mcpbeat Sign in

Models Agent Skill

>- Add any Hugging Face image or video model, checkpoint or LoRA to Guaardvark from a URL, list what is installed, and download registry models on request. Use when the user pastes a huggingface.co link or a .safetensors URL, asks "can it run <model>", or wants a new LoRA or checkpoint available in the Studio.

694 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
211
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/guaardvark/guaardvark --skill models

The instruction itself

5 sections, as written by the author

Models and LoRAs with Guaardvark

B=${GUAARDVARK_URL:-http://localhost:5000}. Nothing downloads without an explicit Install;

the product never phones home on its own. Always confirm the size and the licence with the user first.

What is there

  • Video: GET $B/api/batch-video/models (registry + user catalog, with installed, modes, limits).
  • Image: GET $B/api/batch-image/models.
  • Download a registry model: POST $B/api/batch-video/models/download {"model_id": "wan22-14b"} /

POST $B/api/batch-image/models/download {"model_path": "<id>"}; progress at

GET .../models/download-status.

  • Inspect: POST $B/api/batch-video/models/from-hf {"url": "https://huggingface.co/<org>/<repo>"}

(or the batch-image twin). The server reads the repo and returns what it found: files,

revision, the likely role (checkpoint, LoRA, VAE, text encoder), family, whether a

model_index exists, and a proposed catalog entry.

  • Show that to the user: which file(s), role, family, size, licence.
  • Register (and optionally install) with POST $B/api/batch-video/models/user (or batch-image)

sending the entry back, e.g.

   {"url": "...", "hf_repo": "org/repo", "revision": "main", "files": ["model.safetensors"],
    "role": "lora", "family": "wan22", "name": "My LoRA", "description": "...", "install": true}

role and family decide where the Studio offers it (a Wan LoRA appears under Wan models;

an SDXL checkpoint under image models). Video entries also take like: "<registry id>" to

inherit that model's capabilities.

  • Remove: DELETE .../models/user/<model_id> with {"delete_files": true|false}.

Using a user LoRA

  • Batch image: adapters: [{"id": "<user model id>", "scale": 0.8}] on /generate/prompts.
  • Batch video: lora_name + lora_strength, or adapters on /generate/text.
  • A trained Cast LoRA is different: it rides on subject_ids (the cast skill).

Rules

  • A direct .safetensors URL works when it lives on huggingface.co; the inspector needs the repo

to read the file list. For other hosts, ask the user to download the file and drop it in the

Studio's model folder instead.

  • Declared limits (min steps, max frames) come from the registry entry; a user model inherits

them from like/family. Do not invent numbers for a model the registry does not know.

How to use it

Copy the folder

Take guaardvark/models from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.