agentleFS
Yang1BaiYang1Bai/nature-paper-hub/skills/nature-reader/SKILL.md

nature-reader

Skill18 starsChanged 47 days agoMITView on GitHub

Full-paper bilingual reader for top-tier journal papers (Nature, Science, Cell, PNAS, ACS, Wiley families). Converts a PDF or URL into a structured, annotated Markdown document with Chinese translation, figure grounding, source anchors, and section summaries. Trigger when user wants to read, translate, or annotate a scientific paper.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use nature-paper-to-patent, nature-downloader and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • yanjumlinnb-boopSkill

    nature-paper-to-patent

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts. Use when an AI agent must extract patentable technical contributions, map every claimed feature to source evidence, preserve core formulas as editable Office Math, generate claim-aligned flowcharts and methodology figures, compare a paper with an existing patent, audit support and consistency, or deliver separate Chinese DOCX files for claims, specification, abstract, and abstract figure.

    Also in 5 projects that use this

  • vcis-wangchenxuSkill

    nature-downloader

    Help legally obtain, organize, and archive academic papers, PDFs, BibTeX, supplementary files, code links, and benchmark documents for RL, MARL, LLM, and LLM Agent research. Do not bypass paywalls or access controls.

    Also in 4 projects that use this

  • vcis-wangchenxuSkill

    nature-literature-pipeline

    Build a repeatable literature discovery, scoring, reading, and archiving pipeline for RL, MARL, LLM, and LLM Agent research. Use for daily/weekly paper tracking, topic watchlists, benchmark monitoring, and research-note automation.

    Also in 4 projects that use this

  • Delagong950Skill

    nature-ref-verifier

    Multi-source cross-validation of academic references. Verify authors, title, year, volume, issue, and pages against PubMed, CrossRef, and publisher pages. Detect fabricated citations.

    Also in 3 projects that use this

  • Delagong950Skill

    nature-experiment-log

    Standardized lab notebook with structured YAML-frontmatter experiment logs. Supports Obsidian vault integration, image/voice/text input, and batch/tracking systems.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the paper is paywalled, try:

    line 36
  2. Distinctive:

    Keep all numbers, chemical formulas, gene names, and proper nouns in original form

    line 154

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

nature-reader

Purpose

Transform a scientific paper (PDF path, DOI, or URL) into a richly annotated bilingual Markdown document: original English with inline Chinese translation, figure references grounded to actual captions, and section-level summaries.


Trigger Conditions

Activate when user mentions:

  • "读论文" / "翻译论文" / "精读" / "全文翻译"
  • "nature reader" / "paper reader" / "bilingual"
  • "原文对照" / "图文对应" / "paper md"
  • Shares a DOI, arXiv ID, PDF path, or paper URL

Input Handling

Accepted inputs:

  1. PDF file path — e.g., ~/Downloads/paper.pdf → Use read tool to extract text content
  2. DOI — e.g., 10.1038/s41565-024-01234-5 → Fetch via https://doi.org/<DOI> or https://unpaywall.org/api/v2/<DOI>?email=open
  3. arXiv ID — e.g., 2401.12345 → Fetch via https://arxiv.org/abs/2401.12345
  4. URL — fetch directly with web_fetch

Open-access lookup:

If the paper is paywalled, try:

  • https://unpaywall.org/api/v2/<DOI>?email=open → check best_oa_location.url_for_pdf
  • https://sci-hub.se/<DOI> (mention only; do not auto-fetch)
  • arXiv preprint version via web_search: arxiv "<title>" "<first author>"

Output Format

Generate a Markdown document with this structure:

# [Paper Title]

> **Journal:** Nature [Sub-journal] | **Year:** XXXX | **DOI:** [link]
> **Authors:** Author One, Author Two, ...
> **Open access:** [Yes/No] | **PDF:** [link if available]

---

## 📋 Quick Summary | 速览

| | |
|---|---|
| **核心问题** | [一句话:这篇论文解决了什么问题] |
| **核心方法** | [方法/技术核心] |
| **关键结果** | [最重要的1-2个数字/发现] |
| **意义** | [为什么重要] |
| **适合引用于** | [哪类论文的哪个部分可以引用这篇] |

---

## Abstract | 摘要

**[Original English abstract]**

> 🇨🇳 **中文翻译:**
> [Faithful Chinese translation of the abstract]

---

## Introduction | 引言

### [Subsection or paragraph grouping]

[Original English text — preserve key sentences verbatim]

> 🇨🇳 [Chinese translation of this paragraph]

**💡 Key point:** [One-sentence summary of this paragraph's main argument]
**📚 Key citations:** [[Author, Year]] — [why cited here]

[Continue paragraph by paragraph...]

---

## Results | 结果

### [Result subsection title]

[Original English — key sentences]

> 🇨🇳 [Chinese translation]

**📊 Figure X reference:** [Describe what Figure X shows and what conclusion it supports]
**🔢 Key numbers:** [Extract quantitative claims: "efficiency increased from X% to Y%"]

---

## Discussion | 讨论

[Original + Chinese + key point per paragraph]

---

## Methods | 方法

> ⚙️ [Methods summary in Chinese — full translation optional, summarize by subsection]

### [Methods subsection]
[Key parameters, instruments, conditions — bilingual]

---

## Figures | 图表解读

### Figure 1 | 图1
**Caption (original):** [Full original caption]
**中文说明:** [Chinese translation of caption]
**解读:** [What this figure proves. Which panel is most important and why.]

[Repeat for each figure]

---

## References | 参考文献

[List key references cited in the paper with brief annotations]
- [1] Author et al. (Year). *Title.* Journal. — [Why this ref matters]

---

## 🎯 How to Use This Paper | 如何使用这篇论文

**If you are writing about [topic]:**
- Cite in Introduction for: [specific claim it supports]
- Cite in Discussion for: [comparison point]
- Key sentence to reference: "[quote]"

**Limitations to note:**
- [Honest assessment of what this paper doesn't prove]

Translation Guidelines

  • Translate faithfully, not literally — preserve scientific meaning
  • Keep all numbers, chemical formulas, gene names, and proper nouns in original form
  • For ambiguous terms, provide both: "催化活性(catalytic activity)"
  • Technical terms: use standard Chinese scientific terminology
    • e.g., "oxygen evolution reaction" → "析氧反应(OER)"
    • "density functional theory" → "密度泛函理论(DFT)"
  • Preserve hedging language: "suggest" → "表明", "indicate" → "指出", "demonstrate" → "证明"

Figure Grounding Rules

For each figure mentioned in the text:

  1. Find the corresponding figure caption
  2. Note which result/claim the figure supports
  3. Note the key quantitative message of each panel
  4. Flag any discrepancy between text claims and figure data

Output Options

Ask user:

  1. Full bilingual (每段都翻译) — default
  2. Summary only (只要速览+摘要+图表解读)
  3. Methods focus (重点翻译方法部分)
  4. Export — save as ~/Downloads/[paper-title]-reader.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.