← Back to Skills Marketplace
fangbb-coder

connect-to-another-openclaw

by fangbb-coder · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
94
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install connect-to-another-openclaw
Description
Connect to and manage another OpenClaw server remotely. Check status, sync skills, restart gateway, and monitor channels.
README (SKILL.md)

Connect to Another OpenClaw

What This Skill Does

Provides a unified interface to connect to a remote OpenClaw server via SSH, perform health checks, manage skills, and troubleshoot common issues like port conflicts.

Prerequisites

  1. SSH Access to the remote machine:
    • SSH private key file (recommended) OR password access
    • Remote user must have sudo/root privileges
    • Remote machine must have OpenClaw installed
  2. SkillHub on both local and remote (for skill sync)
  3. Network connectivity (port 22 SSH)

Primary Workflow

1. Connect and Check Status

connect-openclaw --host \x3Cyour-remote-host> --action status

Important: Replace \x3Cyour-remote-host> with your actual remote server IP or domain (e.g., 192.168.1.100 or myserver.com). This is a required placeholder.

This will:

  • Test SSH connectivity
  • Check OpenClaw Gateway status
  • List active channels (QQBot, etc.)
  • Show recent sessions

2. Fix Common Issues

connect-openclaw --host \x3Cyour-remote-host> --action fix-port

Automatically:

  • Detect port conflicts on gateway port (default 18790)
  • Kill conflicting processes (SSH tunnels, test services)
  • Restart OpenClaw gateway
  • Verify recovery

3. Sync Skills

# See differences
connect-openclaw --host \x3Cyour-remote-host> --action diff

# Install remote's missing skills to local
connect-openclaw --host \x3Cyour-remote-host> --action sync-to-local

# Install local's missing skills to remote (if remote has SkillHub)
connect-openclaw --host \x3Cyour-remote-host> --action sync-to-remote

4. Send Message via Remote QQBot

connect-openclaw --host \x3Cyour-remote-host> --action send-qqbot \
  --session "agent:main:qqbot:direct:..." \
  --message "Hello from local OpenClaw"

Commands Reference

Command Description
status Full health check of remote OpenClaw
fix-port Auto-fix port 18790 conflicts
diff Compare local vs remote skills
sync-to-local Install remote-only skills to local
sync-to-remote Push local-only skills to remote
list-skills List all skills on remote
list-channels List configured channels
list-sessions Show active sessions
tail-logs Tail OpenClaw logs filtered by channel
test-connection Simple SSH test

Configuration

The skill uses these environment variables (optional):

Variable Purpose Default
CONNECT_OPENCLAW_SSH_KEY Path to SSH private key ~/.ssh/id_rsa
CONNECT_OPENCLAW_USER Remote username root
CONNECT_OPENCLAW_PORT SSH port 22
CONNECT_OPENCLAW_GATEWAY_PORT Remote OpenClaw port 18790

You can also pass these as CLI flags:

connect-openclaw --host example.com --user admin --key ~/.ssh/mykey.pem --action status

Examples

Quick diagnostic

connect-openclaw --host \x3Cyour-remote-host> --action status

Fix port conflict and restart

connect-openclaw --host \x3Cyour-remote-host> --action fix-port

Compare skills before syncing

connect-openclaw --host \x3Cyour-remote-host> --action diff

One-way sync (remote → local)

connect-openclaw --host \x3Cyour-remote-host> --action sync-to-local

Installation

If not already installed, run:

skillhub install Connect_to_another_openclaw

Or clone this repository to ~/.openclaw/workspace/skills/Connect_to_another_openclaw/.

Requirements

  • Python 3.9+ (or Node.js version if implemented in JS)
  • paramiko (Python SSH library) or native ssh command
  • Access to remote shell

Troubleshooting

Problem Solution
SSH connection failed Check key permissions (chmod 600), network, and authorized_keys
SkillHub not found on remote Install SkillHub on remote first
Permission denied Ensure remote user has sudo/root and correct key
Port still in use after fix Manually check with lsof -i :18790 and kill processes

Notes

  • Always test with --action test-connection first
  • fix-port will kill processes matching ssh -N.*18790 and voice-bridge-light
  • Skill sync uses SkillHub CLI; ensure it's installed on both sides
  • For safety, sync-to-remote prompts before each installation (use --yes to auto-confirm)

Version: 1.0.0 Author: 小李 (基于 2026-03-28 实践经验) License: MIT

Usage Guidance
This skill legitimately connects to remote OpenClaw servers over SSH and will execute commands that can kill processes, restart services, and install skills on the remote host—so only use it against systems you control and trust. Before installing or running: - Prefer using a non-root administrative user where possible and avoid leaving the default root path (/root/...) if you are not root. - Use a dedicated SSH key and keep its permissions tight (chmod 600). The code sets StrictHostKeyChecking=no which disables host key verification—consider running initial SSH manually to verify host keys or modify the tool if you need strict verification. - Understand that sync-to-remote can trigger remote SkillHub installs (which will install code on the remote machine). Review what will be installed and avoid auto-confirm (--yes) unless you trust the remote SkillHub index. - For sensitive environments, run test-connection first, inspect local_skills_file used by diff, and consider auditing the remote commands the skill runs (ls, lsof/ss, pkill, system/service restarts, tail) to ensure they meet your operational policies.
Capability Analysis
Type: OpenClaw Skill Name: connect-to-another-openclaw Version: 1.0.0 The skill provides remote administration of OpenClaw servers via SSH but contains critical security vulnerabilities. Specifically, main.py is vulnerable to shell injection in the sync-to-local and install_skill functions because it uses os.system and unsanitized string concatenation with remote input. It also disables SSH host key verification (StrictHostKeyChecking=no), exposing the user to man-in-the-middle attacks. While these appear to be unintentional flaws rather than intentional malware, the combination of high-privilege requirements (root access, SSH keys) and poor input sanitization poses a significant risk.
Capability Assessment
✓ Purpose & Capability
The name/description (remote OpenClaw management) matches what the files implement: SSH-based status checks, port fixes, skill listing/sync, log tailing, and gateway restarts. Required capabilities (SSH access, SkillHub on remote) are appropriate for the stated functionality.
ℹ Instruction Scope
SKILL.md and main.py instruct the agent to run many remote shell commands (ls, lsof/ss, pkill, openclaw gateway restart, tail, and SkillHub installs). These actions are within the stated scope but involve running privileged operations on the remote host (killing processes, restarting services, installing skills). The skill also reads a local skills file (default /root/.openclaw/workspace/local_skills.txt) for diffs; users should be aware of that path and permissions.
✓ Install Mechanism
There is no install spec and the package is delivered as code (main.py + docs). No external downloads or installers are invoked by the skill itself. This is the lower-risk delivery model for this type of tool.
✓ Credentials
The skill declares optional environment variables for SSH key, user, and ports which align with its SSH-based function. It does not request unrelated credentials. The default local skills file path and default to root user are somewhat heavy-handed but coherent with remote admin tasks.
✓ Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide agent settings. It executes on demand and relies on SSH to a user-specified host.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install connect-to-another-openclaw
  3. After installation, invoke the skill by name or use /connect-to-another-openclaw
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: Connect and manage remote OpenClaw servers via SSH. - Provides remote status checks, troubleshooting (such as auto-fixing gateway port conflicts), and OpenClaw health monitoring. - Enables comparing and syncing skills between local and remote servers using SkillHub. - Supports sending messages via remote QQBot channels. - Offers detailed CLI and environment variable configuration options. - Includes troubleshooting guidance and example commands for common tasks.
Metadata
Slug connect-to-another-openclaw
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is connect-to-another-openclaw?

Connect to and manage another OpenClaw server remotely. Check status, sync skills, restart gateway, and monitor channels. It is an AI Agent Skill for Claude Code / OpenClaw, with 94 downloads so far.

How do I install connect-to-another-openclaw?

Run "/install connect-to-another-openclaw" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is connect-to-another-openclaw free?

Yes, connect-to-another-openclaw is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does connect-to-another-openclaw support?

connect-to-another-openclaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created connect-to-another-openclaw?

It is built and maintained by fangbb-coder (@fangbb-coder); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments