← All skills

computer-use-agents

CommunityMIT

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.

The ZIP contains only this skill. It lives on GitHub Releases of the public orlandoneto/agent-skills repo — Ontoom is the showcase. A daily crawler refreshes the catalog.

How to install

  1. Download the ZIP and extract the skill folder.
  2. Cursor: .agents/skills/computer-use-agents/ or .cursor/skills/computer-use-agents/
  3. Claude Code: .claude/skills/computer-use-agents/
  4. Other AIs: .agents/skills/computer-use-agents/
cursorclaude-codecodexgeminiany

Source / credits: agent-skills-hub/agent-skills-hub

Other skills in this collection

Other collections

  • computer-vision-expert

    SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.

  • concise-planning

    Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

  • condense

    Maximize information density: preserve all instructions, remove prose filler.

  • container

    Host-side setup, configuration, customization, builds, migration, and troubleshooting for the Aerovato Container CLI. Use when working with Aerovato Container, settings.json, Dockerfile.User, build stages, V2-to-V3 migration, mounts, harnesses, tools, permissions, Docker, or Podman. Do not use it to expose host Container configuration inside managed containers.

  • content-engine

    Repurpose source assets into platform-native social content.

  • content-repurposing

    Turns one piece of content into multiple surfaces — blog post → Twitter/X thread → LinkedIn post → newsletter issue — matching each platform's conventions. Use when a user has shipped a long-form piece and wants to extract shorter variants for other channels, or is planning a content launch across multiple platforms.