computer-use
The computer-use skill provides a CLI interface for Orca to interact with desktop applications. It enables listing applications and windows, reading accessibility trees, capturing screenshots, and performing UI actions like clicking, typing, scrolling, and dragging.
Is computer-use safe to install?
Review the source first: our audit of computer-use's source files found 19 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands, interacts with local desktop applications, and can perform input actions like clicking and typing. It writes screenshot data to local files.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and power users who need to automate desktop application workflows or integrate Orca with local GUI-based software.
What can you do with it?
- Automating interactions with desktop applications like Spotify or Slack.
- Navigating web applications by controlling the host browser window.
- Extracting information from desktop UI elements via accessibility trees.
- Performing keyboard and mouse input sequences in local apps.
- Managing application window focus and state.
How good is this skill?
Quality score: 5/10. The documentation is highly technical, provides clear command examples, and includes a robust error-handling guide.
What does the skill file contain?
# Computer Use Use this skill for desktop UI through `orca computer`. When the requested target is a website or web app, operate the desktop browser app/window that contains the page. ## Preconditions - Prefer `orca computer ...`; on Linux, use `orca-ide computer ...` if `orca` is unavailable. In this Orca worktree, use `./config/scripts/orca-dev computer ...` only when testing the local dev runtime. - Prefer `--json`. Screenshot bytes are omitted from JSON and written to `screenshot.path`. - Do not push, submit forms, send messages, buy items, delete data, change account settings, or expos...
Frequently asked questions
How do I handle web applications?
Identify the desktop browser window containing the web app and use the browser's bundle ID with the computer-use commands.
What should I do if an element index is not found?
The index is likely stale. Run get-app-state again to retrieve the current accessibility tree and fresh indexes.
How do I avoid exposing secrets in shell history?
Use the --value-stdin flag with a pipe to pass sensitive text directly to the command.
Why is my screenshot capture failing?
The application might be hidden, minimized, off-screen, or lacking necessary permissions. Run orca computer permissions --id screenshots --json to check.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
agent-browser
506.7KAI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications
The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.
web-design-guidelines
440.2KDevelopers and designers who need to verify UI code compliance with interface standards
The web-design-guidelines skill audits UI code against Web Interface Guidelines. It fetches current rules from a remote source and compares them against specified local files.
image-to-video
355.0KDevelopers and users who need to automate video generation from images using the RunComfy platform
The image-to-video skill routes user requests to specific RunComfy animation models based on intent. It selects HappyHorse 1.0 I2V for general animation, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition. The skill executes the RunComfy CLI to process inputs and download generated video files.