Skip to content
TrustedSkillsbeta
Back to all skills

Openclaw Local Mac Mini

Listed
bagelhole·vlatest·agents·MIT

This skill sets up a local Mac Mini powered by OpenClaw for offline AI processing, boosting privacy and speed.

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add bagelhole/devops-security-agent-skills --skill openclaw-local-mac-mini -a claude-code
  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

bagelhole

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: www.apple.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    www.apple.comundeclared127.0.0.1local

    What it found

    • infrastructure/local-ai/openclaw-local-mac-mini/SKILL.md:285contacts www.apple.com
      "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
    • infrastructure/local-ai/openclaw-local-mac-mini/SKILL.md:373contacts www.apple.com
      "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
  • No credential access: failed

    Touches credential material in 3 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found

    • infrastructure/local-ai/openclaw-local-mac-mini/SKILL.md:267OS keychain / credential manager
      OPENAI_API_KEY=$(security find-generic-password -a openclaw -s "OPENAI_API_KEY" -w)
    • infrastructure/local-ai/openclaw-local-mac-mini/SKILL.md:273OS keychain / credential manager
      export OPENAI_API_KEY=$(security find-generic-password -a openclaw -s "OPENAI_API_KEY" -w 2>/dev/null)
    • infrastructure/local-ai/openclaw-local-mac-mini/SKILL.md:274OS keychain / credential manager
      export ANTHROPIC_API_KEY=$(security find-generic-password -a openclaw -s "ANTHROPIC_API_KEY" -w 2>/dev/null)
  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned bagelhole/devops-security-agent-skills at 0365f57a07.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Scanned
1 file, 577 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The openclaw-local-mac-mini skill allows an AI agent to interact with and control a local Mac Mini. It enables remote execution of commands, file management tasks, and potentially other system operations on the specified machine. This provides a means for automation and remote administration capabilities.

When to use it

  • Remote Command Execution: Run scripts or commands on the Mac Mini from another location without direct physical access.
  • File Transfer & Management: Copy files between the agent's environment and the local Mac Mini, or manage files already present on the target machine.
  • Automated System Tasks: Automate repetitive tasks like backups, system updates, or log analysis on the Mac Mini.

Key capabilities

  • Remote command execution
  • File transfer (upload/download)
  • Targeted to a specific local Mac Mini

Example prompts

  • "Run ls -l /Users/shared on my Mac Mini."
  • "Download /var/log/system.log from the Mac Mini."
  • "Execute sudo reboot on the Mac Mini after confirming I have entered my password."

Tips & gotchas

The skill requires proper authentication and authorization to access the target Mac Mini, typically involving SSH keys or similar mechanisms. Ensure the agent has the necessary permissions configured on the remote machine for successful operation.