Skill UI

The official Hugging Face Hub CLI (`hf`) is a comprehensive command-line tool for managing all types of resources on the Hugging Face Hub. Use it to download, upload, synchronize, and manage models, datasets, Spaces, and cloud buckets. It facilitates secure authentication, local cache management, and complex data operations, making it essential for ML workflows.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

Integrate Langfuse into CI/CD pipelines (e.g., GitHub Actions) to automate the testing and validation of Large Language Models (LLMs). This guide covers prompt regression testing, tracing validation, and setting up experiment-driven quality gates, ensuring reliable and high-performing AI applications throughout the development lifecycle.

A comprehensive skill for fine-tuning and training large language and vision models using advanced techniques like TRL (SFT, DPO, GRPO) or Unsloth. This process runs entirely on managed Hugging Face cloud GPUs, eliminating the need for local GPU setup. It supports modern training workflows, model conversion (GGUF for local deployment), and ensures seamless artifact storage to the Hugging Face Hub.

This skill provides comprehensive tools for AI engineers and researchers to publish, manage, and link research papers directly on the Hugging Face Hub. It supports creating dedicated paper pages, linking papers to corresponding models and datasets, claiming authorship, and generating professional, markdown-based research articles with LaTeX support. Use it to streamline the entire academic publishing workflow from initial draft to final publication.

This skill is designed for running comprehensive evaluations of Hugging Face Hub models on local hardware. It supports multiple evaluation frameworks, including `inspect-ai` and `lighteval`, and provides flexibility in backend selection (e.g., `vllm`, Transformers, or `accelerate`) to optimize for performance and compatibility. Use this for local GPU benchmarking, smoke testing, and backend selection, but note that it does not handle remote job orchestration or result publishing.

This skill provides comprehensive analysis and structured data extraction for academic research papers hosted on Hugging Face and arXiv. It can read paper content in markdown format, retrieve key metadata (authors, abstracts, GitHub repos), and identify linked assets such as associated models, datasets, and Spaces. Use this when the user provides a Hugging Face or arXiv URL, or explicitly requests a summary or explanation of an AI research topic.

This skill provides a managed cloud environment for training and fine-tuning advanced vision models. Users can build and customize models for object detection (e.g., DETR, YOLOS), image classification, and segmentation (SAM/SAM2). By leveraging Hugging Face Jobs, training is executed on powerful cloud GPUs without requiring local GPU setup, and all resulting models are automatically saved to the Hugging Face Hub.

Reads `.agent.md` or `.prompt.md` files, assesses task complexity, tooling, and requirements, then recommends the most cost-efficient GitHub Copilot model(s) (e.g., GPT-5, Claude Sonnet) with rationale for users across different subscription tiers and priorities.

Python SDK for Biohub's ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding. Supports local model inference and hosted clients for protein sequence completion, structure prediction, and embedding extraction. Requires Python 3.12+ and isolated environment setup.

Load Hugging Face Hub models, run pipeline inference, generate text, and fine-tune with the Trainer API across NLP, vision, audio, and multimodal tasks using Python and PyTorch.

This skill provides the frontend interface for image generation tasks. It has been moved to a dedicated GitHub repository containing other image-generation skills. It runs only when explicitly called by name and does not invoke models directly. Users can install it via the npx skills command to access the web interface for generating images.