huggingface / skills

✓ Official★ 10,800

A skill package that teaches your agent 15 capabilities — every one documented and browsable below, no GitHub required · by huggingface.

Each skill below is one capability this package teaches your agent. Install the whole package, or open a skill to install just that one.

hf-cli🔥🔥🔥🔥✓ VerifiedAccount requiredNeeds API keys

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub.…

1 file — installable on its own

→

hf-mcp🔥🔥🔥✓ VerifiedFreeQuick setup

Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio…

3 files — installable on its own

→

huggingface-best🔥🔥🔥✓ VerifiedFreeAdvanced setup

Finds the best models for a task by querying official HF benchmark leaderboards, enriching results with model size data, filtering for what fits on the user's device, and returning a comparison table with benchmark scores.

1 file — installable on its own

→

huggingface-community-evals🔥🔥🔥✓ VerifiedAccount requiredNeeds API keys

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between…

8 files — installable on its own

→

huggingface-datasets🔥🔥🔥✓ VerifiedFreeQuick setup

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet…

1 file — installable on its own

→

huggingface-gradio🔥🔥🔥🔥✓ VerifiedFreeQuick setup

Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.

2 files — installable on its own

→

huggingface-llm-trainer🔥🔥🔥🔥✓ VerifiedFreeQuick setup

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO,…

21 files — installable on its own

→

huggingface-local-models🔥🔥🔥🔥✓ VerifiedFreeQuick setup

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact…

5 files — installable on its own

→

huggingface-paper-publisher🔥🔥✓ VerifiedAccount requiredNeeds API keys

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating…

12 files — installable on its own

→

huggingface-papers🔥🔥✓ VerifiedFreeQuick setup

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github…

1 file — installable on its own

→

huggingface-tool-builder🔥🔥🔥✓ VerifiedAccount requiredNeeds API keys

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful…

9 files — installable on its own

→

huggingface-trackio🔥🔥🔥✓ VerifiedFreeQuick setup

Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or…

5 files — installable on its own

→

huggingface-vision-trainer🔥🔥🔥✓ VerifiedPaid serviceNeeds API keys

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet,…

14 files — installable on its own

→

train-sentence-transformers🔥🔥🔥🔥✓ VerifiedFreeQuick setup

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity,…

30 files — installable on its own

→

transformers-js🔥🔥🔥🔥✓ VerifiedFreeQuick setup

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation,…

9 files — installable on its own

→

Hugging Face Skills

Hugging Face Skills are definitions for AI/ML tasks like dataset creation, model training, and evaluation. They are interoperable with all major coding agent tools like OpenAI Codex, Anthropic's Claude Code, Google DeepMind's Gemini CLI, and Cursor.

The skills in this repository follow the standardized Agent Skills format.

[!NOTE] Just want to give your agent access to the Hugging Face Hub? Start with hf-cli. It's the recommended first Skill to install: it teaches your agent every hf command (search models, manage datasets and buckets, launch Spaces, run jobs) and is generated from your locally installed CLI so it stays current.

How do Skills work?

In practice, skills are self-contained folders that package instructions, scripts, and resources together for an AI agent to use on a specific use case. Each folder includes a SKILL.md file with YAML frontmatter (name and description) followed by the guidance your coding agent follows while the skill is active.

[!TIP] If your agent doesn't support skills, you can use agentsmd/AGENTS.md directly as a fallback.

The skills in this repository are also available through:

Cursor Marketplace (https://cursor.com/marketplace/huggingface)
Codex Plugins Directory (https://developers.openai.com/codex/plugins)

Installation

Hugging Face skills are compatible with Claude Code, Codex, Gemini CLI, and Cursor.

Claude Code

Copy & paste — that's it

/plugin marketplace add huggingface/skills

To install a skill, run:

Copy & paste — that's it

/plugin install <skill-name>@huggingface/skills

For example:

Copy & paste — that's it

/plugin install hf-cli@huggingface/skills

Codex

Copy or symlink any skills you want to use from this repository's skills/ directory into one of Codex's standard .agents/skills locations (for example, $REPO_ROOT/.agents/skills or $HOME/.agents/skills) as described in the Codex Skills guide.
Once a skill is available in one of those locations, Codex will discover it using the Agent Skills standard and load the SKILL.md instructions when it decides to use that skill or when you explicitly invoke it.
If your Codex setup still relies on AGENTS.md, you can use the generated agentsmd/AGENTS.md file in this repo as a fallback bundle of instructions.

Gemini CLI

This repo includes gemini-extension.json to integrate with the Gemini CLI.
Install locally:

Copy & paste — that's it

gemini extensions install . --consent

or use the GitHub URL:

Copy & paste — that's it

gemini extensions install https://github.com/huggingface/skills.git --consent

See Gemini CLI extensions docs for more help.

Cursor

This repository includes Cursor plugin manifests:

.cursor-plugin/plugin.json
.mcp.json (configured with the Hugging Face MCP server URL)

Install from repository URL (or local checkout) via the Cursor plugin flow.

For contributors, regenerate manifests with:

Copy & paste — that's it

./scripts/publish.sh

Skills

This repository contains a few skills to get you started. You can also contribute your own skills to the repository.

Available skills

Name	Description	Documentation
`hf-cli`	Execute Hugging Face Hub operations using the hf CLI. Download models/datasets, upload files, manage repos, and run cloud compute jobs.	SKILL.md
`hf-mem`	Estimate memory requirements for Hugging Face Safetensors and GGUF model weights, including optional KV cache estimates for inference planning.	SKILL.md
`huggingface-best`	Find the best AI model for any task by querying Hugging Face leaderboards and benchmarks. Recommends top models based on task type, hardware constraints, and benchmark scores.	SKILL.md
`huggingface-community-evals`	Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom evaluations with vLLM/lighteval.	SKILL.md
`huggingface-datasets`	Explore, query, and extract data from any Hugging Face dataset using the Dataset Viewer REST API and npx tooling. Zero Python dependencies — covers split/config discovery, row pagination, text search, filtering, SQL via parquetlens, and dataset upload via CLI.	SKILL.md
`huggingface-gradio`	Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.	SKILL.md
`huggingface-llm-trainer`	Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes hardware selection, cost estimation, Trackio monitoring, and Hub persistence.	SKILL.md
`huggingface-local-models`	Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.	SKILL.md
`huggingface-lora-space-builder`	Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.	SKILL.md
`huggingface-paper-publisher`	Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.	SKILL.md
`huggingface-papers`	Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata like authors, linked models, datasets, Spaces, and media URLs when needed.	SKILL.md
`huggingface-spaces`	Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.	SKILL.md
`huggingface-tool-builder`	Build reusable scripts for Hugging Face Hub and API workflows. Useful for chaining API calls, enriching Hub metadata, or automating repeated tasks.	SKILL.md
`huggingface-trackio`	Track and visualize ML training experiments with Trackio. Log metrics via Python API and retrieve them via CLI. Supports real-time dashboards synced to HF Spaces.	SKILL.md
`huggingface-vision-trainer`	Train and fine-tune object detection models (RTDETRv2, YOLOS, DETR and others) and image classification models (timm and transformers models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3) using Transformers Trainer API on Hugging Face Jobs infrastructure or locally. Includes COCO dataset format support, Albumentations augmentation, mAP/mAR metrics, trackio tracking, hardware selection, and Hub persistence.	SKILL.md
`huggingface-zerogpu`	Coding rules for Gradio Spaces using Hugging Face Spaces ZeroGPU hardware. Covers `@spaces.GPU`, duration and quota tuning, pickle-based process isolation, `gr.State` semantics across the worker boundary, the CUDA availability model, concurrency safety, and CUDA wheel-only build constraints.	SKILL.md
`train-sentence-transformers`	Train or fine-tune sentence-transformers models across all three architectures: SentenceTransformer (bi-encoder embeddings), CrossEncoder (rerankers), and SparseEncoder (SPLADE). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing.	SKILL.md
`transformers-js`	Run state-of-the-art machine learning models directly in JavaScript/TypeScript for NLP, computer vision, audio processing, and multimodal tasks. Works in Node.js and browsers with WebGPU/WASM using Hugging Face models.	SKILL.md
`trl-training`	Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.	SKILL.md

Using skills in your coding agent

Once a skill is installed, mention it directly while giving your coding agent instructions:

"Use the HF LLM trainer skill to estimate the GPU memory needed for a 70B model run."
"Use the HF model evaluation skill to launch run_eval_job.py on the latest checkpoint."
"Use the HF dataset creator skill to draft new few-shot classification templates."
"Use the HF paper publisher skill to index my arXiv paper and link it to my model."

Your coding agent automatically loads the corresponding SKILL.md instructions and helper scripts while it completes the task.

Contribute or customize a skill

Copy one of the existing skill folders (for example, hf-datasets/) and rename it.

Update the new folder's SKILL.md frontmatter:

Copy & paste — that's it

---
name: my-skill-name
description: Describe what the skill does and when to use it
---

# Skill Title
Guidance + examples + guardrails

Add or edit supporting scripts, templates, and documents referenced by your instructions.
Add an entry to .claude-plugin/marketplace.json with a concise, human-readable description.
Run:
Copy & paste — that's it
```
./scripts/publish.sh
```
to regenerate and validate all generated metadata.
Reinstall or reload the skill bundle in your coding agent so the updated folder is available.

Marketplace

The .claude-plugin/marketplace.json file lists skills with human-readable descriptions for the plugin marketplace. The CI validates that skill names and paths match between SKILL.md files and marketplace.json, but descriptions are maintained separately: SKILL.md descriptions guide when Claude activates the skill, while marketplace descriptions are written for humans browsing available skills.

Additional references

Browse the latest instructions, scripts, and templates directly at huggingface/skills.
Review Hugging Face documentation for the specific libraries or workflows you reference inside each skill.

Install the whole package (15 skills):

Copy & paste — that's it

npx skills add https://github.com/huggingface/skills

Or install a single skill:

Copy & paste — that's it

npx skills add https://github.com/huggingface/skills --skill <name>

Pick the skill name from the Skills tab — each entry there installs independently.