Menu
Direct VPS operations via SSH MCP. Manage Docker containers, check logs, run commands, and troubleshoot services on registered VPS servers.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Detect project stack, apply architecture patterns, wire quality gates, and scaffold features. Use when bootstrapping a project, adding a vertical slice, wiring CI/CD, adding Docker compose, or setting up quality gates.
Generates structured Handoff Pack prompts for delegating work to Gemini with clear scope, acceptance criteria, and output format requirements.
Incrementally improve type safety by replacing string literals with enums, narrowing `any` types, and using shared types. Works in small verified batches. Preserves functionality while improving code quality.
Cloudflare DNS and infrastructure management. Manage DNS records, tunnels, Access policies, SSL certificates, and CDN caching.
Deploy projects to staging or production environments. Repo-agnostic deployment orchestration using SSH MCP for VPS operations and Cloudflare for DNS/SSL. Reads project configuration from deployments.registry.json.
Generate a session briefing from development memory (events.jsonl, sessions.jsonl). Shows recent timeline, open questions, and suggested focus areas.
| name | vps |
| description | Direct VPS operations via SSH MCP. Manage Docker containers, check logs, run commands, and troubleshoot services on registered VPS servers. |
| examples | ["/vps status","/vps logs api","/vps exec 'docker ps'","/vps restart api","/vps health"] |
Direct SSH access to VPS servers for container management and troubleshooting.
/vps # Show VPS status for current project
/vps status # Container status + resource usage
/vps logs <service> # View service logs (tail -100)
/vps logs <service> --follow # Stream logs
/vps exec '<command>' # Execute arbitrary command on VPS
/vps restart <service> # Restart specific container
/vps health # Run health checks on all services
/vps resources # Show CPU, memory, disk usage
/vps backup # Backup database to NAS
Reads project from:
deployments.registry.json lookup# List all containers
ssh ${USER}@${HOST} "docker ps -a --format 'table {{.Names}}\t{{.Status}}\t{{.Ports}}'"
# Restart service
ssh ${USER}@${HOST} "docker compose -f ${COMPOSE_PATH} restart ${SERVICE}"
# View logs
ssh ${USER}@${HOST} "docker logs ${CONTAINER} --tail 100"
# Execute in container
ssh ${USER}@${HOST} "docker exec ${CONTAINER} npm run db:migrate"
# System resources
ssh ${USER}@${HOST} "free -h && df -h && uptime"
# Docker resource usage
ssh ${USER}@${HOST} "docker stats --no-stream"
# Nginx status
ssh ${USER}@${HOST} "sudo systemctl status nginx"
# Active connections
ssh ${USER}@${HOST} "netstat -an | grep ESTABLISHED | wc -l"
# Backup database
ssh ${USER}@${HOST} "docker exec ${DB_CONTAINER} pg_dump -U postgres ${DB} > /backup/${DB}_$(date +%Y%m%d).sql"
# Copy backup to NAS
scp ${USER}@${HOST}:/backup/${DB}_*.sql berry@10.0.0.23:/volume1/backups/
# Check database connections
ssh ${USER}@${HOST} "docker exec ${DB_CONTAINER} psql -U postgres -c 'SELECT count(*) FROM pg_stat_activity;'"
# Check for OOM kills
ssh ${USER}@${HOST} "dmesg | grep -i 'out of memory' | tail -10"
# Check docker events
ssh ${USER}@${HOST} "docker events --since '1h' --until 'now'"
# Check failed services
ssh ${USER}@${HOST} "docker ps -a --filter 'status=exited' --format '{{.Names}}: {{.Status}}'"
pkill node - will kill Claude Code--dry-run firstdocker compose restart instead of killing containersmcp__project-vps__exec # Execute commands on project VPS
mcp__home-nas__exec # Execute commands on home NAS