Skill of Skills
📄 skillActivePromisinghigh

trycua/cua

by trycua

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

17.8k

Skill Type

📖 Library & API Reference

Quality Score

109/200

License

MIT

Forks

1.1k

Last Updated

Jun 11, 2026

Discovered

Apr 26, 2026

Validation

Passed

github.com/trycua/cua

Quality Breakdown

109/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
â—‹Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains extensive Docker container orchestration workflows for multiple systems (Android, Linux, Windows, XFCE) suggesting capability for autonomous system environment provisioning
  • Multiple CD/CI workflows for building and publishing containers to registries indicate automated deployment capabilities without apparent human approval gates
  • Presence of sandbox, agent, and computer automation components (py-agent, py-auto, py-computer-server) suggests autonomous operation and multi-agent orchestration patterns
  • Repository includes MCP server, computer server, and driver components that facilitate remote command execution and system control
  • Contains QEMU and virtualization-based automation workflows suggesting capability for spawning isolated execution environments
  • Extensive use of GitHub Actions workflows for automated builds, tests, and deployments across multiple programming languages and platforms