claude-home/monitoring/recovered-lxc300/server-diagnostics/SKILL.md

name	description
server-diagnostics	Automated server troubleshooting for Docker containers and system health. Provides SSH-based diagnostics, log reading, metrics collection, and low-risk remediation. USE WHEN N8N triggers troubleshooting, container issues detected, or system health checks needed.

Server Diagnostics - Automated Troubleshooting

When to Activate This Skill

• N8N triggers with error context
• "diagnose container X", "check docker status"
• "read logs from server", "check disk usage"
• "troubleshoot server issue"
• Any automated health check response

Quick Start

Check All Containers

python ~/.claude/skills/server-diagnostics/client.py docker-status paper-dynasty

Quick Health Check (Docker + System Metrics)

python ~/.claude/skills/server-diagnostics/client.py health paper-dynasty

Get Container Logs

python ~/.claude/skills/server-diagnostics/client.py docker-logs paper-dynasty paper-dynasty_discord-app_1 --lines 200

Restart a Container

python ~/.claude/skills/server-diagnostics/client.py docker-restart paper-dynasty paper-dynasty_discord-app_1

System Metrics

python ~/.claude/skills/server-diagnostics/client.py metrics paper-dynasty --type all
python ~/.claude/skills/server-diagnostics/client.py metrics paper-dynasty --type disk

Run Diagnostic Command

python ~/.claude/skills/server-diagnostics/client.py diagnostic paper-dynasty disk_usage
python ~/.claude/skills/server-diagnostics/client.py diagnostic paper-dynasty memory_usage

Troubleshooting Workflow

When an issue is reported:

1. Quick Health Check - Get overview of containers and system state

   python ~/.claude/skills/server-diagnostics/client.py health paper-dynasty
   

2. Check MemoryGraph - Recall similar issues

   python ~/.claude/skills/memorygraph/client.py recall "docker container error"
   

3. Get Container Logs - Look for errors

   python ~/.claude/skills/server-diagnostics/client.py docker-logs paper-dynasty <container> --lines 500 --filter error
   

4. Remediate if Safe - Restart if allowed

   python ~/.claude/skills/server-diagnostics/client.py docker-restart paper-dynasty <container>
   

5. Store Solution - Save to MemoryGraph if resolved

   python ~/.claude/skills/memorygraph/client.py store \
     --type solution \
     --title "Fixed <container> issue" \
     --content "Description of problem and solution" \
     --tags "docker,paper-dynasty,troubleshooting" \
     --importance 0.7
   

Server Inventory

Server	IP	SSH User	Description
paper-dynasty	10.10.0.88	cal	Paper Dynasty Discord bots and services

Monitored Containers

Container	Critical	Restart Allowed	Description
paper-dynasty_discord-app_1	Yes	Yes	Paper Dynasty Discord bot
paper-dynasty_db_1	Yes	Yes	PostgreSQL database
paper-dynasty_adminer_1	No	Yes	Database admin UI
sba-website_sba-web_1	Yes	Yes	SBA website
sba-ghost_sba-ghost_1	No	Yes	Ghost CMS

Available Diagnostic Commands

• disk_usage - df -h
• memory_usage - free -h
• cpu_usage - top -bn1 | head -20
• cpu_load - uptime
• process_list - ps aux --sort=-%mem | head -20
• network_status - ss -tuln
• docker_ps - docker ps -a (formatted)
• docker_stats - docker stats --no-stream
• journal_errors - journalctl -p err -n 50

Security Constraints

DENIED Patterns (Will Be Rejected)

• rm -rf, rm -r /
• dd if=, mkfs
• shutdown, reboot
• systemctl stop
• chmod 777
• wget|sh, curl|sh

Container Restart Rules

• Only containers in config.yaml with restart_allowed: true
• N8N container restart is NEVER allowed (it triggers us)

MemoryGraph Integration

Before troubleshooting, check for known solutions:

python ~/.claude/skills/memorygraph/client.py recall "docker paper-dynasty"

After resolving, store the pattern:

python ~/.claude/skills/memorygraph/client.py store \
  --type solution \
  --title "Brief description" \
  --content "Full explanation..." \
  --tags "docker,paper-dynasty,fix" \
  --importance 0.7

Common Issues and Solutions

Container Not Running

1. Check logs for crash reason
2. Check disk space and memory
3. Attempt restart if allowed
4. Escalate if restart fails

High Memory Usage

1. Check which container is consuming
2. Review docker stats
3. Check for memory leaks in logs
4. Consider container restart

Disk Space Low

1. Run disk_usage diagnostic
2. Check docker system df
3. Consider log rotation
4. Alert user for cleanup

Output Format

All commands return JSON:

{
  "success": true,
  "stdout": "...",
  "stderr": "...",
  "returncode": 0,
  "data": {...}  // Parsed data if applicable
}