agent-computer-use Eval report.

Task wording matches this skill metadata.

• Evaluate agent-computer-use before installing it in an agent workflow
• design-creative
• Local desktop workflows; Claude Code teams; builders willing to evaluate younger projects

Install handoff is available.

• npx skills add kortix-ai/agent-computer-use --skill agent-computer-use

standard package or runtime install path

• npx skills add kortix-ai/agent-computer-use --skill agent-computer-use

Good trust signals with a few areas worth checking before rollout.

• Strong shortlist
• 65 GitHub stars
• MIT

Needs review

• Financial research output is not financial advice; require human review before any live investment decision

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

• Test manually in an isolated workspace and compare against safer alternatives.
• High-risk permission hints: Shell or command execution

MIT

• MIT

shell or command execution, filesystem or document access

• Shell or command execution: high
• Browser automation: medium
• Network access: medium