Agent skill

Computer

by iii-hq in iii-hq/workers

Drive a full desktop computer over the iii bus: start a session, see the screen as an image, and click, type, and scroll by coordinate.

Apache-2.0Auto-check passed

Install Computer

skills CLI
$ npx skills add iii-hq/workers --skill computer -a claude-code

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

GitHub CLI
$ gh skill install iii-hq/workers computer --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/iii-hq/workers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/computer/skills .claude/skills/computer && 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
GitHub stars
113
Token cost
~1.1k tokens
SKILL.md length
597 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Drive a full desktop computer over the iii bus: start a session, see the screen as an image, and click, type, and scroll by coordinate.

  • Works in 2 steps: Register a handler:… → Register the trigger
  • SKILL.md covers When to Use, Boundaries, Functions and Keeping context small, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Computer is an agent skill from iii-hq/workers. Drive a full desktop computer over the iii bus: start a session, see the screen as an image, and click, type, and scroll by coordinate. Reach for it when a task needs to operate a real GUI app or whole desktop, not just a web page.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is Apache-2.0.

Example prompts

  • “/computer”

Workflow steps

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

  1. Register a handler: registerFunction('mywatcher::on-desktop', handler).
  2. Register the trigger

What it can do on your machine

Read from SKILL.md and the folder at commit 72ae6ab. 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 (its code samples are typescript).

    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 loads about 1.1k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 597 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 iii-hq/workers at commit 72ae6ab, republished under its Apache-2.0 licence (© iii-hq). 597 words, ~1,148 tokens.

Download SKILL.mdSave it as .claude/skills/computer/SKILL.md (or your agent's skills folder).
name
computer
description
Drive a full desktop computer over the iii bus: start a session, see the screen as an image, and click, type, and scroll by coordinate. Reach for it when a task needs to operate a real GUI app or whole desktop, not just a web page.

computer

The computer worker turns a live desktop into iii functions. Start a session with neither image nor endpoint to drive the local machine this worker runs on (unless the operator configured a default image or endpoint, which is resolved first), pass an image to boot a sandboxed desktop, or an endpoint to drive a remote one. Take a screenshot to see the screen, then act on it by pixel coordinate: the screenshot is the source of truth for where things are, and computer::act clicks and types at those coordinates. The session stays alive, so you can act, screenshot the result, and act again.

Sessions usually survive a worker restart (it reconnects them best-effort, so an id can still go away — start a new session if one does) and cost one driver connection each; the configured session cap is small. Stop sessions when a task is done. Screenshots are large; take one when you need to see the screen, not after every action.

When to Use

  • Operating a desktop GUI application that is not a web page (an installer, a native app, a settings panel).
  • End-to-end tasks that span the whole screen: move a window, drag between apps, use a system dialog.
  • Watching the effect of a change on screen: run the command with the shell worker, then computer::screenshot to see the result.

Boundaries

  • Web-only tasks belong to the browser worker (a real Chromium tab with an accessibility outline and page console) or web::fetch for a one-shot page. Do not start a desktop session just to open a URL.
  • Shell and files are not this worker's job; computer only sees the screen and drives the cursor. Reach for shell::exec / shell::fs::* when the session is native (the desktop is that host), sandbox::exec / sandbox::fs for a sandboxed desktop, and the guest's own executor for a remote one. shell always runs on the worker's host, not inside a guest.
  • With neither argument it drives whatever the configuration defaults to, and the local machine when nothing is configured; an image boots a sandboxed desktop through the iii-sandbox worker; an endpoint connects to a desktop somebody else booted.
  • computer::screencast::* and computer::frame are console-UI plumbing, not agent surface.
  • Coordinates are integer pixels, top-left origin, in the space of the most recent screenshot. Re-screenshot after the screen changes before acting.
Show full SKILL.md (214 more words)Show less

Functions

  • computer::sessions::start — connect a desktop session; returns the session_id every session-scoped function needs (all but computer::sessions::list and computer::displays), plus the screen size.
  • computer::sessions::list — live sessions with endpoint, OS, and screen.
  • computer::sessions::stop — stop a session; idempotent.
  • computer::screenshot — the desktop as a viewable image; how you see the screen before acting.
  • computer::observe — screenshot plus, on macOS guests, the accessibility tree (include_a11y: true).
  • computer::act — click, right_click, double_click, move, drag and scroll are addressed by pixel coordinates; type, press and hotkey carry their own text or keys and land wherever the desktop's focus is.

Keeping context small

Desktop screenshots are large and land in the transcript, so a few careless captures fill the context window. Screenshot when you need to see the screen, not reflexively after each action; a computer::act returns a short confirming detail on its own. Reuse one session across steps and stop it when done.

Reactive triggers

Bind a computer::* trigger when another function should react to session activity instead of polling. The types: computer::session-started (payload carries endpoint, os, screen) and computer::session-stopped (payload carries reason). Both accept an optional session_id equality filter.

How to bind
  1. Register a handler: registerFunction('mywatcher::on-desktop', handler).
  2. Register the trigger:
typescript
iii.registerTrigger({
  type: 'computer::session-stopped',
  function_id: 'mywatcher::on-desktop',
  config: { session_id: 'c1' },
})

Omit session_id to receive events for all sessions. For event payload shapes, call get function info on the trigger type.

© iii-hq, 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 computer/skills of iii-hq/workers.

Open the folder on GitHubat commit 72ae6ab

Compare with similar skills

Computer 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Computer this skilliii-hq/workers113—~1.1kAutomated safety check: PassApache-2.0
Ito Computeaffaan-m/ECC275k1 repos~1.7kAutomated safety check: PassMIT
Senior Computer Visiondavila7/claude-code-templates32k3 repos~1.4kAutomated safety check: PassMIT
Senior Computer Visionalirezarezvani/claude-skills28k2 repos~3.2kAutomated safety check: PassMIT
Codewhale Computer Use Controllercodewhale-hq/Codewhale41k—~1.4kAutomated safety check: PassMIT
Feishu Driveopenclaw/openclaw392k—~375Automated safety check: PassMIT

Similar skills

  • Ito Compute

    affaan-m/ECC

    Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately…

    275k GitHub starsUsed in 1 repo~1.7k tokens
    Business, Finance & HRAuto-check passed
  • Senior Computer Vision

    davila7/claude-code-templates

    World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.

    32k GitHub starsUsed in 3 repos~1.4k tokens
    AI & LLM EngineeringAuto-check passed
  • Senior Computer Vision

    alirezarezvani/claude-skills

    Computer vision engineering skill for object detection, image segmentation, and visual AI systems.

    28k GitHub starsUsed in 2 repos~3.2k tokens
    AI & LLM EngineeringAuto-check passed
  • Codewhale Computer Use Controller

    codewhale-hq/Codewhale

    Operates desktop apps and isolated or disposable browsers on registered computers through an observe, act, verify loop, separate from driving the user's own signed-in Chrome.

    41k GitHub stars~1.4k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Feishu Drive

    openclaw/openclaw

    Feishu cloud-storage and comment workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~375 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • GCP Compute

    sickn33/agentic-awesome-skills

    Manage Compute Engine instances and instance templates. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~2.6k tokens
    DevOps & CloudAuto-check passed

More from iii-hq/workers

All 19 skills in this repo
  • Cron

    iii-hq/workers

    Schedule any registered function on a 6- or 7-field cron expression with the standalone cron worker.

    113 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Email

    iii-hq/workers

    Send and read email from the iii engine — SMTP send, IMAP read, and real-time IDLE push as a subscribable trigger type.

    113 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • HTTP

    iii-hq/workers

    Expose registered functions as HTTP endpoints with the standalone http worker.

    113 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Kanban

    iii-hq/workers

    File-backed kanban board: create, read, move and comment on tickets by key or uuid, assign agent profiles, and wake on comments through the kanban:comment trigger instead of polling.

    113 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Pubsub

    iii-hq/workers

    Fire-and-forget topic pub/sub: broadcast an event with publish and every matching subscribe trigger receives it.

    113 GitHub stars~989 tokensUpdated today
    Auto-check passed
  • Release Sync

    iii-hq/workers

    Organize worker release tags into Linear release waves — one team document plus one release/<date label per same-day batch of worker releases, with shipped MOT issues labeled and linked.

    113 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Questions about Computer

What does Computer do?

Drive a full desktop computer over the iii bus: start a session, see the screen as an image, and click, type, and scroll by coordinate. Computer is an agent skill from iii-hq/workers. Drive a full desktop computer over the iii bus: start a session, see the screen as an image, and click, type, and scroll by coordinate.

How do I install Computer in Claude Code?

Run `npx skills add iii-hq/workers --skill computer -a claude-code`. Or copy the skill folder (computer/skills in iii-hq/workers) into .claude/skills/computer in your project. Claude Code loads it when a task matches its description.

How do I install Computer in Codex?

Run `npx skills add iii-hq/workers --skill computer -a codex`. Or copy the skill folder (computer/skills in iii-hq/workers) into .agents/skills/computer in your project. Codex loads it when a task matches its description.

Can I use Computer 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 iii-hq/workers --skill computer -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, .gemini/skills/computer, .github/skills/computer and .opencode/skills/computer in your project.

What does Computer need to run?

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

Does Computer 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 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?

Computer 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?

About 1.1k tokens (SKILL.md is roughly 4.6k 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?

Skills that share tags, products or a category with Computer: Ito Compute (affaan-m/ECC, 275k stars), Senior Computer Vision (davila7/claude-code-templates, 32k stars), Senior Computer Vision (alirezarezvani/claude-skills, 28k stars) and Codewhale Computer Use Controller (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Computer?

iii-hq (a GitHub organization) maintains it in iii-hq/workers, which has 113 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.

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