What problem does it solve? Reading and analyzing AI research papers requires manually navigating arXiv pages, PDFs, and scattered metadata. This Skill lets you fetch Hugging Face paper pages as markdown and query structured metadata such as authors, linked models, datasets, Spaces, GitHub repos, and project pages through the Hugging Face papers API. ## Core Features & Use Cases - Markdown Paper Retrieval: Fetch any paper page as clean markdown via the .md endpoint or an Accept: text/markdown header, with automatic fallback to arXiv sources. - Structured Metadata Queries: Retrieve authors, summaries, upvotes, linked models/datasets/spaces, GitHub repos, and project pages as JSON from /api/papers/{PAPER_ID}. - Discovery and Management: Search papers semantically, list the Daily Papers feed, index new arXiv papers, claim authorship, and update paper links with an HF token. - Use Case: A user shares https://arxiv.org/abs/2602.08025 and asks for a summary. The Skill parses the arXiv ID, fetches the markdown content, and pulls linked models and datasets to produce a complete analysis. ## Quick Start Summarize the Hugging Face paper at https://huggingface.co/papers/2602.08025 and list its linked models and datasets.
