Transformers

This handles Hugging Face's transformers library for working with pre-trained models across NLP, vision, and audio tasks. You get pipelines for quick inference on things like text generation, classification, and question answering, plus lower-level APIs when you need fine-tuning or custom preprocessing. The skill covers the standard workflow: load a model with AutoModel classes, tokenize inputs, run inference or training with the Trainer API. It's comprehensive without being overwhelming, though you'll still need to know which model architecture fits your task. The pipeline API is genuinely convenient for prototyping, and the references break down generation strategies, tokenization, and training patterns clearly enough to get productive fast.

skills.sh installs: 383
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill transformers --agent claude-code

Installs into .claude/skills of the current project.

Files

Transformers

Overview

The Hugging Face Transformers library provides access to thousands of pre-trained models for tasks across NLP, computer vision, audio, and multimodal domains. Use this skill to load models, perform inference, and fine-tune on custom data.

Installation

Install transformers and core dependencies:

uv pip install torch transformers datasets evaluate accelerate

For vision tasks, add:

uv pip install timm pillow

For audio tasks, add:

uv pip install librosa soundfile

Authentication

Many models on the Hugging Face Hub require authentication. Set up access:

from huggingface_hub import login
login()  # Follow prompts to enter token

Or set environment variable:

export HUGGINGFACE_TOKEN="your_token_here"

Get tokens at: https://huggingface.co/settings/tokens

Quick Start

Use the Pipeline API for fast inference without manual configuration:

from transformers import pipeline

# Text generation
generator = pipeline("text-generation", model="gpt2")
result = generator("The future of AI is", max_length=50)

SKILL.md on GitHub