read-arxiv-paper
Installation
Summary
Fetch and summarize arxiv papers from their LaTeX source code.
- Normalizes arxiv URLs to source format (/src/), downloads .tar.gz archives, and unpacks them locally with caching to avoid re-downloads
- Locates the LaTeX entrypoint (main.tex or equivalent) and recursively reads all relevant source files to reconstruct the full paper
- Generates markdown summaries in the local knowledge directory with contextual tags, designed for integration with the nanochat project
- Includes guidance for connecting paper insights and techniques to existing nanochat codebase patterns and architecture
SKILL.md
You will be given a URL of an arxiv paper, for example:
https://www.arxiv.org/abs/2601.07372
Part 1: Normalize the URL
The goal is to fetch the TeX Source of the paper (not the PDF!), the URL always looks like this:
https://www.arxiv.org/src/2601.07372
Notice the /src/ in the url. Once you have the URL:
Part 2: Download the paper source
Fetch the url to a local .tar.gz file. A good location is ~/.cache/nanochat/knowledge/{arxiv_id}.tar.gz.
(If the file already exists, there is no need to re-download it).