Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Building agents that control a screen v1.0.0

Use this resource to design an agent that operates a computer through vision and clicks

New

  • 321 downloads
  • 210 likes
  • 219 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install computer-use-agent-design

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent designs an agent that interacts with a computer the way a person does: reading the screen, moving the cursor, clicking and typing. It covers the approaches of Anthropic, OpenAI and open-source alternatives, with a focus on isolation and security. A detailed guide sets out the limits of this method.

Mostly picked by

Updated November 2, 2026

Card for the “Building agents that control a screen” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • references/detailed-guide.md: full procedure and limits
  • SKILL.md: scope of use and implementation boundaries

Good fit for

  • You are automating an application that has no API
  • You are assessing the risks of an agent acting on a workstation

Not for

    Tags

    • agents
    • vision
    • security

    About

    You say

    “Design an agent that fills our billing form in an isolated environment.”

    Card for the “Building agents that control a screen” skill

    Skill published by sickn33 under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to design an agent that operates a computer through vision and clicks
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/detailed-guide.md56.9 KB
    • SKILL.md2.9 KB

    Origin and licence

    Listed unmodified

    Author
    sickn33
    Source
    github.com/sickn33/agentic-awesome-skills/tree/e9809578fd426a284af017c5db99f8eb6628e6ca/skills/computer-use-agents
    Licence
    MIT

    Notice

    « computer-use-agents » (sickn33, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.