Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
lybic-sandbox 0.1.3 - Updated the skill description to provide a clearer and more comprehensive explanation of Lybic Sandbox, highlighting its role in automation workflows, control, and observability. - No code or file changes; this release focuses on documentation and description improvements.
What This Skill Does
Lybic Sandbox provides disposable cloud computers (Windows, Linux, Android) that agents control via GUI actions, code execution, and file operations. Agents interact with the screen directly, enabling automation of apps that have no API. Execution can be monitored in real time, stopped, and replayed for debugging.
GUI-level control lets agents work with any application regardless of whether an API exists, filling the gap that browser automation and SDK-only tools leave for desktop and mobile workflows.
When to use it
- Automating a legacy Windows desktop app with no API
- Running untrusted scripts in an isolated cloud environment
- Testing Android mobile apps without a physical device
- Processing data files in a clean Linux environment
- Debugging an automation run by replaying its execution
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: automate login to a Windows desktop app and export a report
- 1Creates a Windows sandbox with the specified shape
- 2Takes a screenshot to observe the current screen state
- 3Clicks the username field using fractional coordinates and types credentials
- 4Presses Enter and waits for the app to load
- 5Navigates to the export menu, clicks the export button, and confirms the file is saved
Report file saved in the sandbox, ready for download or further processing
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.