resolve
/resolve
Always resolve Hugging Face models via `model-shelf` before any download. Supports GGUF, MLX, and safetensors. Triggers whenever the user asks to load, run, or use a local LLM model (llama.cpp / Ollama / MLX / vLLM / transformers flows).
- Author
- alexziskind1 ↗
- Repository
- model-shelf ↗
- Licence
- MIT
- Last repository change
- 01.09.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 01.09.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Always resolve Hugging Face models via `model-shelf` before any download. Supports GGUF, MLX, and safetensors. Triggers whenever the user asks to load, run, or use a local LLM model (llama.cpp / Ollama / MLX / vLLM / transformers flows).
Original author description
Always resolve Hugging Face models via `model-shelf` before any download. Supports GGUF, MLX, and safetensors. Triggers whenever the user asks to load, run, or use a local LLM model (llama.cpp / Ollama / MLX / vLLM / transformers flows).
How it works
- Workflow
- Examples
SKILL.md preview
---
name: resolve
description: Always resolve Hugging Face models via `model-shelf` before any download. Supports GGUF, MLX, and safetensors. Triggers whenever the user asks to load, run, or use a local LLM model (llama.cpp / Ollama / MLX / vLLM / transformers flows).
---
# Resolve a Hugging Face model locally
When the user wants to load, run, or use a Hugging Face model — **always**
go through `model-shelf`. Do not invoke `huggingface-cli download`, `hf
download`, `snapshot_download`, or any other direct download command.
The user does **not** need to give you an exact `org/repo` id. Loose
descriptions ("qwen 3 4b mlx 4-bit", "the latest llama 3.1") are normal
and expected. Do not push back on whether a model exists — your training
data is stale and Model Shelf can search the live Hub.
## Workflow
1. **Decide whether to search first.**
- If the user gave a clean `org/repo` string (e.g. `Qwen/Qwen3-14B-GGUF`),
skip to step 2.
- Otherwise the input is loose — run:
```
model-shelf find "<user's words>" [--format gguf|mlx|safetensors] --json --limit 5
```
Use any format hint from the user (`mlx`, `gguf`, `safetensors`). Pick the
top result that matches the user's format/quant intent. Use its `repo_id`
as the input to step 2. If `find` returns nothing, tell the user no
matching model was found — do **not** invent a repo id.
2. **Resolve the repo to a local path.**
```
model-shelf resolve <repo_id> [--format gguf|mlx|safetensors] [--quant <QUANT>] --json
```
- `--format` is auto-detected from `repo_id` if omitted:
- `*-GGUF` (case-insensitive) → `gguf`
- `mlx-community/*` or `*-mlx` → `mlx`
- everything else → `safetensors`
- `--quant` is **required for `gguf`** (e.g. `Q4_K_M`); ignored otherwise.
3. **Use the returned `path`** with the user's runtime:
- **gguf**: file path → `llama.cpp` / `llama-server` / Ollama / LM Studio
- **mlx**: directory path → `mlx_lm.generate` / `mlx_lm.server` (Apple Silicon)
- **safetensors**: directory path → `transformers` / `vllm`
4. **Error handling:**
- If `status == "missing"`, downloads are disabled in their config —
surface that to the user and stop.
- If `model-shelf` exits **non-zero with a message on stderr**, surface
the error verbatim and stop. Do **not** work around it — don't fall
back to `huggingface-cli`, don't change paths, don't retry. Common causes:
- **Volume not mounted** — user's external drive isn't connected.
- **Shelf not initialized** — error tells them to run `model-shelf init`.
Don't run it for them unless they explicitly ask; the curated shelf
is a deliberate one-time setup the user owns.
## Examples
Loose user input — search first:
```
User: "fetch qwen 3 4b in mlx 4-bit"
You: model-shelf find "qwen3 4b 4-bit" --format mlx --json --limit 5
# pick top result, e.g. mlx-community/Qwen3-4B-4bit
model-shelf resolve "mlx-community/Qwen3-4B-4bit" --json
```
Explicit repo — resolve directly:
```
User: "load Qwen/Qwen3-14B-GGUF with Q4_K_M"
You: model-shelf resolve "Qwen/Qwen3-14B-GGUF" --quant Q4_K_M --json
```
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · alexziskind1/model-shelf | 100 | MIT |
| griffinwork40/agent-framework | 100 | Apache-2.0 |
| OutlineDriven/outline-driven-development | 100 | Apache-2.0 |
| outlinedriven/odin-claude-plugin | 100 | Apache-2.0 |
| gosuda/dalcom-skills | 95 | Apache-2.0 |
| OutlineDriven/odin-codex-plugin | 90 | Apache-2.0 |
Database snapshot: 13.11.2026 · package version b71e2aa20248 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100local-model-orchestrator
Scan, explain, select, install, and call local AI models across Ollama, Hugging Face cache, MLX Whisper, whisper.cpp, LM Studio, and common Mac model stores. Use when the user asks to list local models, understand what installed models do, check whether models are healthy,… - 90codealta-model-servers
Use this skill to run local models with llama.cpp on this computer or on the machines of the fleet - install or update the best build of llama.cpp for their GPUs (CUDA, ROCm, Vulkan, Metal), choose a GGUF model of Hugging Face and a quantization that fits, download it, add,… - 100local-inference-tuning
Select and tune a local LLM inference engine for the user's hardware. Use when setting up or auditing local/private model serving, choosing between MLX, llama.cpp, Ollama, and vLLM, estimating model fit, deciding cache/storage policy, tuning batching and KV cache flags, running… - 100unsloth
Unsloth fine-tunes open LLMs such as Llama, Qwen and Gemma with LoRA or QLoRA about twice as fast and with far less GPU memory than a stock Hugging Face setup, then exports the result to GGUF for Ollama and llama.cpp or to merged weights for vLLM. Use it when someone wants to… - 90models
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… - 100llama-cpp
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.cpp. Includes Qwen 3.5 serve scripts (9B dense + F16, 35B MoE) with asymmetric KV cache and thinking mode. Secondary to Ollama; use when needing direct model…