nature-reader

Convert research papers into bilingual Markdown with figures and source maps.

Updated May 13, 2026
One-click install
npx skills add https://github.com/Ricardo-Vae/codex-research-skills --skill nature-reader-ricardo-vae
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nature-reader
Source: https://github.com/Ricardo-Vae/codex-research-skills/tree/main/skills/nature-skills/nature-reader
Command: npx skills add https://github.com/Ricardo-Vae/codex-research-skills --skill nature-reader-ricardo-vae

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It converts full research papers into a complete Markdown reading artifact with original text and Chinese translation aligned, while preserving figure/table proximity and stable source anchors for traceable reading.

Core Features & Use Cases

  • Full-paper bilingual Markdown: Produces a complete paper.md with the paper’s original paragraph structure and a readable original/translation pairing.
  • Source-grounded traceability: Builds a source_map.json with stable block IDs so every substantive block can be referenced by page and ID.
  • Figure/table-aware placement and crops: Extracts and places figures/tables near the discussion that introduces or interprets them, with tight crops when needed.

Quick Start

Use the nature-reader skill to generate a full bilingual Markdown reader for an entire paper, keeping figures and tables near their relevant prose and producing paper.md plus a source_map.json for source-grounded answers.

Frequently Asked Questions about nature-reader

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

FAQPage Schema
How do I convert a research paper PDF to bilingual Markdown with figures?

Converting a research paper PDF to bilingual Markdown is done by processing the document to produce a complete paper.md with aligned original text and Chinese translation, while extracting and placing figures near their relevant prose.

What is the best way to translate an arXiv paper while keeping citations traceable?

Translating an arXiv paper with traceable citations requires generating a source_map.json containing stable block IDs, ensuring every substantive text block can be referenced by its original page and ID for source-grounded evidence tracing.

Can I extract and place figures near their discussion text when converting publisher HTML to Markdown?

Extracting and placing figures near their discussion text from publisher HTML is fully supported, preserving the paper's original structure and ensuring tables and figures remain close to the paragraphs that interpret them.

Does this paper translation tool support reading original text alongside the translation?

The paper translation tool supports original-vs-translation reading by generating a complete Markdown artifact that pairs the paper's original paragraph structure with a readable Chinese translation side by side.

What are the limitations of converting full papers into figure-aware Markdown?

A limitation of converting full papers into figure-aware Markdown is that it relies on the input document's structure; heavily complex or irregularly formatted manuscripts may challenge the stable source anchor generation and precise figure extraction.