Skip to content
Agentmart
Submit a tool

Best agent skills for Hugging Face

We found 93 agent skills for Hugging Face in the catalog; these are the 15 that rank highest. The order comes from our rank, which weighs adoption, freshness, documentation and publisher identity. Nobody can pay for a place on this list. hf-cli, huggingface-spaces and deepstream-import-vision-model lead it. hf-cli and huggingface-spaces are published by the company that makes them. transformers comes from the largest repository here (54,411 stars). 9 of the 15 had activity in the last 30 days. Each entry lists why it made the list and links to its install page.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

Top 15 of 93

  1. 1
    hf-cli

    huggingfaceOfficial

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

    • Published by the vendor
    • Repository has 11.2K stars
    • Active in the last 30 days

    ★ 11.2KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6

  2. 2
    huggingface-spaces

    huggingfaceOfficial

    Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging…

    • Published by the vendor
    • Repository has 11.2K stars
    • Open source (Apache-2.0)

    ★ 11.2KLast active Aug 3, 2026Claude Code, Claude apps, Codex, Cursor +6

  3. 3
    deepstream-import-vision-model

    Tushar Khinvasara <tkhinvasara@nvidia.com>

    Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end…

    • Repository has 3.7K stars
    • Open source (CC-BY-4.0 AND Apache-2.0)
    • Ships helper scripts

    ★ 3.7KLast active Sep 4, 2026Claude Code, Claude apps, Codex, Cursor +6

  4. 4
    nvflare-convert-huggingface

    NVIDIA FLARE Team <federatedlearning@nvidia.com>

    Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation…

    • Repository has 3.7K stars
    • Open source (Apache-2.0)
    • Ships helper scripts

    ★ 3.7KLast active Sep 13, 2026Claude Code, Claude apps, Codex, Cursor +6

  5. 5
    stable-diffusion-image-generation

    taracodlabs

    Generate images via Stable Diffusion (HuggingFace Diffusers, local/API)

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 863Last active Oct 19, 2026Claude Code, Claude apps, Codex, Cursor +6

  6. 6
    stable-diffusion-image-generation

    taracodlabs

    Generate images using Stable Diffusion via HuggingFace Diffusers library locally or via API

    • Active in the last 30 days
    • Open source (Apache-2.0)

    ★ 863Last active Oct 19, 2026Claude Code, Claude apps, Codex, Cursor +6

  7. 7
    github-trending

    aeonfun

    Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line…

    • Active in the last 30 days
    • Open source (MIT)

    ★ 782Last active Oct 1, 2026Claude Code, Claude apps, Codex, Cursor +6

  8. 8
    quark-torch-llm-ptq

    amd

    Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan…

    • Active in the last 30 days
    • Open source (MIT)

    ★ 465Last active Oct 1, 2026Claude Code, Claude apps, Codex, Cursor +6

  9. 9
    transformers

    K-Dense-AI

    Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal…

    • Largest repository here (54,411 stars)
    • Active in the last 30 days
    • Open source (MIT)

    ★ 54.4KLast active Oct 1, 2026Claude Code, Claude apps, Codex, Cursor +6

  10. 10
    hugging-face-stat

    cafe3310

    获取 Hugging Face 上的模型、数据集和 Space 的统计信息

    • Open source (Apache-2.0)
    • Ships helper scripts
    • For bash

    ★ 256Last active Jun 26, 2026Claude Code, Claude apps, Codex, Cursor +6

  11. 11
    quark-torch-llm-ptq-eval

    amd

    L3 recipe that runs a Torch LLM PTQ end-to-end for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input): quantize → validate →…

    • Active in the last 30 days
    • Open source (MIT)

    ★ 186Last active Sep 28, 2026Claude Code, Claude apps, Codex, Cursor +6

  12. 12
    huggingface-accelerate

    Orchestra-Research

    Simplest distributed training API.

    • Repository has 13.9K stars
    • Open source (MIT)

    ★ 13.9KLast active Jun 16, 2026Claude Code, Claude apps, Codex, Cursor +6

  13. 13
    huggingface-tokenizers

    Orchestra-Research

    Fast tokenizers optimized for research and production.

    • Repository has 13.9K stars
    • Open source (MIT)

    ★ 13.9KLast active Jun 16, 2026Claude Code, Claude apps, Codex, Cursor +6

  14. 14
    hf-cli

    metaspartan

    Inspect and manage Hugging Face Hub models, datasets, Spaces, repositories, cache, authentication, and downloads with the current hf CLI.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 32Last active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

  15. 15
    huggingface-datasets

    metaspartan

    Explore, validate, filter, paginate, export, and prepare Hugging Face datasets through the Dataset Viewer API and Hub tooling.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 32Last active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6

Related