skills.rest
AlexenderSokolov
AlexenderSokolovCOMMUNITY
Explore all skills by this author →
GitHub

nature-reader

Convert papers from PDF, DOI, arXiv, or HTML into bilingual source-anchored Markdown readers.

2|Updated Jun 18, 2026
Search Tags:#pdf#arxiv#figure extraction#academic reading#paper translation#bilingual reader#source map
One-click install
npx skills add https://github.com/AlexenderSokolov/deepscientist-lite-codex-plugin --skill nature-reader-alexendersokolov
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nature-reader
Source: https://github.com/AlexenderSokolov/deepscientist-lite-codex-plugin/tree/main/plugins/deepscientist-lite-academic/skills/nature-reader
Command: npx skills add https://github.com/AlexenderSokolov/deepscientist-lite-codex-plugin --skill nature-reader-alexendersokolov

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Reading and translating full academic papers manually is slow, and typical AI summaries lose the original text, figure placement, and source traceability needed for citation checks and follow-up questions. ## Core Features & Use Cases - Full-paper bilingual reader: Produces paragraph-level Original/中文 pairs in paper.md for every extractable block, never degrading to a summary unless explicitly requested. - Figure/table extraction and placement: Crops figures and tables into assets/ and places them near their first substantive mention with bilingual captions. - Source map and grounding: Generates source_map.json with stable page and block anchors so follow-up answers can cite exact locations like p.5 S014. - Use Case: Provide a DOI for a conference paper; the skill resolves it, extracts the full text, and delivers a Chinese-English Markdown reader with figures, a terminology table, and translation notes flagging any unretrievable content. ## Quick Start Use nature-reader to turn this paper PDF into a full Chinese-English side-by-side Markdown reader with figures placed near the relevant text 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 full 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 into assets/, and writes a source_map.json with page anchors for every block.

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 missing content.

Does paper translation work with scanned PDFs?▼

Yes, via OCR. Each block gets a confidence level in the source map, and low-confidence OCR results are flagged in translation_notes.md rather than silently corrected. Skewed or cut-off pages are noted explicitly.

How are figures and tables handled during paper reading?▼

Figures and tables are tightly cropped into assets/ and placed near their first substantive mention in the text, with both the original caption and a Chinese translation attached. Later references link back to the same figure card.

What are the limitations of automated full-paper translation?▼

Scanned pages, two-column ordering, image-only formulas, and copyright-restricted full text may require manual checking. When full text cannot be legally obtained, the skill works from available abstracts or metadata and labels the output as draft mode.

Related Skills

Explore More Education & Research Skills→
BraveDistributionBraveDistribution

download-paper

Download full-text PDFs from IEEE Xplore, ScienceDirect, and DOI links.

Community
Intermediate
q734738781q734738781
13

citation-grounding-and-claim-discipline

Review manuscript text for unsupported claims and missing citations.

Community
Intermediate
SamyakJhaveriSamyakJhaveri

citation-audit

Verify citation entries against official sources and generate audit reports.

Community
Advanced
aiyinluyaaiyinluya
2

sn-search-academic

Search academic papers across ArXiv, Semantic Scholar, PubMed, and Wikipedia.

Community
Intermediate