New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Computer Use

by Porabuild in Porabuild/Poracode

Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools.

Apache-2.0Auto-check passedProductivity & Automation

Install Computer Use

skills CLI
$ npx skills add Porabuild/Poracode --skill computer-use -a claude-code

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

GitHub CLI
$ gh skill install Porabuild/Poracode 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/Porabuild/Poracode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/plugins/computer-use/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
114
Token cost
~718 tokens
SKILL.md length
352 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools.

  • Works in 7 steps: Pick the exact window with list_apps or… → Inspect with get_window_state… → Call computer_use.enable immediately… → …
  • Visual workflows that require real windows
  • SKILL.md covers Workflow, Boundaries and Output
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Computer Use is an agent skill from Porabuild/Poracode. Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools. Use for visual workflows that require real windows; prefer Browser for web pages and a purpose-built connector or API when one can complete the task directly.

Its SKILL.md is about 720 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. It works with Linux and macOS. The repository describes itself as: One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and chat, any layout. The licence is Apache-2.0.

When your agent uses it

  • Visual workflows that require real windows
  • Prefer Browser for web pages and a purpose-built connector
  • API when one can complete the task directly

Example prompts

  • “/computer-use”

Workflow steps

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

  1. Pick the exact window with list_apps or list_windows. Call computer_use.api only for capability or permission status. If the app is not…
  2. Inspect with get_window_state (include_text:true; include_screenshot:false unless you need pixels or coordinates). Prefer invoke_element…
  3. Call computer_use.enable immediately before the first control action and keep it enabled across uninterrupted related steps.
  4. Act, then verify from the window. Prefer observe:"text"; use "screenshot" or "both" for visual checks. Reuse observation.state. Continue…
  5. Use perform only for a deterministic background element/value/key/text sequence against one window, with one final observation. After a…
  6. Use mode:"foreground" and activate_window only when the user asked for a takeover, and tell them immediately before taking over the real…
  7. Call computer_use.disable before asking the user for input, waiting on an external event, or finishing.

What it can do on your machine

Read from SKILL.md and the folder at commit bffd89d. 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 718 tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 352 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~718

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

The full file from Porabuild/Poracode at commit bffd89d, republished under its Apache-2.0 licence (© Porabuild). 352 words, ~718 tokens.

Download SKILL.mdSave it as .claude/skills/computer-use/SKILL.md (or your agent's skills folder).
name
computer-use
description
Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools. Use for visual workflows that require real windows; prefer Browser for web pages and a purpose-built connector or API when one can complete the task directly.

Computer Use

Use Poracode's computer_use MCP for tasks that require interacting with desktop applications or native windows. Do not use it for a web page when Browser or Chrome is the intended surface, or for a semantic operation that a safer purpose-built connector can perform.

Tree conventions, delivery.verified, refusals, and platform recovery live in the computer_use MCP instructions. Do not re-derive them here.

Workflow

  1. Pick the exact window with list_apps or list_windows. Call computer_use.api only for capability or permission status. If the app is not running, list_apps with query then launch_app.
  2. Inspect with get_window_state (include_text:true; include_screenshot:false unless you need pixels or coordinates). Prefer invoke_element or set_element_value over coordinates.
  3. Call computer_use.enable immediately before the first control action and keep it enabled across uninterrupted related steps.
  4. Act, then verify from the window. Prefer observe:"text"; use "screenshot" or "both" for visual checks. Reuse observation.state. Continue only after a successful delivery; follow a refused hint.
  5. Use perform only for a deterministic background element/value/key/text sequence against one window, with one final observation. After a partial failure, inspect before continuing; do not replay the batch.
  6. Use mode:"foreground" and activate_window only when the user asked for a takeover, and tell them immediately before taking over the real pointer and keyboard. A refusal is never the licence: a background_unavailable refusal means follow the hint to find_elements plus invoke_element or set_element_value. If no background route can do the job, stop and tell the user what you need instead of taking their desktop.
  7. Call computer_use.disable before asking the user for input, waiting on an external event, or finishing.
Show full SKILL.md (87 more words)Show less

Boundaries

  • Background actions leave the user's foreground window, pointer, and keyboard alone. Foreground actions take over the desktop.
  • Locked desktops, secure prompts, operating-system permission dialogs, passwords, and authentication surfaces require the user.
  • Do not type or expose secrets unless the user supplied them for that exact purpose.
  • Confirm before destructive changes or external communication unless the user already authorized the exact action.

Output

Report the application and window used, the verified final state, and any step requiring user interaction. Do not claim completion from input dispatch alone.

© Porabuild, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in resources/plugins/computer-use/skills/computer-use of Porabuild/Poracode.

Open the folder on GitHubat commit bffd89d

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 skillPorabuild/Poracode114—~718Automated safety check: PassApache-2.0
Open Computer UseiFurySt/open-codex-computer-use2.3k—~1.5kAutomated safety check: PassMIT
Waku Computer Useegoist/waku1.6k—~3.6kAutomated safety check: PassGPL-3.0
Browser MCP Agentantibrow/anti-detect-browser-skills9141 repos~4.2kAutomated safety check: WarnMIT
Drive Screencoleam00/skills670—~5.4kAutomated safety check: PassMIT
Gooeypi Computer Useam-will/gooey-pi940—~370Automated safety check: PassMIT

Similar skills

  • Open Computer Use

    iFurySt/open-codex-computer-use

    Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows.

    2.3k GitHub stars~1.5k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Waku Computer Use

    egoist/waku

    Control local macOS, Windows, and Linux apps through Waku Computer Use.

    1.6k GitHub stars~3.6k tokensUpdated 5 days ago
    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…

    914 GitHub starsUsed in 1 repo~4.2k tokens
    Productivity & AutomationAuto-check: warnings

  • Drive Screen

    coleam00/skills

    Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals.

    670 GitHub stars~5.4k tokensUpdated 20 days ago
    Productivity & AutomationAuto-check passed

  • Gooeypi Computer Use

    am-will/gooey-pi

    Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.

    940 GitHub stars~370 tokensUpdated 28 days ago
    Productivity & AutomationAuto-check passed

  • Computer Use

    johnson7788/MultiUserClaw

    Drive the user's desktop in the background — clicking, typing, scrolling, dragging — without stealing the cursor, keyboard focus, or switching virtual desktops / Spaces.

    327 GitHub starsUsed in 1 repo~2.8k tokens
    Productivity & AutomationAuto-check: warnings

More from Porabuild/Poracode

All 21 skills in this repo

  • Interactive Testing

    Porabuild/Poracode

    Run repeatable integration and smoke testing against the real Poracode Electron app through Chrome DevTools Protocol.

    114 GitHub stars~4.5k tokensUpdated today
    Auto-check: notes

  • Release Notes

    Porabuild/Poracode

    Write consistent, hand-written-looking changelog entries for a Poracode release.

    114 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Skill Creator Poracode

    Porabuild/Poracode

    Create a new reusable agent skill managed by Poracode. An agent skill from Porabuild/Poracode.

    114 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • App Controls

    Porabuild/Poracode

    Inspect and drive Poracode itself — the Terminal panel, other threads, projects, workspaces, git, pull requests, and schedules — through the poracode MCP.

    114 GitHub stars~745 tokensUpdated today
    Auto-check passed

  • Chrome Control

    Porabuild/Poracode

    Use the user's real Chrome tabs and signed-in sessions for visible browser workflows.

    114 GitHub stars~691 tokensUpdated today
    Auto-check passed

  • Provider Chat Smoke

    Porabuild/Poracode

    Smoke test real Poracode provider chat threads and ACP sessions end to end.

    114 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Computer Use

What does Computer Use do?

Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools. Computer Use is an agent skill from Porabuild/Poracode. Inspect and operate native Windows, macOS, or Linux applications through Poracode's desktop-control tools.

When should I use Computer Use?

Computer Use fits situations like: visual workflows that require real windows; prefer Browser for web pages and a purpose-built connector; API when one can complete the task directly.

How do I install Computer Use in Claude Code?

Run `npx skills add Porabuild/Poracode --skill computer-use -a claude-code`. Or copy the skill folder (resources/plugins/computer-use/skills/computer-use in Porabuild/Poracode) 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 Porabuild/Poracode --skill computer-use -a codex`. Or copy the skill folder (resources/plugins/computer-use/skills/computer-use in Porabuild/Poracode) 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 Porabuild/Poracode --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?

Computer Use is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Computer Use use?

About 718 tokens (SKILL.md is roughly 2.9k 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: Open Computer Use (iFurySt/open-codex-computer-use, 2.3k stars), Waku Computer Use (egoist/waku, 1.6k stars), Browser MCP Agent (antibrow/anti-detect-browser-skills, 914 stars) and Drive Screen (coleam00/skills, 670 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Computer Use?

Porabuild (a GitHub organization) maintains it in Porabuild/Poracode, which has 114 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

Source: Porabuild/Poracode on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.