Agent skill

Computer Use

by QwenLM in QwenLM/qwen-code-examples

Control the local desktop using the computer MCP tool from computer-use-mcp.

No licenceAuto-check passedProductivity & Automation

Install Computer Use

skills CLI
$ npx skills add QwenLM/qwen-code-examples --skill computer-use -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install QwenLM/qwen-code-examples computer-use --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/QwenLM/qwen-code-examples.git skills-src && mkdir -p .claude/skills && cp -r skills-src/extensions/computer-use-vision/skills/computer-use .claude/skills/computer-use && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
computer-use
GitHub stars
143
Token cost
~632 tokens
SKILL.md length
322 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Control the local desktop using the computer MCP tool from computer-use-mcp.

  • Works in 5 steps: Observe first with computer action… → Prefer keyboard shortcuts and typed… → Use coordinate clicks only after a… → …
  • The user asks to operate local Mac/Windows apps
  • SKILL.md covers Operating Loop, Safety, Tool Notes and Platform Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Computer Use is an agent skill from QwenLM/qwen-code-examples. Control the local desktop using the computer MCP tool from computer-use-mcp. Use when the user asks to operate local Mac/Windows apps, inspect the screen, click UI, type text, press shortcuts, scroll, drag, or interact with native GUI software.

Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Desktop control and MCP servers. It works with Model Context Protocol and Qwen. The repository describes itself as: A collection of practical examples and best practices for Qwen Code.

When your agent uses it

  • The user asks to operate local Mac/Windows apps
  • Inspect the screen
  • Press shortcuts
  • Interact with native GUI software

Example prompts

  • “/computer-use”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Observe first with computer action get_screenshot.
  2. Prefer keyboard shortcuts and typed navigation when practical.
  3. Use coordinate clicks only after a screenshot confirms the target location.
  4. After every action, verify with another get_screenshot.
  5. Keep actions small and reversible.

What it can do on your machine

Read from SKILL.md and the folder at commit 0ece9fe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Computer Use loads about 632 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 322 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~632

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 322 words (~632 tokens).

“Use the computer MCP tool from the computer-use MCP server to operate the user's real local desktop.”

— opening of SKILL.md by QwenLM
name
computer-use

Read the full SKILL.md on GitHub

Files

Just SKILL.md in extensions/computer-use-vision/skills/computer-use of QwenLM/qwen-code-examples.

Open the folder on GitHubat commit 0ece9fe

Compare with similar skills

Computer Use next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Computer Use compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Computer Use this skillQwenLM/qwen-code-examples143—~632Automated safety check: PassNone
Linux Desktop Controlagent-sh/computer-use-linux663—~2.8kAutomated safety check: PassMIT
Browser MCP Agentantibrow/anti-detect-browser-skills9321 repos~4.2kAutomated safety check: WarnMIT
Isolated Linux Agent Workspaceagent-sh/agent-workspace-linux186—~2.1kAutomated safety check: PassMIT
Altic Studioaltic-dev/altic-mcp173—~3.3kAutomated safety check: PassApache-2.0
Windows CLIsbroenne/mcp-windows106—~1.8kAutomated safety check: PassMIT

Similar skills

  • Linux Desktop Control

    agent-sh/computer-use-linux

    Lets an agent observe and operate a local Linux desktop through the computer-use-linux MCP server or Pi tools: accessibility trees, screenshots, windows and input.

    663 GitHub stars~2.8k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Browser MCP Agent

    antibrow/anti-detect-browser-skills

    Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…

    932 GitHub starsUsed in 1 repo~4.2k tokens
    Productivity & AutomationAuto-check: warnings
  • Isolated Linux Agent Workspace

    agent-sh/agent-workspace-linux

    Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.

    186 GitHub stars~2.1k tokensUpdated 5 days ago
    Productivity & AutomationAuto-check passed
  • Altic Studio

    altic-dev/altic-mcp

    macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.

    173 GitHub stars~3.3k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Windows CLI

    sbroenne/mcp-windows

    Guidance for driving Windows desktop automation from the wincli command-line tool - the token-efficient entry point that mirrors the Windows MCP server.

    106 GitHub stars~1.8k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Amazon Workspaces Agent Access

    aws/agent-toolkit-for-aws

    Official

    Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation.

    2.8k GitHub stars~2.7k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

More from QwenLM/qwen-code-examples

All 9 skills in this repo
  • Dashboard Builder

    QwenLM/qwen-code-examples

    Build full-stack dashboard applications using React/Next.js + shadcn/ui + Tailwind CSS + Recharts + Express with customizable data sources.

    143 GitHub stars~3.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Auto PR

    QwenLM/qwen-code-examples

    Automated PR submission assistant, including code review, documentation generation, and PR creation

    143 GitHub stars~790 tokensUpdated 4 mo ago
    Auto-check passed
  • Codegraph QA

    QwenLM/qwen-code-examples

    Use CodeScope to analyze any indexed codebase via its graph database (neug) and vector index (zvec).

    143 GitHub stars~4.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Image Generation

    QwenLM/qwen-code-examples

    Image generation skill based on Alibaba Cloud DashScope, supporting the creation of high-quality hand-drawn or standard images from user descriptions.

    143 GitHub stars~568 tokensUpdated 4 mo ago
    Auto-check passed
  • Oss Styles

    QwenLM/qwen-code-examples

    为开源项目生成专业宣传视频,传入 {owner}/{repo} 参数 Triggers on "生成开源视频", "宣传视频", "oss video", "remotion video".

    143 GitHub stars~405 tokensUpdated 4 mo ago
    Auto-check passed
  • Browser Use

    QwenLM/qwen-code-examples

    Control browser pages using the Playwright MCP server. An agent skill from QwenLM/qwen-code-examples.

    143 GitHub stars~451 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Computer Use

What does Computer Use do?

Control the local desktop using the computer MCP tool from computer-use-mcp. Computer Use is an agent skill from QwenLM/qwen-code-examples. Control the local desktop using the computer MCP tool from computer-use-mcp.

When should I use Computer Use?

Computer Use fits situations like: the user asks to operate local Mac/Windows apps; inspect the screen; press shortcuts; interact with native GUI software.

How do I install Computer Use in Claude Code?

Run `npx skills add QwenLM/qwen-code-examples --skill computer-use -a claude-code`. Or copy the skill folder (extensions/computer-use-vision/skills/computer-use in QwenLM/qwen-code-examples) into .claude/skills/computer-use in your project. Claude Code loads it when a task matches its description.

How do I install Computer Use in Codex?

Run `npx skills add QwenLM/qwen-code-examples --skill computer-use -a codex`. Or copy the skill folder (extensions/computer-use-vision/skills/computer-use in QwenLM/qwen-code-examples) into .agents/skills/computer-use in your project. Codex loads it when a task matches its description.

Can I use Computer Use in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add QwenLM/qwen-code-examples --skill computer-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/computer-use, .gemini/skills/computer-use, .github/skills/computer-use and .opencode/skills/computer-use in your project.

What does Computer Use need to run?

SKILL.md names no scripts, command-line tools or credentials: Computer Use is instructions for the agent only.

Does Computer Use access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Computer Use safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Computer Use use?

No licence was found for Computer Use or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Computer Use use?

About 632 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Computer Use?

Skills that share tags, products or a category with Computer Use: Linux Desktop Control (agent-sh/computer-use-linux, 663 stars), Browser MCP Agent (antibrow/anti-detect-browser-skills, 932 stars), Isolated Linux Agent Workspace (agent-sh/agent-workspace-linux, 186 stars) and Altic Studio (altic-dev/altic-mcp, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Computer Use?

QwenLM (a GitHub organization) maintains it in QwenLM/qwen-code-examples, which has 143 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on May 19, 2026.

Source: QwenLM/qwen-code-examples on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.