skills.rest
huaibovip
huaibovipCOMMUNITY
Explore all skills by this author →
GitHub

nature-reader

Convert academic papers into bilingual source-anchored Markdown readers with figures, tables, and rendered equations.

Updated Jul 5, 2026
Search Tags:#pdf#markdown#academic reading#paper translation#bilingual reader#source map#equation rendering
One-click install
npx skills add https://github.com/huaibovip/research-marketplace --skill nature-reader-huaibovip
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nature-reader
Source: https://github.com/huaibovip/research-marketplace/tree/main/plugins/nature-skills/skills/nature-reader
Command: npx skills add https://github.com/huaibovip/research-marketplace --skill nature-reader-huaibovip

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Reading and translating academic papers across PDF, DOI, arXiv, HTML, or pasted text often produces lossy summaries, broken equations, and figures detached from the text that discusses them. This Skill builds a full-paper Chinese-English Markdown reader where every paragraph, figure, table, and equation keeps a stable source anchor back to the original document. ## Core Features & Use Cases - Bilingual full-paper reader: Generates paragraph-level Original/中文 pairs in paper.md with page and block anchors, never degrading to a summary-only output. - Figure, table, and equation handling: Crops figures and tables into assets/ near their first substantive mention, renders display equations as Markdown math with stable E... IDs, and falls back to original image crops for low-confidence or scanned formulas. - Source map and validation: Produces source_map.json and translation_notes.md for traceability, plus a deterministic script that validates math delimiters, equation anchors, and source-map linkage. - Use Case: Give it a scanned conference PDF and receive a complete bilingual reading bundle with OCR confidence labels, cropped figures placed near the relevant prose, and an equation index linking every formula to its page. ## Quick Start Use the nature-reader skill to turn this paper PDF into a full Chinese-English side-by-side Markdown reader with figures, equations, and a source map.

Frequently Asked Questions about nature-reader

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

FAQPage Schema
How do I translate a research paper PDF into Chinese-English bilingual Markdown?▼

Provide the PDF and request a full bilingual reader. The skill extracts the text layer, builds paragraph-level Original/中文 pairs in paper.md, crops figures and tables into assets/, and records every block in source_map.json for traceability.

Can I generate a paper reader from just a DOI or arXiv link?▼

Yes. The skill resolves the DOI or arXiv identifier to the article, preferring lawful open-access versions, then processes the resolved PDF or HTML. If only the abstract is reachable, it builds a draft reader and marks the missing content.

Does it work with scanned PDFs that need OCR?▼

Yes. A dedicated scanned-PDF workflow OCRs every page, records per-block confidence levels, and flags uncertain text in translation_notes.md instead of guessing. Equations are cropped as original images first, with any transcription labeled low confidence.

How are equations handled in the Markdown output?▼

Display equations render inside $$...$$ blocks with stable E001-style anchors and source-map entries; inline math uses $...$. Image-only or unreadable formulas keep the original crop from assets/equations/ rather than invented LaTeX, and a validator script checks all delimiters and anchors.

What are the limitations of automated paper translation and reading?▼

Scanned pages, two-column layouts, and copyright-restricted full text may require manual checking, and the skill labels these gaps rather than fabricating content. It also does not produce summary-only output unless explicitly requested, and chat responses stay short for copyrighted sources.

Related Skills

Explore More Education & Research Skills→
Yjj0333Yjj0333

nature-reader

Convert academic papers into bilingual Chinese-English Markdown readers with figures, equations, and source anchors.

Community
Advanced
BeopsooKimBeopsooKim
2

research-artifact-reviewer

Review academic papers, thesis chapters, reports, and academic emails for rigor and contribution clarity.

Community
Intermediate
biomaps-infrabiomaps-infra

lib-pyzotero

Manage Zotero items, collections, tags, and attachments via the Web API v3.

Official
Intermediate
littlt-momo-c-yfclittlt-momo-c-yfc

nature-reader

Generates bilingual Chinese-English Markdown readers with figure extraction and source anchors from academic papers.

Community
Advanced