Hugging Face Skills
Official Hugging Face skills: Hub operations via the hf CLI, datasets, model training, Spaces, evals and deployment
- 11,236 ★ on the repository
- Last commit
- Apache-2.0
Broad access
Why this level
- Uploads and deletes data in Hub repos on the user's behalf
- Launches paid jobs on cloud GPUs and AWS
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/hugging-face-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Uploads and deletes data in Hub repos on the user's behalf
- Launches paid jobs on cloud GPUs and AWS
This is third-party code. Review the repository files before installing.
What it does
The repository collects skills for machine learning tasks in the Hugging Face ecosystem. The core hf-cli skill teaches the agent every hf command: download and upload models and datasets, manage repos, buckets, Spaces and jobs on Hugging Face infrastructure. Other skills install on demand: fine-tuning language and vision models with TRL and Unsloth on HF Jobs, Dataset Viewer API workflows, Gradio and ZeroGPU demos, picking local GGUF models, model evaluation, paper publishing and SageMaker deployment.
Who it is for. For ML engineers and researchers working with models and datasets on Hugging Face through an agent.
Good fit when
- You need to find, download or publish a model or dataset on the Hub
- You need to fine-tune a model on cloud GPUs without manual setup
- You need a quick Gradio demo deployed to Spaces
- You need a model that runs locally with llama.cpp
Not a fit when
- Models and data live outside Hugging Face and cannot be uploaded there
- You need production deployment outside AWS and HF
Example request
Find a small model on the Hub for review classification and download it to ./modelsLimitations
Most operations need a Hugging Face account and token. Training on HF Jobs, ZeroGPU and dedicated Spaces hardware are paid, and SageMaker skills need an AWS account. The Claude Code and Cursor marketplaces install only hf-cli; add the rest with hf skills add.
How to disable. Remove the hf-cli plugin via /plugin, the Gemini extension with gemini extensions uninstall, or skill folders from .agents/skills.
FAQ
Which skill should I start with?
hf-cli: it covers core Hub operations and is generated from your installed CLI, so it stays current.
What if my agent does not support skills?
Use agentsmd/AGENTS.md from the repo as an instruction bundle.
Discussion
No questions or reviews yet.
Related
SkillsA CLI for fine-tuning language models from one YAML: LoRA, QLoRA, DPO and GRPO, layer streaming for 8B on a 4 GB GPU, export to GGUF
A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology
A three-stage workflow for math modeling tasks: analysis and model choice, Python or MATLAB computation, and paper assembly in Word or LaTeX
High-Stakes Analytics Lab
High-Stakes Analytics & Decision Lab
An evidence-gated analytics skill for high-stakes decisions: profiles data, picks a method the evidence supports, can answer with a data request
Official Apify skills for agents: web scraping via ready-made Actors, plus building, actorizing and integrating Actors
dbt Agent Skills
dbt-agent-skills
Official dbt Labs skills: the agent understands dbt projects, runs workflows and helps with migration
README in short
The README explains the Agent Skills format and recommends starting with hf-cli. It covers Claude Code via the plugin marketplace, Codex by copying into .agents/skills, Gemini CLI via extension and Cursor via plugin manifest. A table lists every skill and its purpose. It also describes adding your own skill and why marketplaces expose only hf-cli.
README badge
Original SKILL.md
--- name: hf-cli description: "Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints." --- Install: `curl -LsSf https://hf.co/cli/install.sh | bash -s`. The Hugging Face Hub CLI tool `hf` is available. IMPORTANT: The `hf` command replaces the deprecated `huggingface-cli` command. Use `hf --help` to view available functions. Note that auth commands are now all under `hf auth` e.g. `hf auth whoami`. Generated with `huggingface_hub v1.30.0`. Run `hf skills add --force` to regenerate. ## Commands - `hf cp SRC` — Copy files between local paths, repositories, and buckets. - `hf download REPO_ID` — Download files from the Hub. - `hf env` — Print information about the environment. - `hf sync` — Sync files between local directory and a bucket. - `hf update` — Update the `hf` CLI to the latest version. - `hf upload REPO_ID` — Upload a file or a folder to the Hub. Recommended for single-commit uploads. - `hf version` — Print information about the hf version. ### `hf auth` — Manage authentication (login, logout, etc.). - `hf auth list` — List all stored access tokens. - `hf auth login` — Login from your browser, or using a token from huggingface.co/settings/tokens. - `hf auth logout` — Logout from a specific token. - `hf auth switch` — Switch between access tokens. - `hf auth token` — Print the current access token to stdout. - `hf auth whoami` — Find out which huggingface.co account you are logged in as.