Agent skill

Huggingface Hub

HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.

MITAuto-check passedAI & LLM Engineering

Install Huggingface Hub

skills CLI

$ npx skills add AlexAI-MCP/hermes-CCC --skill huggingface-hub -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC huggingface-hub --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/huggingface-hub .claude/skills/huggingface-hub && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "huggingface-hub" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub into .claude/skills/huggingface-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-hub", 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.

$skill-installer

$skill-installer install https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub

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 AlexAI-MCP/hermes-CCC --skill huggingface-hub -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC huggingface-hub --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/huggingface-hub .agents/skills/huggingface-hub && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "huggingface-hub" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub into .agents/skills/huggingface-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-hub", 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 AlexAI-MCP/hermes-CCC --skill huggingface-hub -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC huggingface-hub --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/huggingface-hub .cursor/skills/huggingface-hub && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "huggingface-hub" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub into .cursor/skills/huggingface-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-hub", 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.

gemini skills install

$ gemini skills install https://github.com/AlexAI-MCP/hermes-CCC.git --path skills/huggingface-hub

--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 AlexAI-MCP/hermes-CCC --skill huggingface-hub -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC huggingface-hub --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/huggingface-hub .gemini/skills/huggingface-hub && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "huggingface-hub" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub into .gemini/skills/huggingface-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-hub", 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.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC huggingface-hub

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 AlexAI-MCP/hermes-CCC --skill huggingface-hub -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/huggingface-hub .github/skills/huggingface-hub && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "huggingface-hub" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub into .github/skills/huggingface-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-hub", 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 AlexAI-MCP/hermes-CCC --skill huggingface-hub -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install AlexAI-MCP/hermes-CCC huggingface-hub --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/AlexAI-MCP/hermes-CCC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/huggingface-hub .opencode/skills/huggingface-hub && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "huggingface-hub" agent skill from https://github.com/AlexAI-MCP/hermes-CCC/tree/master/skills/huggingface-hub into .opencode/skills/huggingface-hub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huggingface-hub", 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: huggingface-hub
GitHub stars: 135
Token cost: ~965 tokens
SKILL.md length: 73 words
Files: 1
Skills in repo: 44
Repo updated: Apr 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.

Works in 3 steps: Go to hf.co/model-card and accept terms → Use a token with read access:… → Download normally — gate is checked…
AI & LLM Engineering work in your project
SKILL.md covers Setup, Download Models, Download Datasets and Upload Models, plus 6 more sections
Calls huggingface-cli, pip and python; needs HF_TOKEN

What it does

Huggingface Hub is an agent skill from AlexAI-MCP/hermes-CCC. HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.

Its SKILL.md is about 970 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. It works with Hugging Face and Python. The repository describes itself as: Hermes Agent ported to Claude Code Channel — 46 native skills, no OAuth, no external process. The licence is MIT.

When your agent uses it

AI & LLM Engineering work in your project

Example prompts

“/huggingface-hub”

Requirements

Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Go to hf.co/model-card and accept terms
Use a token with read access: huggingface-cli login
Download normally — gate is checked server-side

What it can do on your machine

Read from SKILL.md and the folder at commit 8107e89. 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
- pip
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Huggingface Hub loads about 965 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 73 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~32
When it runs · the whole SKILL.md, loaded when a task matches: ~965

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.

SKILL.md

The full file from AlexAI-MCP/hermes-CCC at commit 8107e89, republished under its MIT licence (© AlexAI-MCP). 73 words, ~965 tokens.

Download SKILL.mdSave it as .claude/skills/huggingface-hub/SKILL.md (or your agent's skills folder).

name: huggingface-hub
description: HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.
version: 1.0.0
author: hermes-CCC (ported from Hermes Agent by NousResearch)
license: MIT

HuggingFace Hub

Download models and datasets, upload artifacts, and manage your Hub presence via CLI and Python API.

Setup

bash

pip install huggingface_hub datasets transformers
huggingface-cli login   # paste your token from hf.co/settings/tokens

Or set env var:

bash

export HF_TOKEN=hf_...

Download Models

bash

# Download entire model to cache (~/.cache/huggingface/)
huggingface-cli download meta-llama/Llama-3.1-8B-Instruct

# Download to specific directory
huggingface-cli download Qwen/Qwen2.5-7B-Instruct --local-dir ./models/qwen

# Download specific file only
huggingface-cli download microsoft/phi-4 config.json

# Download GGUF quantized model
huggingface-cli download bartowski/Llama-3.1-8B-Instruct-GGUF \
  Llama-3.1-8B-Instruct-Q4_K_M.gguf --local-dir ./models/

Python API:

python

from huggingface_hub import snapshot_download, hf_hub_download

# Full model
snapshot_download("meta-llama/Llama-3.1-8B-Instruct", local_dir="./models/llama")

# Single file
hf_hub_download("meta-llama/Llama-3.1-8B-Instruct", "config.json", local_dir="./")

Download Datasets

bash

# CLI
huggingface-cli download --repo-type dataset HuggingFaceH4/ultrachat_200k

# Python (preferred)
from datasets import load_dataset

dataset = load_dataset("HuggingFaceH4/ultrachat_200k")
dataset["train_sft"].to_json("./data/train.jsonl")

Upload Models

bash

# Upload directory
huggingface-cli upload your-username/my-model ./local-model-dir

# Upload specific file
huggingface-cli upload your-username/my-model ./model.safetensors

# Create repo first if needed
huggingface-cli repo create my-new-model --type model

Python API:

python

from huggingface_hub import HfApi

api = HfApi()
api.upload_folder(
    folder_path="./fine-tuned-model",
    repo_id="your-username/my-fine-tuned-model",
    repo_type="model",
)

Search Models

bash

# CLI search
huggingface-cli search models --filter task=text-generation --filter language=ko

# Python API
from huggingface_hub import list_models

models = list_models(
    task="text-generation",
    language="ko",
    sort="downloads",
    limit=10,
)
for m in models:
    print(m.id, m.downloads)

Cache Management

bash

# Show cache info
huggingface-cli cache info

# List cached repos
huggingface-cli cache scan

# Delete specific cached model
huggingface-cli cache evict --model meta-llama/Llama-3.1-8B-Instruct

# Cache location
echo ~/.cache/huggingface/hub/

Custom cache dir:

bash

export HF_HOME=/path/to/custom/cache

Model Cards

bash

# Read model card
python -c "from huggingface_hub import ModelCard; print(ModelCard.load('Qwen/Qwen2.5-7B-Instruct'))"

Spaces

bash

# Deploy a Gradio/Streamlit app to Spaces
huggingface-cli upload your-username/my-space ./app --repo-type space

# Check Space status
huggingface-cli space info your-username/my-space

Token Management

bash

# Who am I?
huggingface-cli whoami

# List tokens
huggingface-cli token list

# Revoke
huggingface-cli token revoke TOKEN_NAME

Gated Models (Llama, Gemma, etc.)

Go to hf.co/model-card and accept terms
Use a token with read access: huggingface-cli login
Download normally — gate is checked server-side

python

# Check if you have access
from huggingface_hub import model_info
info = model_info("meta-llama/Llama-3.1-8B-Instruct")
print(info.gated)  # False if you have access

Files

Just SKILL.md in skills/huggingface-hub of AlexAI-MCP/hermes-CCC.

Open the folder on GitHubat commit 8107e89

Compare with similar skills

Huggingface Hub 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.

Huggingface Hub compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Huggingface Hub this skillAlexAI-MCP/hermes-CCC	135	—	~965	Automated safety check: Pass	MIT	6 mo ago
Chroma Vector DatabaseOrchestra-Research/AI-Research-SKILLs	13k	7 repos	~2.3k	Automated safety check: Pass	MIT	3 mo ago
Python Environment Setup for SageMakerhuggingface/skills	11k	2 repos	~1.7k	Automated safety check: Pass	Apache-2.0	2 days ago
Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide	1.7k	—	~1.7k	Automated safety check: Pass	MIT	3 mo ago
Hugging Face TokenizersOrchestra-Research/AI-Research-SKILLs	13k	6 repos	~3.4k	Automated safety check: Pass	MIT	3 mo ago
Hugging Face Vision Trainerhuggingface/skills	11k	1 repos	~7.5k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
13k GitHub starsUsed in 7 repos~2.3k tokens
AI & LLM EngineeringAuto-check passed
Python Environment Setup for SageMaker
huggingface/skills
Official
Sets up an isolated Python environment with a supported interpreter and current boto3 before any SageMaker deployment, training or AWS automation code runs.
11k GitHub starsUsed in 2 repos~1.7k tokens
AI & LLM EngineeringAuto-check passed
Qwen Mtp Gguf
R6410418/Jackrong-llm-finetuning-guide
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
1.7k GitHub stars~1.7k tokensUpdated 3 mo ago
AI & LLM EngineeringAuto-check passed
Hugging Face Tokenizers
Orchestra-Research/AI-Research-SKILLs
Shows how to load, train and use fast Hugging Face tokenizers, with BPE, WordPiece and Unigram models, padding, truncation and alignment tracking.
13k GitHub starsUsed in 6 repos~3.4k tokens
AI & LLM EngineeringAuto-check passed
Hugging Face Vision Trainer
huggingface/skills
Official
Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.
11k GitHub starsUsed in 1 repo~7.5k tokens
AI & LLM EngineeringAuto-check passed
Edge Bringup
exeex/edge-cores
Prepare a macOS or Ubuntu machine for edge-e3 development, diagnose missing Verilator/LLVM/Python dependencies, initialize the public repository, and answer or act on the example prompts in the root…
110 GitHub stars~1.7k tokensUpdated 15 days ago
AI & LLM EngineeringAuto-check: notes

Questions about Huggingface Hub

What does Huggingface Hub do?

HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API. Huggingface Hub is an agent skill from AlexAI-MCP/hermes-CCC. HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.

When should I use Huggingface Hub?

Huggingface Hub fits situations like: AI & LLM Engineering work in your project.

How do I install Huggingface Hub in Claude Code?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill huggingface-hub -a claude-code`. Or copy the skill folder (skills/huggingface-hub in AlexAI-MCP/hermes-CCC) into .claude/skills/huggingface-hub in your project. Claude Code loads it when a task matches its description.

How do I install Huggingface Hub in Codex?

Run `npx skills add AlexAI-MCP/hermes-CCC --skill huggingface-hub -a codex`. Or copy the skill folder (skills/huggingface-hub in AlexAI-MCP/hermes-CCC) into .agents/skills/huggingface-hub in your project. Codex loads it when a task matches its description.

Can I use Huggingface Hub 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 AlexAI-MCP/hermes-CCC --skill huggingface-hub -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huggingface-hub, .gemini/skills/huggingface-hub, .github/skills/huggingface-hub and .opencode/skills/huggingface-hub in your project.

What does Huggingface Hub need to run?

Going by SKILL.md and its folder, Huggingface Hub needs the command-line tools its instructions call (huggingface-cli, pip and python) and credentials named HF_TOKEN. Our summary lists: Python 3.

Does Huggingface Hub access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Huggingface Hub 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 Huggingface Hub use?

Huggingface Hub is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Huggingface Hub use?

About 965 tokens (SKILL.md is roughly 3.9k 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 Huggingface Hub?

Skills that share tags, products or a category with Huggingface Hub: Chroma Vector Database (Orchestra-Research/AI-Research-SKILLs, 13k stars), Python Environment Setup for SageMaker (huggingface/skills, 11k stars), Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Hugging Face Tokenizers (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Huggingface Hub?

AlexAI-MCP (a GitHub user) maintains it in AlexAI-MCP/hermes-CCC, which has 135 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on April 8, 2026.

Source: AlexAI-MCP/hermes-CCC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Huggingface Hub

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

HuggingFace Hub

Setup

Download Models

Download Datasets

Upload Models

Search Models

Cache Management

Model Cards

Spaces

Token Management

Gated Models (Llama, Gemma, etc.)

Files

Compare with similar skills

Similar skills

More from AlexAI-MCP/hermes-CCC

Related

Questions about Huggingface Hub