Install the "resolve" agent skill from https://github.com/alexziskind1/model-shelf/tree/main/skills/resolve into .claude/skills/resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add alexziskind1/model-shelf --skill resolve -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "resolve" agent skill from https://github.com/alexziskind1/model-shelf/tree/main/skills/resolve into .agents/skills/resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add alexziskind1/model-shelf --skill resolve -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "resolve" agent skill from https://github.com/alexziskind1/model-shelf/tree/main/skills/resolve into .cursor/skills/resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add alexziskind1/model-shelf --skill resolve -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "resolve" agent skill from https://github.com/alexziskind1/model-shelf/tree/main/skills/resolve into .gemini/skills/resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add alexziskind1/model-shelf --skill resolve -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "resolve" agent skill from https://github.com/alexziskind1/model-shelf/tree/main/skills/resolve into .github/skills/resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add alexziskind1/model-shelf --skill resolve -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "resolve" agent skill from https://github.com/alexziskind1/model-shelf/tree/main/skills/resolve into .opencode/skills/resolve/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
resolve
GitHub stars
130
Token cost
~792 tokens
SKILL.md length
331 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT
At a glance
Always resolve Hugging Face models via model-shelf before any download.
Works in 4 steps: Decide whether to search first. → Resolve the repo to a local path. → Use the returned path with the user's… → …
Ever the user asks to load
SKILL.md covers Workflow and Examples
Calls huggingface-cli
What it does
Resolve is an agent skill from alexziskind1/model-shelf. 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).
Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM inference and serving and Model hubs and datasets. It works with llama.cpp, Hugging Face, Ollama and vLLM. The repository describes itself as: Model Shelf is a local-first model resolver that helps AI agents and scripts find model weights on your own storage before downloading from Hugging Face. Point it at an internal… The licence is MIT.
When your agent uses it
Ever the user asks to load
Use a local LLM model (llama.cpp / Ollama / MLX / vLLM / transformers flows)
Example prompts
“Use the resolve skill to alway resolve Hugging Face models via model-shelf before any download”
“/resolve”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
1Decide whether to search first.
2Resolve the repo to a local path.
3Use the returned path with the user's runtime
4Error handling
What it can do on your machine
Read from SKILL.md and the folder at commit 0499129. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
huggingface-cli
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Resolve loads about 792 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 331 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~61
When it runs· the whole SKILL.md, loaded when a task matches
~792
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/resolve/SKILL.md (or your agent's skills folder).
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
Decide whether to search first.
If the user gave a clean org/repo string (e.g. Qwen/Qwen3-14B-GGUF),
skip to step 2.
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.
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
Resolve next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.
Always resolve Hugging Face models via model-shelf before any download. Resolve is an agent skill from alexziskind1/model-shelf. Always resolve Hugging Face models via model-shelf before any download.
When should I use Resolve?
Resolve fits situations like: ever the user asks to load; use a local LLM model (llama.cpp / Ollama / MLX / vLLM / transformers flows).
How do I install Resolve in Claude Code?
Run `npx skills add alexziskind1/model-shelf --skill resolve -a claude-code`. Or copy the skill folder (skills/resolve in alexziskind1/model-shelf) into .claude/skills/resolve in your project. Claude Code loads it when a task matches its description.
How do I install Resolve in Codex?
Run `npx skills add alexziskind1/model-shelf --skill resolve -a codex`. Or copy the skill folder (skills/resolve in alexziskind1/model-shelf) into .agents/skills/resolve in your project. Codex loads it when a task matches its description.
Can I use Resolve in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alexziskind1/model-shelf --skill resolve -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resolve, .gemini/skills/resolve, .github/skills/resolve and .opencode/skills/resolve in your project.
What does Resolve need to run?
Going by SKILL.md and its folder, Resolve needs the command-line tools its instructions call (huggingface-cli).
Does Resolve access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Resolve safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Resolve use?
Resolve is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Resolve use?
About 792 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Resolve?
Skills that share tags, products or a category with Resolve: Add Model (guoqingbao/xinfer, 334 stars), Test Model (guoqingbao/xinfer, 334 stars), Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Check Model (guoqingbao/xinfer, 334 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Resolve?
alexziskind1 (a GitHub user) maintains it in alexziskind1/model-shelf, which has 130 GitHub stars. The repository was last updated on September 1, 2026.
Source: alexziskind1/model-shelf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
