Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Control remote Windows machines via SSH. Use when executing commands on Windows, checking GPU status (nvidia-smi), running scripts, or managing remote Windows systems. Triggers on "run on Windows", "execute on remote", "check GPU", "nvidia-smi", "远程执行", "Windows 命令".
Control remote Windows machines via SSH. Use when executing commands on Windows, checking GPU status (nvidia-smi), running scripts, or managing remote Windows systems. Triggers on "run on Windows", "execute on remote", "check GPU", "nvidia-smi", "远程执行", "Windows 命令".
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Execute commands on remote Windows machines via SSH.
Set environment variables in ~/.openclaw/openclaw.json under skills.windows-remote.env: { "skills": { "windows-remote": { "env": { "WINDOWS_SSH_HOST": "192.168.1.100", "WINDOWS_SSH_PORT": "22", "WINDOWS_SSH_USER": "Administrator" } } } } Or export directly: export WINDOWS_SSH_HOST="192.168.1.100" export WINDOWS_SSH_PORT="22" export WINDOWS_SSH_USER="Administrator"
scripts/win-exec.sh "echo connected"
scripts/win-exec.sh "nvidia-smi"
scripts/win-exec.sh "powershell -Command 'Get-Process | Select-Object -First 10'"
scripts/win-exec.sh "python C:\\path\\to\\script.py"
Execute a single command on the remote Windows machine. scripts/win-exec.sh "<command>"
Quick GPU status check (nvidia-smi wrapper). scripts/win-gpu.sh scripts/win-gpu.sh --query # Compact output
Upload files to the remote machine via SCP. scripts/win-upload.sh <local-file> <remote-path>
Download files from the remote machine. scripts/win-download.sh <remote-path> <local-file>
scripts/win-exec.sh "tasklist | findstr ollama"
scripts/win-exec.sh "net start <service-name>"
scripts/win-exec.sh "python -c \"import torch; print(torch.cuda.is_available())\""
scripts/win-exec.sh "wmic logicaldisk get size,freespace,caption"
IssueSolutionConnection refusedCheck SSH service: Get-Service sshdPermission deniedVerify SSH key in ~/.ssh/authorized_keys or administrators_authorized_keysTimeoutCheck firewall rules, verify IP/portCommand not foundUse full path or check PATH on Windows
Use SSH keys instead of passwords Keep private keys secure (chmod 600) Consider using Tailscale for cross-network access
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.