paper-researcher

Search arXiv and OpenAlex, download PDFs, convert to Markdown, and save analyses to WPS notes.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/dy9759/SkillCollection --skill paper-researcher
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper-researcher
Source: https://github.com/dy9759/SkillCollection/tree/main/skills/paper-researcher
Command: npx skills add https://github.com/dy9759/SkillCollection --skill paper-researcher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires arxiv, markitdown, pymupdf, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the repetitive and fragmented tasks involved in literature discovery and reading by searching for papers, downloading PDFs, converting them to text, and producing structured analyses ready to store in WPS notes.

Core Features & Use Cases

  • Multi-source search: Query arXiv and OpenAlex to find relevant papers with ranked results.
  • Reliable PDF retrieval: Download PDFs with retries and integrity checks, and fall back to canonical arXiv links when needed.
  • PDF → Markdown conversion: Convert PDFs to Markdown using markitdown or pymupdf and handle scanned/low-quality PDFs with graceful failure.
  • WPS note integration: Save or append analyzed summaries into WPS notes via wpsnote-cli or MCP, enabling literature reviews and per-paper deep reading.
  • Use case: Run a topic search, download top papers as Markdown, extract methods and results, and compile a literature-review note in WPS.

Quick Start

Use the paper-researcher skill to search arXiv for transformer attention, download the top result as Markdown, analyze its methods and results, and save the structured summary into WPS notes.

Frequently Asked Questions about paper-researcher

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate arXiv paper search and PDF to markdown conversion for a literature review?

Yes, you can save literature review summaries directly into WPS notes using wpsnote-cli or MCP integrations. This skill structures analyzed paper summaries and appends them into WPS notes, enabling organized per-paper deep reading and review compilation.

Can I save extracted paper summaries and literature reviews directly into WPS notes?

Yes, you can save literature review summaries directly into WPS notes using wpsnote-cli or MCP integrations. This skill structures analyzed paper summaries and appends them into WPS notes, enabling organized per-paper deep reading and review compilation.

What is the best way to handle scanned or low-quality PDF text extraction when converting academic papers?

Converting academic PDFs to markdown requires Python along with the arxiv, markitdown, and pymupdf libraries installed. These dependencies enable the search, download, and text extraction processes needed for paper analysis.

Does PDF to markdown conversion for academic papers handle scanned documents or low-quality PDFs?

PDF to markdown conversion handles scanned or low-quality PDFs with graceful failure mechanisms. The skill uses markitdown and pymupdf to attempt text extraction, ensuring reliable processing of downloaded academic literature.

What do I need to set up to search arXiv and convert PDFs to markdown?

To search arXiv and convert PDFs to markdown, you need Python installed along with the arxiv, markitdown, and pymupdf libraries. This environment enables automated paper search, PDF downloading, and text extraction for literature analysis.