Hugging Face publishes official AI agent skills for its tools, services, and developer workflows.
Browse 50 official AI agent skills across 13 Hugging Face repositories, with install commands and source links.
Install
Install a full repository package, then let your agent activate the right skill for the task.
Fetch this Markdown manifest as plain text: https://skillscout.sh/official/huggingface/huggingface_skills_skillscout.md. If your browser cannot display the Markdown directly, use curl or another text fetcher. Recommend the relevant Hugging Face skills package or packages for my goal, explain which individual skills matter, and wait for my approval. After I approve, install with the npx command. If no project is open, install it as an agent skill I can use later.
Skills packages
Covers Hugging Face CLI, huggingface-gradio, huggingface-datasets, huggingface-llm-trainer, huggingface-papers, transformers-js. The `hf` CLI manages Hugging Face Hub repositories, models, datasets, and Spaces from the terminal. Gradio is a Python library for building web-based UIs for machine learning models and data tools.
npx skills add huggingface/skills -y
Includes 5 official skills: cuda-kernels, rocm-kernels, cpu-kernels, xpu-kernels, triton-kernels.
npx skills add huggingface/kernels -y
Includes 1 official skill: add-or-fix-type-checking.
npx skills add huggingface/transformers -y
Includes 3 official skills: inference-server, installation, toml-config.
npx skills add huggingface/prime-rl -y
Includes 1 official skill: add-model-descriptions.
npx skills add huggingface/chat-ui -y
Includes 4 official skills: self-review, custom-blocks, diffusers-cli, model-integration.
npx skills add huggingface/diffusers -y
Includes 1 official skill: hf-release-notes.
npx skills add huggingface/huggingface_hub -y
Includes 1 official skill: example-skill.
npx skills add huggingface/upskill -y
Includes 1 official skill: trl-training.
npx skills add huggingface/trl -y
Includes 2 official skills: init-physics-intern, init-physics-intern.
npx skills add huggingface/physics-intern-skills -y
Includes 1 official skill: train-sentence-transformers.
npx skills add huggingface/sentence-transformers -y
Includes 1 official skill: transformers-to-mlx.
npx skills add huggingface/transformers-to-mlx -y
Includes 3 official skills: add-mlinter-rule, release, remove-mlinter-rule.
npx skills add huggingface/transformers-mlinter -y
Individual skills
50 skills
The `hf` CLI manages Hugging Face Hub repositories, models, datasets, and Spaces from the terminal.
Gradio is a Python library for building web-based UIs for machine learning models and data tools.
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 G...
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
Repository documentation
Covers Hugging Face CLI, huggingface-gradio, huggingface-datasets, huggingface-llm-trainer, huggingface-papers, transformers-js. The `hf` CLI manages Hugging Face Hub repositories, models, datasets, and Spaces from the terminal. Gradio is a Python library for building web-based UIs for machine learning models and data tools.
Install the full package:
npx skills add huggingface/skills -yInstall a specific skill:
npx skills add huggingface/skills@hf-cli -yUse the package when you want your agent to choose the relevant skill from this official Hugging Face repository.
View huggingface/skills on GitHub