12 skills
The `hf` CLI manages Hugging Face Hub repositories, models, datasets, and Spaces from the terminal. It handles downloads, uploads, cache, inference endpoints, jobs, and webhooks. It replaces the depre
Read-only API client for the Hugging Face Dataset Viewer. Fetches dataset splits, paginates rows, runs text search and filter queries, retrieves parquet shard URLs, and reads size and column statistic
Manages datasets on the Hugging Face Hub. Handles repo initialization, configuration, streaming row updates, and SQL-based querying and transformation via DuckDB. Works alongside the HF MCP server, wh
Adds and manages evaluation results in Hugging Face model cards using the model-index metadata format. Supports extracting benchmark tables from README files, importing scores from the Artificial Anal
Runs Python workloads on Hugging Face managed infrastructure — CPUs, GPUs, or TPUs — without any local setup. Supports UV scripts with inline dependencies, Docker-based jobs, scheduled tasks, and resu
Trains and fine-tunes language models on Hugging Face's cloud GPU infrastructure using TRL. Supports SFT, DPO, GRPO, and reward modeling. Handles job submission, dataset validation, cost estimation, a
Fetches and parses Hugging Face paper pages using arXiv IDs or HF paper URLs. Returns full paper content as markdown or structured metadata including authors, linked models, datasets, spaces, GitHub r
Publishes and manages research papers on the Hugging Face Hub. Handles indexing papers from arXiv, linking them to models and datasets, claiming authorship, and generating markdown-based research arti
Builds reusable command-line scripts that interact with the Hugging Face API to fetch, filter, and process models, datasets, spaces, and papers. Scripts support chaining and piping for multi-step work
Trackio is an experiment tracking library for ML training. It logs metrics via a Python API, fires structured alerts for diagnostic conditions, and exposes a CLI for querying logged data. Metrics sync
Trains and fine-tunes vision models on Hugging Face Jobs cloud GPUs, covering object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models including MobileNetV3, ResNet, ViT),
Gradio is a Python library for building web-based UIs for machine learning models and data tools. It provides both a high-level Interface class and a lower-level Blocks API for layouts, event wiring,
