Skip to main content الرئيسية المنشئون 1yihui yihui openclaw-ops
openclaw-ops Use when diagnosing, repairing, or maintaining an OpenClaw Gateway on the same machine. Designed for rescue agents to fix a down gateway or check operational health. Supports Linux (systemd) and macOS (launchd).
الانتقال إلى التثبيت سوق المهارات اكتشف واستكشف مهارات الذكاء الاصطناعي التي بناها المجتمع.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
عرض تفاصيل Prompt يتجاوز الأمر المباشر Prompt المخصّص للمراجعة. افحص المصدر قبل تشغيله.
npx skills add https://github.com/1yihui/YiHui --skill openclaw-opsيبقى الأمر في سطر واحد. مرّر أفقيًا لمراجعته كاملًا قبل النسخ.
تفضّل نسخة محلية؟ نزّل الملفات المتاحة حاليًا لدى SkillsMP.
تحميل Zip جاري التحميل... المزيد من هذا المستودع Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent's behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
brain v1.1.7 用户版（免费）：让AI Agent拥有类大脑决策架构。置信度触发、双保险记忆、经验胶囊复用。开箱即用，3片段内存池，2并发上限。
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
المهن ذات الصلة SOC
استنادا إلى تصنيف SOC المهني
name openclaw-ops license MIT version 1.2.1 description Use when diagnosing, repairing, or maintaining an OpenClaw Gateway on the same machine. Designed for rescue agents to fix a down gateway or check operational health. Supports Linux (systemd) and macOS (launchd). repository https://github.com/dinstein/openclaw-ops-skill requirements ["Shell access on the same machine as the OpenClaw Gateway","Read/write access to ~/.openclaw/ (config, agents, sessions)","Read access to systemd user service config (Linux) or LaunchAgents (macOS)","Node.js 18+ and npm (for openclaw CLI)",{"Optional":"Tailscale CLI (for reverse proxy troubleshooting)"}] security_notes ["This skill instructs the agent to read and modify OpenClaw config files","The agent will access env files containing tokens (but is instructed never to print them)","Config edits are always preceded by timestamped backups","Destructive operations require user confirmation"] source https://github.com/1yihui/YiHui compatibility openclaw
OpenClaw Operations
Design Philosophy
This skill serves two core scenarios and nothing else:
Rescue — The main OpenClaw Gateway is down or broken. You (the rescue agent) need to diagnose the root cause, fix it, and bring the gateway back online.Health Check — The main OpenClaw Gateway is running. You need to verify its operational health, clean up resources, or perform maintenance tasks like upgrades.
What this skill is NOT for:
Day-to-day business configuration (adding channels, configuring agents, setting up integrations)
Application-level issues (agent behavior, prompt tuning, skill management)
Initial deployment or first-time setup (use openclaw daemon install and openclaw configure)
Principle: Diagnose → Judge → Act → Verify. Never skip steps.
Platform Detection
Detect the platform first — commands differ between Linux (systemd) and macOS (launchd):
OS=$(uname -s)
echo "Platform: $OS "
Port Detection
Do NOT assume port 18789. Detect the actual configured port first:
PORT=$(openclaw config get gateway.port 2>/dev/null | grep -oE '[0-9]+' )
PORT=${PORT:-18789}
echo "Gateway port: $PORT "
Use $PORT in all port-related commands throughout this guide.
Scenario A: Rescue (Gateway Down)
Follow these sections in order when the main gateway is not running.
A1. Assess the Situation
systemctl --user status openclaw-gateway
launchctl list | grep openclaw
pgrep -af openclaw
ss -tlnp | grep $PORT
$PORT
A2. Check Logs for Root Cause journalctl --user -u openclaw-gateway --since "1 hour ago" --no-pager | grep -iE "error|crash|fatal|SIGTERM|OOM"
journalctl --user -u openclaw-gateway -n 50 --no-pager
LOG_DIR="$HOME /.openclaw/logs"
grep -iE "error|crash|fatal" "$LOG_DIR /gateway.log" | tail -20
tail -50 "$LOG_DIR /gateway.log"
log show --predicate 'process == "node"' --last 1h | grep -iE "error|crash|fatal"
Common crash patterns Log pattern Meaning Fix EADDRINUSEPort already in use Find conflicting process: ss -tlnp | grep $PORT (Linux) or lsof -iTCP:$PORT (macOS), kill it or change port ENOMEM / JavaScript heapOut of memory Check free -h (Linux) / vm_stat (macOS), kill memory hogs or increase Node heap SyntaxError in configBad JSON in openclaw.json See A3 Config Repair MODULE_NOT_FOUNDMissing dependency cd $(npm root -g)/openclaw && npm install --productionInvalid token / 401 / 403Auth failure Check tokens in env file or systemd drop-in ECONNREFUSEDUpstream unreachable Check network, Tailscale, API endpoints
A3. Config Repair cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak.$(date +%s)
python3 -c "import json; json.load(open('$HOME /.openclaw/openclaw.json'))"
Common JSON issues: trailing comma, missing quotes, unescaped characters. The error message shows line/position.
Config schema validation:
openclaw config get gateway
openclaw config get channels
Symptom Likely cause Fix "device identity mismatch" Service env token ≠ config token Sync tokens between env file and openclaw.json Agent not routing bindings misconfiguredBindings go at top-level, not inside agents.list[].routing
python3 -c "import json; json.load(open('$HOME /.openclaw/openclaw.json')); print('JSON OK')"
openclaw status
A4. Check Resources
df -h ~
free -h
vm_stat | head -5
node -v
which openclaw
openclaw --version
A5. Restart and Verify Only restart after identifying and fixing the root cause .
systemctl --user restart openclaw-gateway
sleep 3
systemctl --user status openclaw-gateway
journalctl --user -u openclaw-gateway -n 20 --no-pager
launchctl kickstart -k "gui/$(id -u) /com.openclaw.gateway"
sleep 3
launchctl list | grep openclaw
tail -20 ~/.openclaw/logs/gateway.log
If service won't start at all:
openclaw status
openclaw doctor --non-interactive
Scenario B: Health Check (Gateway Running) Follow these sections for routine operational checks on a running gateway.
B1. Quick Health Check
openclaw doctor
openclaw doctor --fix
B2. Update & Upgrade
CURRENT=$(openclaw --version)
LATEST=$(npm view openclaw version)
echo "Current: $CURRENT Latest: $LATEST "
openclaw doctor --non-interactive 2>&1 | tee /tmp/doctor-before.txt
cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.pre-upgrade.$(date +%s)
npm update -g openclaw
openclaw --version
systemctl --user restart openclaw-gateway
launchctl kickstart -k "gui/$(id -u) /com.openclaw.gateway"
sleep 5
openclaw doctor --non-interactive 2>&1 | tee /tmp/doctor-after.txt
diff /tmp/doctor-before.txt /tmp/doctor-after.txt
npm install -g openclaw@<previous_version>
cp ~/.openclaw/openclaw.json.pre-upgrade.<timestamp> ~/.openclaw/openclaw.json
B3. Session & Disk Cleanup
for agent_dir in ~/.openclaw/agents/*/; do
agent=$(basename "$agent_dir " )
size=$(du -sh "$agent_dir /sessions/" 2>/dev/null | cut -f1)
count=$(find "$agent_dir /sessions/" -name "*.jsonl" 2>/dev/null | wc -l)
echo "$agent : $size ($count transcripts)"
done
openclaw doctor --fix
find ~/.openclaw/agents/*/sessions/ -name "*.jsonl" -mtime +30 -exec ls -lh {} \;
find ~/.openclaw/agents/*/sessions/ -name "*.jsonl" -mtime +30 -delete
B4. Backup BACKUP_DIR=~/openclaw-backup-$(date +%Y%m%d-%H%M%S)
mkdir -p "$BACKUP_DIR "
cp ~/.openclaw/openclaw.json "$BACKUP_DIR /"
[ -f ~/.openclaw/env ] && cp ~/.openclaw/env "$BACKUP_DIR /" || echo "No env file (tokens may be in systemd drop-in or plist)"
cp -r ~/.openclaw/agents "$BACKUP_DIR /"
cp -r ~/.openclaw/devices "$BACKUP_DIR /"
cp -r ~/.openclaw/workspace "$BACKUP_DIR /"
if [ "$(uname -s) " = "Linux" ]; then
cp ~/.config/systemd/user/openclaw-gateway.service "$BACKUP_DIR /" 2>/dev/null
cp -r ~/.config/systemd/user/openclaw-gateway.service.d "$BACKUP_DIR /" 2>/dev/null
elif [ "$(uname -s) " = "Darwin" ]; then
cp ~/Library/LaunchAgents/com.openclaw.gateway.plist "$BACKUP_DIR /" 2>/dev/null
fi
echo "Backup saved to $BACKUP_DIR "
B5. Tailscale Serve Check If OpenClaw uses Tailscale Serve as reverse proxy:
tailscale status
tailscale serve status
curl -s -o /dev/null -w "%{http_code}" http://localhost:$PORT /healthz || echo "Gateway not reachable on localhost"
tailscale serve reset
tailscale serve https / http://localhost:$PORT
tailscale serve status
Reference
Troubleshooting Quick Index Symptom Path Gateway won't start A1 → A2 → A3 → A5 Gateway crashed A2 (logs) → A4 (resources) → A3 (config) → A5 (restart) Config broken after edit A3 → A5 Disk filling up B3 After upgrade something broke B2 (rollback) Tailscale not proxying B5
openclaw doctor ReferenceFlag Effect (none) Interactive health check --fixApply safe repairs (orphan cleanup, stale locks) --forceAggressive repairs (may overwrite custom service config) --deepScan system for extra gateway installs --non-interactiveNo prompts, safe migrations only
--fix repairs:--fix does NOT:--force), delete workspace files.
Key Commands Command Purpose openclaw statusQuick status: running, version, basic info openclaw doctorDeep health check: state, channels, plugins, skills openclaw doctor --fixHealth check + auto-repair safe issues openclaw gateway startStart gateway in foreground (for debugging) openclaw daemon installInstall as persistent service (systemd/launchd) openclaw daemon restartRestart the service openclaw config get <path>Read config value openclaw config set <path> <value>Write config value
Safety Rules
Always check logs before changing anything — understand the problem firstAlways backup before editing config — cp with timestamp suffixAlways validate JSON after editing — one bad comma kills the serviceNever print secrets — check env file exists, don't cat itNever delete workspace files — use trash if you must remove somethingAlways verify after restart — status + logs, don't assume it workedDestructive operations require confirmation — ask the user before wiping data
File Layout ~/.openclaw/
├── openclaw.json # Main config
├── openclaw.json.bak # Auto-backup
├── env # Environment variables (secrets)
├── logs/ # macOS: launchd log output
├── agents/ # Per-agent configs
│ └── <agent>/agent/
│ ├── auth-profiles.json
│ └── models.json
├── devices/
│ └── paired.json
├── workspace/ # Agent workspace
└── sessions/ # Session logs
# Linux:
~/.config/systemd/user/
├── openclaw-gateway.service
└── openclaw-gateway.service.d/
└── env.conf
# macOS:
~/Library/LaunchAgents/
└── com.openclaw.gateway.plist
