Skill UI

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles. Ideal for AI engineers and researchers.

Look up Hugging Face paper pages as markdown and query the papers API for structured metadata including authors, linked models, datasets, Spaces, GitHub repos, and project pages. Ideal for summarizing or analyzing AI research papers from hf.co or arXiv URLs and IDs.

Train object detection, image classification, and SAM/SAM2 segmentation models locally or on Hugging Face Jobs with dataset validation and Hub saving.

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics. It also covers creating and uploading datasets, and uploading agent traces.

This skill enables users to build reusable command-line scripts and utilities for interacting with the Hugging Face API. It supports chaining API calls, automating repetitive tasks, and processing model or dataset data efficiently. Scripts utilize HF_TOKEN for authentication and can leverage the hf CLI for advanced repository interactions.

Instrument LLM applications with Langfuse tracing, prompt versioning and evaluation. Covers SDK setup, masking sensitive data, span verification, dataset comparison and debugging production LLM pipelines.

A specialized skill for achieving asymptotic performance gains when classical algorithms are already near optimal. It leverages advanced mathematical techniques and probabilistic data structures (e.g., Bloom Filters, HyperLogLog, FFT, MinHash/LSH) to handle massive datasets (n ≥ 10⁶) by accepting bounded approximations or exploiting deep structural properties. Requires strict adherence to error parameter and complexity justification protocols.

Diagnose slow SQL queries using execution plans, preserve results, and validate indexing or query modifications against representative data. This skill helps debug performance issues, design efficient schemas, reduce database load, and improve application scalability for growing datasets.