Add Server logo

Add Server

Organization
serversathome
add-server

Register a new server so HomelabHero can manage it, driven entirely from the chat/UI with no shell access and no password ever entering the conversation. Use this whenever the user asks to add, register, connect, onboard, or "hook up" a server, host, machine, NAS, node, or box, or says things like "add my truenas", "connect to my proxmox at 10.x.x.x", or "I have another Linux box to manage". Trigger it any time someone wants a new machine brought under management, even if they do not say the word "register".

Overview

Publisherserversathome
Repositoryhomelabhero
Skill nameadd-server
Stars
104
Forks
4
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by serversathome on GitHub. Read the source before you install it.

Installation

Install the Add Server AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/serversathome/homelabhero/tree/main/ops/.claude/skills/add-server
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/serversathome/homelabhero.git /tmp/homelabhero
mkdir -p .claude/skills
cp -r /tmp/homelabhero/ops/.claude/skills/add-server .claude/skills/add-server
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Add Server in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Add Server on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Add Server is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Add a server (from the UI, key-only)

This is the safe way to onboard a host through the chat. It never asks for or handles the target's password. It generates a keypair in the vault (you never see the private half) and gives back a public key the user installs on the target themselves.

Steps

  1. Gather from the user: a short alias (e.g. pve1), the IP or hostname, and the platform (linux, truenas, proxmox, or routeros for a MikroTik). Assume SSH port 22 and connect as root unless they say otherwise (routeros defaults to admin, since RouterOS has no root). Confirm briefly.

    Root is the default and needs no sudo. Only ask for a different connect user if the box requires one (e.g. a TrueNAS where root SSH is off, using truenas_admin, or a locked-down Linux login).

  2. Register and generate the key (defaults to root):

    hh provision <alias> <host> [port] [platform]

    To connect as a non-root user instead, pass it as the fifth argument or as user@host:

    hh provision nas1 10.0.0.20 22 truenas truenas_admin
    hh provision box1 deploy@10.0.0.30 22 linux

    This prints a confirmation line (stating the user it registered) and a public key between PUBLIC_KEY_BEGIN and PUBLIC_KEY_END.

  3. Give the user that public key and tell them to install it on the account provision registered (root by default), shown in the confirmation line:

    • TrueNAS: web UI -> Credentials -> Users -> the user -> Edit -> "Authorized Keys" -> paste -> Save (and enable root SSH if you registered as root).
    • Proxmox: add the line to /root/.ssh/authorized_keys on the node.
    • Linux: append it to ~/.ssh/authorized_keys for that login user.
    • MikroTik RouterOS: upload it to the device as a file (WinBox/WebFig Files, or scp), then run /user ssh-keys import public-key-file=<file> user=<user> in the RouterOS terminal. For a read-only link, put that user in the read group.
  4. Once they confirm it's installed, verify:

    hh test <alias>

    OK means it's connected and ready. If it still fails, the key isn't on the target yet, or SSH/key auth is disabled there.

  5. Show it landed:

    hh list
    hh doctor

Important

  • Key-only by design. A password cannot be handled safely through the chat, so if the user insists on password auth, that path is the shell-only command hh add-host, run by an admin on the box. Offer keys first; they are more secure and work cleanly on TrueNAS, Proxmox, and Linux.
  • You never see or need the private key or any password. Do not ask for one.
  • Wrong connect user? hh test will fail even with the key installed, because the broker logs in as the registered user. Provision refuses to overwrite an existing alias, so to change the user ask the operator to run hh rm-host <alias> from an admin shell, then re-provision with the correct user. (rm-host needs sudo and cannot be run from the chat.)
  • After adding, hh overview and hh inventory will include the new host.

Frequently asked questions

What does the Add Server AI skill do?

Register a new server so HomelabHero can manage it, driven entirely from the chat/UI with no shell access and no password ever entering the conversation. Use this whenever the user asks to add, register, connect, onboard, or "hook up" a server, host, machine, NAS, node, or box, or says things like "add my truenas", "connect to my proxmox at 10.x.x.x", or "I have another Linux box to manage". Trigger it any time someone wants a new machine brought under management, even if they do not say the word "register".

Why use Add Server on TypingMind?

Because you install it once and use it with any model. Add Server is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Add Server in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/serversathome/homelabhero/tree/main/ops/.claude/skills/add-server. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Add Server?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Add Server?

As many as you like. As long as a model supports skills, you can use Add Server with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Add Server AI skill free?

It is published on GitHub by serversathome. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇