ArXiv Paper Search & Parsing
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md and install @org-rn88lg3j/arxiv-paper.
About this skill
Problem
When tracking AI research, it is common to search arXiv, open abstract pages, download PDFs, and extract text for model reading. That workflow can be fragmented.
How It Works
This skill wraps a few arXiv-related operations into tool calls:
- Search papers: scripts.tools.search_arxiv takes an English keyword query and optional maxResults, defaulting to 5.
- View recent AI papers: scripts.tools.get_recent_ai_papers targets cs.AI/recent.
- Get PDF links: scripts.tools.get_arxiv_pdf_url accepts a paper URL or arXiv ID.
- Parse content: scripts.tools.parse_paper_content prefers HTML and falls back to PDF, with optional paperInfo for metadata.
It requires XBY_APIKEY. If missing, ask for the key and save it instead of fabricating search results.
Boundaries
It is useful for arXiv paper search, PDF link retrieval, and extracting readable content. It is not an offline tool when the key is absent and is not a full reference manager. Search queries work best in English, and parsing depends on HTML or PDF accessibility.
Use Cases
- When researching LLM inference optimization, search arXiv with English keywords and collect abstracts.
- When tracking cs.AI/recent updates, list the newest AI papers and pick candidates to read.
- After obtaining an arXiv ID, retrieve the PDF download link and save it to a local library.
- Before reading, parse the HTML or PDF content to extract methods, experiments, and conclusions.
Best For
- Research-focused algorithm engineers tracking frontier AI papers who need fast search, PDF links, and parsed content.
- Engineers writing technical surveys who need to collect candidate arXiv papers around English keywords.
- Graduate students studying LLMs who need to review recent cs.AI papers and extract method details.
- Research assistants maintaining reading notes who need to organize paper links and parsed body content.
Related Skills
Reads conversation-trace files to generate an animal- or mythology-based soul mirror card and Johari Window insights.
A Deling knowledge-base research workflow that clarifies intent, runs broad and vertical searches, supplements with web sources, validates diversity, and traces key claims.
A SiYuan knowledge-base management skill for double-link parent indexes, MOCs, numbered documents, tags, repo sync, and WeChat import workflows.
A structured workflow for academic literature reviews, covering multi-database search, screening, thematic synthesis, citation validation, and PDF output.