agentleFS
soulmachinesoulmachine/skills/openclaw-diagnose/SKILL.md

openclaw-diagnose

Skill3 starsChanged yesterdayMITView on GitHub

Diagnose and fix OpenClaw gateway and node host issues. Use when openclaw services have warnings, connection failures, pairing errors, or port conflicts.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 4 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user asks you to diagnose or fix OpenClaw gateway/node issues, follow this structured investigation.

    line 9
  2. Distinctive:

    Run these in parallel:

    line 13
  3. Distinctive:

    Look for these common issues:

    line 24
  4. Very specific:

    Check if both ai.openclaw.gateway and ai.openclaw.node are registered as LaunchAgents

    line 27
  5. Very specific:

    Use launchctl print gui/$(id -u)/<label> to inspect each service

    line 28
  6. Very specific:

    Use lsof -iTCP:<port> -sTCP:LISTEN -P to confirm which process owns the port

    line 29
  7. Very specific:

    Check ~/.openclaw/logs/node.err.log for pairing required or ECONNREFUSED

    line 33
  8. Very specific:

    If the node shows "pairing required", run openclaw nodes pending to find the pending request

    line 34
  9. Very specific:

    Check if gateway is listening: lsof -iTCP:<port> -sTCP:LISTEN -P

    line 40
  10. Very specific:

    If gateway is down: openclaw gateway restart

    line 41
  11. Distinctive:

    After taking corrective action, confirm health:

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OpenClaw Diagnose

When the user asks you to diagnose or fix OpenClaw gateway/node issues, follow this structured investigation.

Step 1: Gather status

Run these in parallel:

openclaw gateway status
openclaw node status
openclaw nodes status
openclaw nodes pending

Step 2: Analyze warnings

Look for these common issues:

Multiple gateway-like services detected

  • Check if both ai.openclaw.gateway and ai.openclaw.node are registered as LaunchAgents
  • Use launchctl print gui/$(id -u)/<label> to inspect each service
  • Use lsof -iTCP:<port> -sTCP:LISTEN -P to confirm which process owns the port
  • The gateway listens on the port; the node host connects to the gateway on that port — they do NOT conflict

Pairing required errors

  • Check ~/.openclaw/logs/node.err.log for pairing required or ECONNREFUSED
  • If the node shows "pairing required", run openclaw nodes pending to find the pending request
  • Approve with: openclaw nodes approve <requestId>
  • Pairing requests expire quickly — if approval fails with "unknown requestId", restart the node (openclaw node restart) and immediately re-check pending + approve

ECONNREFUSED errors

  • The gateway may not be running yet when the node starts
  • Check if gateway is listening: lsof -iTCP:<port> -sTCP:LISTEN -P
  • If gateway is down: openclaw gateway restart
  • The node has KeepAlive: true so it will automatically reconnect once the gateway is up

Step 3: Verify fix

After taking corrective action, confirm health:

openclaw nodes status    # Should show: paired · connected
openclaw nodes pending   # Should show: No pending pairing requests
tail -5 ~/.openclaw/logs/node.err.log  # Check for new errors

Key architecture notes

  • Gateway (ai.openclaw.gateway): WebSocket server that listens on a port (default 18789)
  • Node host (ai.openclaw.node): Client that connects to the gateway via WebSocket to register capabilities (browser, system commands)
  • The --host and --port flags on openclaw node run specify the gateway address to connect to, not a port to bind
  • One gateway supports multiple nodes — running both on the same machine is the normal setup
  • Node plist is at ~/Library/LaunchAgents/ai.openclaw.node.plist
  • Gateway plist is at ~/Library/LaunchAgents/ai.openclaw.gateway.plist
  • Node logs: ~/.openclaw/logs/node.log and ~/.openclaw/logs/node.err.log

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.