A versatile file transfer tool that enables AI agents to copy directories and files from remote Windows, macOS, or Linux systems to a local Mac via SSH and SCP.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install remote-copy
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install remote-copy using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Remote Copy skill is designed to simplify cross-platform file transfers between your local Mac and remote machines over a network. Whether pulling research datasets from a Linux node, grabbing documentation from another Mac, or migrating system assets from a Windows environment, this tool handles the heavy lifting. It forms a key part of the catalog of Openclaw Skills, enabling AI agents to seamlessly navigate distributed architectures.
What makes this tool exceptionally reliable is its built-in automation. It automatically transforms drive paths across different operating systems, conducts diagnostic checks for connection timeouts, and executes advanced tar pipelines to eliminate encoding issues (such as converting Windows GBK paths into clean UTF-8).
To unlock this tool and enhance your workflows using Openclaw Skills, configure the host and remote environments using the instructions below.
Install the required session helper for password authentication:
brew install sshpass
Run PowerShell as Administrator to install and activate OpenSSH Server:
Get-WindowsCapability -Online | Where-Object Name -like 'OpenSSH*'
Add-WindowsCapability -Online -Name OpenSSH.Server~~~~0.0.1.0
Start-Service sshd
Set-Service -Name sshd -StartupType Automatic
New-NetFirewallRule -Name sshd -DisplayName 'OpenSSH Server' -Enabled True -Direction Inbound -Protocol TCP -Action Allow -LocalPort 22
Enable Remote Login via the terminal:
sudo systemsetup -setremotelogin on
Ensure the SSH service is running and the port is open:
sudo apt update && sudo apt install openssh-server -y
sudo systemctl start sshd
sudo systemctl enable sshd
sudo ufw allow 22/tcp
| Parameter | Required | Default Value | Description |
|---|---|---|---|
remote_ip |
Yes | - | Target IP address |
remote_path |
Yes | - | Source path (supports Windows, macOS, Linux structures) |
remote_user |
No | Prompt or vip |
User account for SSH access |
local_dest |
No | ~/remote_data/{ip}/ |
Target directory on local system |
| OS Type | Original Path Example | Translated SSH Path |
|---|---|---|
| Windows | F:\\company\\data |
/f/company/data |
| macOS | /Users/john/projects |
/Users/john/projects |
| Linux | /home/user/dataset |
/home/user/dataset |
When a transfer finishes, a report showing the local landing folder, total size, and copied item count is outputted.
sshpass on-the-fly without permanently saving plain text passwords to disk.ssh-copy-id.rsync for volumes larger than 1GB to guarantee transfer resume capability on network drops.Loading
An advanced competitive intelligence agent skill that automates deep product benchmarking, SWOT strategies, and actionable business roadmaps.

An automated engineering skill that converts raw source code, URLs, or endpoint descriptions into enterprise-ready OpenAPI 3.0 standards, complete with multi-language SDKs and mock servers.

An API-driven, token-optimized content extraction skill designed to allow AI agents to search, retrieve, and summarize high-quality Zhihu content without rendering a heavy browser.

A powerful browser automation CLI designed for AI agents to interact with web pages, extract dynamic JS content, bypass interactive verification, and handle multi-account sessions locally.

An AI-powered Business Model Canvas validation system designed to map business concepts, stress-test unit economics, and formulate actionable MVP strategies.

Doubt-Driven Development is an Openclaw skill that introduces structured adversarial reviews to challenge non-trivial AI decisions, preventing agent overconfidence and catching errors early.








































