New to Claude Skills? Learn how to install them →

ifuryst on GitHub

Open Computer Use

Free

Manage desktop applications via a unified CLI.

Get this skill

Free · Opens the source repo

What Open Computer Use does

Open Computer Use provides a platform-neutral command-line interface (CLI) and standard input/output (stdio) MCP server for managing desktop applications on macOS, Linux, and Windows. This skill is particularly useful for developers and designers who require a consistent way to interact with desktop environments across different operating systems. It allows users to install, verify, troubleshoot, configure, and operate Open Computer Use through its native CLI commands and MCP server functionalities.

The skill supports a range of core commands that enable users to perform various actions such as listing applications, retrieving application states, and simulating user interactions like clicks and text input. The CLI commands are designed to be straightforward, making it easy for users to integrate them into their workflows. For example, commands like list_apps and get_app_state allow users to gather necessary information about the current desktop environment before executing further actions.

For macOS users, it is essential to ensure that the system version is 14.0 or later, as older versions are incompatible with the runtime. The skill also emphasizes the importance of handling permissions correctly, especially for accessibility and screen recording, which are critical for GUI automation tasks. Users can leverage the open-computer-use doctor command to check their setup before executing any GUI tasks, ensuring a smoother experience.

This skill is ideal for automation tasks that require interaction with desktop applications, making it suitable for developers looking to streamline their processes or designers aiming to automate repetitive tasks. However, users should be cautious about its limitations, particularly regarding the need for appropriate permissions and the requirement that commands run within a logged-in desktop session.

When to use it

Use this skill when you need to automate interactions with desktop applications or troubleshoot issues related to the Open Computer Use CLI.

When not to use it

Avoid this skill if your work does not involve desktop application automation or if you are using an unsupported version of macOS.

What you can build with it

Automating Repetitive Tasks

Use Open Computer Use to automate repetitive interactions with desktop applications, such as filling out forms or processing data.

Troubleshooting Application Issues

Quickly verify and troubleshoot application states with the `get_app_state` command to identify problems before executing tasks.

Cross-Platform Application Management

Manage applications seamlessly across macOS, Linux, and Windows, ensuring a consistent approach regardless of the operating system.

How to install Open Computer Use

View source

1. Install with the skills CLI

npx skills add ifuryst/open-codex-computer-use/open-computer-use --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by ifuryst

Open Computer Use

Overview

Open Computer Use exposes Computer Use as a local CLI and stdio MCP server. It is not Codex.app-specific; adapt the commands and MCP config to the agent runtime you are operating in.

The macOS runtime requires macOS 14.0 or later. Windows and Linux use their own platform runtimes and are not subject to this macOS minimum.

It supports the same core tool surface across macOS, Linux, and Windows: list_apps, get_app_state, click, perform_secondary_action, scroll, drag, type_text, press_key, and set_value.

Core Workflow

  1. On macOS, run sw_vers -productVersion before invoking the CLI and require macOS 14.0 or later. On older versions, explain that the runtime cannot launch; do not recommend doctor or permission changes as a fix for binary incompatibility.
  2. Check the CLI is installed with open-computer-use -h or ocu -h. If installation or setup is missing, read references/installation.md.
  3. On supported macOS versions, run open-computer-use doctor before the first real GUI task. If permissions are missing, ask the user to approve Accessibility and Screen Recording in the onboarding UI.
  4. Inspect available apps before acting: open-computer-use call list_apps.
  5. Capture current UI state with open-computer-use call get_app_state --args '{"app":"TextEdit"}'. The default state is usually enough for UI operation.
  6. When the task needs longer semantic text, such as chat history, email bodies, document text, or long form content, call get_app_state with text_limit: 1000 or text_limit: "max".
  7. When visible long pages or lists appear incomplete even after scrolling, call get_app_state with a larger max_tree_nodes or max_tree_depth.
  8. Prefer element-targeted actions using element_index from the latest get_app_state result.
  9. For multi-step CLI work, use open-computer-use call --calls '<json-array>' so one process can reuse the latest element index mapping.
  10. For agent runtimes that support local MCP servers, configure open-computer-use mcp or ocu mcp and call the exposed Computer Use tools directly. Read references/usage.md.
  11. If communication, permission, or desktop-session access fails, read references/troubleshooting.md.

Operating Rules

  • Treat the target desktop as the user's real session. Do not inspect password managers, unrelated private content, or sensitive apps unless the user explicitly asked for that task.
  • Ask before sending, deleting, purchasing, approving, uploading, or making other externally visible changes.
  • Do not assume Codex.app plugin helpers are available. Use the installed open-computer-use / ocu CLI or an explicit MCP config.
  • Always run get_app_state before using element_index; do not guess indexes across sessions or after large UI changes.
  • Prefer semantic actions and set_value for editable controls. Use coordinate click, scroll, and drag only when the element tree does not expose a safer target.
  • On macOS, do not enable OPEN_COMPUTER_USE_ALLOW_GLOBAL_POINTER_FALLBACKS=1 unless the user explicitly requested click_method: "global" or other diagnostic behavior that may move the real pointer.
  • On Windows and Linux, confirm the command is running inside the logged-in desktop session before assuming GUI automation is available.

Common CLI Actions

open-computer-use -h
ocu -h
open-computer-use doctor
open-computer-use call list_apps
ocu call list_apps
open-computer-use call get_app_state --args '{"app":"TextEdit"}'
open-computer-use call get_app_state --args '{"app":"TextEdit","text_limit":1000}'
open-computer-use call get_app_state --args '{"app":"TextEdit","text_limit":"max"}'
open-computer-use call get_app_state --args '{"app":"Google Chrome","max_tree_nodes":3000,"max_tree_depth":96}'
open-computer-use call click --args '{"app":"TextEdit","element_index":"0"}'
open-computer-use call type_text --args '{"app":"TextEdit","text":"Hello from Open Computer Use"}'

For a short sequence that reuses state in one process:

open-computer-use call --calls '[
  {"tool":"get_app_state","args":{"app":"TextEdit"}},
  {"tool":"press_key","args":{"app":"TextEdit","key":"Return"}}
]'

MCP Usage

For runtimes that can launch local MCP servers over stdio, use:

[mcp_servers.open_computer_use]
command = "open-computer-use"
args = ["mcp"]

Read references/usage.md for JSON config examples, direct tool-call patterns, and platform notes.

References

Frequently asked questions about Open Computer Use

Similar skills