A secure and robust Windows system command execution skill featuring four-level security and full multi-language output support.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install system-cmd
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install system-cmd using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is system_cmd?
The system_cmd skill is a specialized extension designed for Openclaw Skills that enables AI agents to interact directly with the Windows operating system. It provides a bridge between natural language prompts and low-level system commands, allowing for seamless execution of diagnostic and management tasks.
This skill is built with a heavy focus on security and usability, featuring a multi-layered defense system to prevent accidental system damage. By utilizing PowerShell and CMD with forced UTF-8 encoding, it ensures that all technical output, including Chinese characters, is rendered perfectly for the user. It is an essential tool for developers and administrators who need to bridge AI workflows with local system administration.
system_cmd Use Cases
- Running network diagnostics such as IP configuration and connectivity tests.
- Monitoring and managing active system processes and resource allocation.
- Querying detailed system specifications and hardware information.
- Automating routine file operations or service management via CLI commands.
- Troubleshooting server environments directly through an AI agent interface.
How system_cmd Works
- The user inputs a command via the /system_cmd interface.
- The skill checks for custom aliases defined in the config.json or predefined shorthand keys.
- The command undergoes a four-tier security evaluation: Safe, Normal, High-Risk, or Forbidden.
- If a command is High-Risk, the skill pauses to request explicit user confirmation via the --yes flag.
- The validated command is executed through PowerShell (or CMD for specific legacy operations) using UTF-8 encoding.
- The output is processed, truncated if it exceeds size limits, and returned as a formatted Markdown response.
system_cmd Setup
To integrate this into your Openclaw Skills environment, ensure you have the following structure and permissions:
# Navigate to your skills directory
mkdir system_cmd
# Place system_cmd.js in the scripts folder
# Initialize your configuration
touch system_cmd/config.json
Ensure that the Openclaw execution environment has sufficient administrative privileges to run commands like tasklist or systeminfo.
system_cmd Data Schema & Taxonomy
The skill manages its operations through a structured directory and configuration file:
| Component | Description |
|---|---|
| SKILL.md | Technical documentation and help system |
| scripts/system_cmd.js | Main logic, security filters, and execution engine |
| config.json | User-definable aliases and variable settings |
| references/commands.md | Comprehensive list of mapped commands and safety levels |
Config Schema:
pingDefaultTarget: Default IP or hostname for the ping alias.aliases: A key-value map for custom command shortcuts.
system_cmd Advanced Features
- Custom Alias System: Map complex CLI strings to simple triggers like 'ip' or 'process' in config.json.
- Variable Substitution: Inject dynamic values into aliases using the ${variable} syntax.
- Multi-Layer Protection: A sophisticated four-tier hierarchy ranging from 'Safe' (direct execution) to 'Forbidden' (absolute block).
- Intelligent Output Handling: Automatic encoding detection and buffer management (5MB) to handle large data streams without crashing.
- High-Risk Confirmation Workflow: Built-in safety gate for destructive commands like del or taskkill requiring explicit user intent.
SKILL.md
Loading
Related Openclaw Skills
Science Agent Compare
A specialized tool for comparing AI science agents side-by-side while resolving same-name project collisions within the ecosystem.
Science Agent Recommend
A comprehensive discovery engine that matches researchers with specialized AI agents and Openclaw Skills across 10 scientific categories.
Agent Memory Pro
An enterprise-grade 5-layer memory architecture for AI agents featuring intelligent routing, importance scoring, and multi-backend storage.
Paper-to-Tools
A research-focused skill that analyzes paper abstracts and methods to identify the specific AI agents and tools needed to reproduce or extend scientific analysis.
Wyndham Hotel Group Guide
A comprehensive digital guide for navigating the Wyndham Hotels & Resorts ecosystem, from luxury brands to loyalty rewards.
SMILES Profiling
A comprehensive chemical analysis tool that transforms a single SMILES string into a unified pharmacology and ADMET profile.
Featured*
