Nature Reader
Turn PDFs, DOI links, arXiv IDs, or publisher HTML into full Chinese–English side-by-side Markdown readers with figures, tables, and source anchors—not a summary dump.
Overview
Nature Reader is an agent skill most often used in Idea (also Build docs) that produces full-paper, figure-aware Chinese–English Markdown readers grounded in exact source anchors from PDF, DOI, or arXiv inputs.
Install
npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-readerWhat is this skill?
- Default full-paper output: complete paper.md plus source_map.json, translation_notes.md, and assets/
- Block-level Chinese–English side-by-side with stable page and block anchors
- Figure and table extraction placed at first substantive mention with bilingual captions
- Inputs: PDF, DOI, arXiv, publisher HTML, or pasted text across disciplines
- Hard rule: must not collapse to summary-only unless the user explicitly asks for a summary
- Default bundle: paper.md, source_map.json, translation_notes.md, assets/
Adoption & trust: 1.1k installs on skills.sh; 17.8k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need to read and translate an entire paper with figures in place, but summary-only outputs lose structure, captions, and traceability.
Who is it for?
Researchers and builder-founders consuming long PDFs or arXiv preprints who require side-by-side translation and citeable block anchors.
Skip if: Users who explicitly want only a short summary or who cannot legally process the source document.
When should I use this skill?
User asks for full-paper translation, 中英文对照, figure/table-aware reading, or source-grounded Markdown from PDF/DOI/arXiv/HTML.
What do I get? / Deliverables
You receive a complete bilingual paper.md, source_map.json, translation_notes.md, and assets/ with figures and tables positioned at first substantive mention.
- paper.md
- source_map.json
- translation_notes.md
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Idea / research is the primary shelf because deep paper reading and bilingual comprehension happen while exploring technical or scientific foundations before build commitments. Research subphase is where primary literature intake belongs; this skill preserves full prose and traceable blocks for that work.
Where it fits
Convert an arXiv methods paper into a bilingual companion before choosing a model architecture.
Read a conference proceedings PDF with tables intact to judge if a technique is reproducible in your MVP.
Import a fully translated methods section into internal build docs with stable block IDs.
How it compares
Use instead of generic “summarize this PDF” skills—this preserves full prose flow and placement-aware figures, not abstract-only output.
Common Questions / FAQ
Who is nature-reader for?
Solo builders, ML engineers, and academics who want bilingual, full-length paper companions for agents and human reading.
When should I use nature-reader?
During Idea research for literature surveys, Validate when methods justify feasibility, or Build docs when importing rigorous sections into specs—whenever 中英文对照 or 全文翻译解读 is requested.
Is nature-reader safe to install?
Processing may involve external fetches for DOI/arXiv/HTML; review the Security Audits panel on this Prism page and only run on papers you are permitted to handle.
SKILL.md
READMESKILL.md - Nature Reader
# Full-Paper Markdown Reader Use this skill to turn a research paper into a complete Markdown reading artifact. The default output should read like a bilingual paper companion, not a summary dump: - keep the extractable prose, paragraph structure, and section flow - show original text and Chinese translation together at block level - extract figures and tables as assets and place them at the first substantive mention or interpretation point - keep captions attached to figures/tables with English caption text and Chinese caption translation - preserve stable page and block anchors for traceability - write a complete `paper.md` by default, plus `source_map.json`, `translation_notes.md`, and `assets/` This skill is for papers, preprints, and conference proceedings across disciplines. It is not limited to Nature-family journals. ## When to use Use this skill when the user wants any of the following: - translate an entire paper into a complete Markdown document - make a paper easier to read without losing the original wording - generate a full-paper reading file with original/translation alignment - keep figures or tables visually close to the claims they support - preserve exact source locations for every substantive block - build a source-grounded markdown artifact rather than a slide deck or short summary If the user only wants a summary, use a summarization skill instead. If the user only wants citation search, use a citation skill instead. ## Non-negotiable defaults When the user asks for paper translation, reading, `nature-reader`, `中英文对照`, `原文对照`, `全文翻译`, or `翻译解读`, produce a paragraph-level bilingual reader by default. Do not replace the reader with: - a Chinese-only summary - a paper review without original/translation alignment - figure captions without figure/table crops - a list of key points detached from source locations - only the abstract, introduction, or selected highlights If constraints prevent full processing, still create a draft reader and clearly label missing pages, missing figures/tables, untranslated blocks, or low-confidence OCR/crops in `translation_notes.md`. ## Core principle Translate for meaning, not for style. Preserve the paper's structure, evidence, hedging, terminology, equations, units, and citation markers. Keep the output in prose paragraphs unless the source itself is tabular or list-like. Do not collapse the paper into keyword bullets or slide-style notes. The reading file should help a reader move between: - original text - translated text - source location - figure or table evidence Each substantive source block should have a stable anchor and a visible bilingual pair: ```markdown <a id="S001"></a> **Source:** p.1 S001 **Original:** [source paragraph] **中文:** [faithful Chinese translation] ``` For copyrighted publisher PDFs, keep chat responses short and point to the local artifact. In local `paper.md`, include the bilingual reader only for the user-provided source file or clearly lawful open-access content; avoid reproducing large copyrighted text directly in chat. ## Workflow ### 1. Identify the source and paper type Determine whether the source is: - selectable-text PDF - scanned PDF - publisher HTML - DOI or arXiv link - pasted text or notes Then identify the paper type at a high level: - discovery or mechanism paper - methods or algorithm paper - resource or dataset paper - conference paper - review or p