API.
azure-monitor-ingestion-java
Azure Monitor Ingestion SDK for Java. Send custom logs to Azure Monitor via Data Collection Rules (DCR) and Data Collection Endpoints (DCE).
nft-standards
Master ERC-721 and ERC-1155 NFT standards, metadata best practices, and advanced NFT features.
nextjs-app-router-patterns
Comprehensive patterns for Next.js 14+ App Router architecture, Server Components, and modern full-stack React development.