Truenas Middleware logo

Truenas Middleware

Organization
serversathome
truenas-middleware

Discover and use the live TrueNAS middleware method surface instead of guessing. Use this whenever a TrueNAS task needs a midclt method that is not in capabilities/truenas.md, whenever the user asks about the TrueNAS API, the middleware, midclt, "what can the API do", available methods, or method parameters, or whenever a midclt call fails with an unknown-method or bad- argument error. Trigger this to look up the real methods, their exact names, and their parameter schemas on THIS box rather than relying on the static catalog. Prefer this over guessing method names for anything beyond the common operations already documented.

Overview

Publisherserversathome
Repositoryhomelabhero
Skill nametruenas-middleware
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 Truenas Middleware 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/truenas-middleware
  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/truenas-middleware .claude/skills/truenas-middleware
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Truenas Middleware 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 Truenas Middleware 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 Truenas Middleware 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.

TrueNAS middleware introspection

capabilities/truenas.md is the fast path for common work. This skill is for everything beyond it: the middleware exposes many hundreds of methods, and their names, parameters, and return shapes vary by TrueNAS version. Do not guess. Read them off the actual box.

All commands run through the broker, e.g. hh run truenas "<command>". midclt talks to the middleware and is the preferred way to read and change TrueNAS: it covers pools, datasets, disks, apps, shares, and more. TrueNAS ships python3 (the middleware is python), so python3 is the reliable JSON parser; jq may or may not be present, so check with command -v jq before relying on it.

List the methods that actually exist

# every method name on this box, sorted
midclt call core.get_methods | python3 -c "import json,sys;[print(k) for k in sorted(json.load(sys.stdin))]"

# only a namespace you care about (e.g. everything under 'pool')
midclt call core.get_methods | python3 -c "import json,sys;[print(k) for k in sorted(json.load(sys.stdin)) if k.startswith('pool')]"

Namespaces are regular: pool.*, pool.dataset.*, pool.snapshottask.*, app.*, service.*, interface.*, sharing.smb.*, replication.*, disk.*, system.*, and so on. Filter by the prefix that matches the task.

The virtualization namespace is the big version trap - it changed backend twice and the method names moved with it, so ALWAYS discover it live rather than recalling a name:

# what VM/container methods actually exist on THIS box
midclt call core.get_methods | python3 -c "import json,sys;[print(k) for k in sorted(json.load(sys.stdin)) if k.split('.')[0] in ('vm','virt','container')]"

Expect one of: vm.* (libvirt VMs, on 24.10 and earlier, and again on 27, whose betas were numbered 26), virt.instance.* plus virt.global.*/virt.device.*/virt.volume.* (Incus, on 25.04 and 25.10), or a libvirt_lxc container namespace (27). Pair the result with midclt call system.version so you know which era you are on. On a 27 pre-release the names may still move - trust the live list, not memory.

Inspect a method BEFORE you call it

For any state-changing method, look up its accepts schema so you pass the right arguments, then confirm with the user before running it.

# description + accepted arguments + return shape for one method
midclt call core.get_methods | python3 -c "import json,sys,pprint;pprint.pprint(json.load(sys.stdin).get('pool.dataset.create'))"

The accepts field is the JSON schema for the arguments; returns is what comes back. Read accepts to build the call correctly.

Calling methods

Arguments are passed as JSON positional args:

# read-only query with a filter (safe)
midclt call pool.dataset.query '[["name","=","tank/media"]]'

# a method that takes an object argument
midclt call service.restart '"cifs"'

Long-running operations are jobs. Add -j so midclt waits for completion and returns the result instead of just a job id:

midclt call -j pool.scrub '{"pool": "tank", "action": "START"}'

Read vs write

Safe to run freely (read-only): anything ending in .query, .config, .get_instance, .info, and the core.get_* introspection methods.

State-changing (inspect the schema first, then confirm before running): verbs like .create, .update, .delete, .start, .stop, .restart, .scrub, .export, .replace, .wipe. Treat pool, dataset, disk, and replication writes as high-risk and never run them without an explicit go-ahead, per the house rules in CLAUDE.md.

Fallbacks

If core.get_methods is unavailable on a given version, midclt call core.get_services lists service namespaces, and the box also serves interactive API docs at https://<truenas-host>/api/docs for a human to browse. Stay on the SSH + midclt path; do not add API keys or network API calls.

Credentials stay off-limits

As always, never read, print, or exfiltrate credentials, and never target the vault. Introspection is about methods, not secrets.

Frequently asked questions

What does the Truenas Middleware AI skill do?

Discover and use the live TrueNAS middleware method surface instead of guessing. Use this whenever a TrueNAS task needs a midclt method that is not in capabilities/truenas.md, whenever the user asks about the TrueNAS API, the middleware, midclt, "what can the API do", available methods, or method parameters, or whenever a midclt call fails with an unknown-method or bad- argument error. Trigger this to look up the real methods, their exact names, and their parameter schemas on THIS box rather than relying on the static catalog. Prefer this over guessing method names for anything beyond the c...

Why use Truenas Middleware on TypingMind?

Because you install it once and use it with any model. Truenas Middleware 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 Truenas Middleware in TypingMind?

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

Which AI models can use Truenas Middleware?

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 Truenas Middleware?

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

Is the Truenas Middleware 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 👇