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.
Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
Instruções da origem · Visualização somente leitura
name
skill-claw
disable-model-invocation
true
aliases
["claw","openclaw-admin","sysadmin"]
description
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
trigger
EXPLICITLY USE when user asks about:
- "manage openclaw" or "openclaw status" or "openclaw health"
- "update openclaw" or "upgrade openclaw" or "openclaw doctor"
- "setup openclaw" or "install openclaw" or "deploy openclaw"
- "openclaw gateway" or "openclaw channels" or "openclaw security"
- "manage my server" or "sysadmin" or "server health"
- "proxmox" or "lxc" or "oracle cloud" or "oci instance"
- "harden my server" or "secure my host" or "firewall setup"
- "openclaw on docker" or "openclaw compose"
- "openclaw backup" or "openclaw restore" or "openclaw migrate"
- "tailscale" or "tailnet" or "tailscale serve" or "tailscale funnel"
- "telegram bot" or "slack bot" or "discord bot" or "whatsapp" or "signal"
- "openclaw telegram" or "openclaw slack" or "openclaw channels"
- "gogcli" or "google workspace" or "google drive cli"
- "openclaw scheduler" or "openclaw cron" or "openclaw memory"
- "openclaw plugins" or "openclaw skills" or "openclaw mcp"
DO NOT activate for:
- OpenClaw extension development (use plugin-dev skills)
- Cloud architecture design from scratch (use /octo:develop with cloud-architect)
- CI/CD pipeline design (use /octo:develop with deployment-engineer)
- Application debugging unrelated to infrastructure (use /octo:debug)
- Kubernetes orchestration (use devops-troubleshooter persona)
OCI: ARM architecture, VCN security, Tailscale, systemd
Proxmox: qm/pct, vzdump, ZFS, LXC bind mounts
Phase 2: Assess Current State
Run diagnostics appropriate to the platform:
OpenClaw Diagnostics (All Platforms)
# Check OpenClaw installationcommand -v openclaw &>/dev/null && openclaw --version
# Gateway status
openclaw status --all
# Health check
openclaw health
# Doctor (auto-detect and report issues)
openclaw doctor
# Security audit
openclaw security audit
macOS Host Diagnostics
# Service status
launchctl list | grep openclaw
# System resources
vm_stat | head -10
df -h /
# Homebrew health
brew doctor 2>&1 | head -20
# Firewall status
/usr/libexec/ApplicationFirewall/socketfilterfw --getglobalstate
Ubuntu/Debian Host Diagnostics
# Service status
systemctl --user status openclaw-gateway 2>/dev/null || systemctl status openclaw-gateway
# System resources
free -h
df -h /
# Failed services
systemctl --failed
# Firewall status
ufw status verbose
# Pending updates
apt list --upgradable 2>/dev/null | head -20
Docker Diagnostics
# Container status
docker compose ps
# Container health
docker inspect --format='{{.State.Health.Status}}' openclaw-gateway 2>/dev/null
# Resource usage
docker stats --no-stream
# Disk usage
docker system df
Proxmox Diagnostics
# Proxmox version
pveversion -v
# VM/LXC list
qm list 2>/dev/null
pct list 2>/dev/null
# Storage status
pvesm status
# ZFS health
zpool status 2>/dev/null
# Cluster status
pvecm status 2>/dev/null
Phase 3: Execute the Requested Action
Route to the appropriate workflow based on user intent:
Firewall: only required ports open (SSH, Tailscale UDP 41641)
Use Anthropic Opus 4.6 as agent model (best prompt injection resistance)
Phase 4: Verify Outcome
After every action, verify it took effect:
# Check gateway is running
openclaw status
# Check health
openclaw health
# Run doctor to catch issues
openclaw doctor
# If security changes were made
openclaw security audit
Report the before/after state and any remaining issues.