nature-skills

大家好，我是上海交通大学博士生袁一哲，目前主要从事医疗 AI 相关的研究与创业实践，计划落地浦东张江！有病理专病或者泛癌万人以上队列的朋友，正在创业的伙伴亦或者欣赏我的投资人等等可以添加我的个人微信，务必备注来意。感谢大家持续关注 nature-skill。如果你有任何需求，欢迎提交 issue；如果我们认为该需求有意义且可行，也会尽量推进实现。我们同样欢迎 PR，但请务必按照 README 后面说明的格式提交，以便我们更高效地审核与合并。 <table> <tr> <td align="center"> <b>个人微信</b><br> <img width="400" alt="个人微信" src="https://github.com/user-attachments/assets/9e2931fb-748b-418e-97ab-0515d191633d" /> </td> <td align="center"> <b>个人介绍</b><br> <img width="400" alt="个人介绍" src="https://github.com/user-attachments/assets/ef355bb8-7189-49a1-bfe0-b1c7dcc7e04e" /> </td> </tr> </table>

Hello everyone, I'm Yizhe Yuan, a Ph.D. candidate at Shanghai Jiao Tong University. My work primarily focuses on Medical AI research and entrepreneurial initiatives, and I am currently planning to establish related ventures in Zhangjiang, Pudong (Shanghai). If you have access to disease-specific pathology cohorts or large-scale pan-cancer cohorts (10,000+ patients), are building a startup in a related field, or are an investor interested in my work, feel free to connect with me via WeChat. Please include a brief note explaining the purpose of your contact request. Thank you for your continued interest in nature-skill. If you have any feature requests or suggestions, please feel free to submit an Issue. If we find the proposal meaningful and feasible, we will do our best to implement it. We also welcome Pull Requests (PRs). However, please follow the contribution format described later in this README to help us review and merge submissions more efficiently.

📢 课题组诚招“医学 + AI”实习生

<table border="0" cellpadding="10" cellspacing="0"> <tr> <td width="34%" valign="top" align="center" style="border: none; background-color: #f9f9f9; padding: 20px; border-radius: 8px;"> <span style="font-size: 14px; color: #666;">微信群聊</span><br> <img width="1080" height="1632" alt="feae2bf93421fbf99d21f20f2cf5562a" src="https://github.com/user-attachments/assets/388f4f6c-9f3e-4582-8136-e15676dff889" /> <div style="margin-top:10px; font-size: 13px; color: #666;">答疑交流群！进群请立刻改备注</div> </td> <td width="66%" valign="top" style="border: none; line-height: 1.6;"> 还在寻找能够落地的 <strong>AI 前沿交叉赛道</strong>吗？我们课题组现向对“医学 + AI”充满热情的你发出邀请！<br><br> 这里有充足的计算资源，以及深耕医疗大模型（LLM）、视觉预训练、Prompt Engineering 及自动化医疗 AI Agent 的科研团队。我们更看重你的<strong>自驱力、学习能力与科研产出追求</strong>。<br><br> 项目信息文档链接：https://iigqjt2m4ia.feishu.cn/wiki/VIvDwHu18iTc6mk411xco8chnJb 密码：664#N926<br> 如果你有相关代码基础或项目经验，渴望在顶级交叉学科中积累成果，请将简历发送至：<br> 📧 <strong><a href="mailto:sjtu520aimedws@163.com" style="text-decoration: none; color: #0056b3;">sjtu520aimedws@163.com</a></strong><br> <small>（标题格式：姓名-专业-医学AI科研申请）</small><br><br> 期待与你在 AI 赋能医疗的征途中，做出最扎实的科研工作！ </td> </tr> </table>

---

Installation

nature-skills is a repository of reusable instruction bundles centred on SKILL.md. Each skills/nature- directory is one installable unit. Copy the whole folder, not only SKILL.md, because many skills depend on references/, static/, assets, scripts, or README context. The skills/_shared/ directory is shared support content used by several skills and should stay next to the nature- folders when you install skills manually.

1. Codex

Codex plugin marketplace installation

This repository includes Codex plugin packaging at plugins/nature-skills/, so Codex users can install the complete Nature Skills bundle from the plugin marketplace instead of copying each skill folder manually.

CLI installation:

codex plugin marketplace add https://github.com/Yuan1z0825/nature-skills --ref main
codex plugin add nature-skills@nature-skills

Codex Desktop users can add the same repository as a custom plugin marketplace:

Marketplace source: https://github.com/Yuan1z0825/nature-skills.git
Branch/ref: main
Plugin: nature-skills

After installation, all nature-* skills are available through the plugin as a complete bundle, together with the shared support directory used by the newer router-style skills. If the skills do not appear immediately, refresh the plugin page or start a new Codex session.

Manual local-skill installation

Codex can also use these folders directly as local skills.

Clone the repo

git clone https://github.com/Yuan1z0825/nature-skills.git
cd nature-skills

Install one skill

mkdir -p ~/.codex/skills
cp -R skills/_shared ~/.codex/skills/
cp -R skills/nature-reader ~/.codex/skills/

Copying _shared is harmless even for skills that do not use it, and it avoids broken relative references for skills such as nature-reader, nature-writing,

nature-polishing, and nature-paper2ppt.

Install all current skills

mkdir -p ~/.codex/skills
cp -R skills/_shared ~/.codex/skills/
for d in skills/nature-*; do
  cp -R "$d" ~/.codex/skills/
done

Update after pulling new changes

git pull
cp -R skills/_shared ~/.codex/skills/
for d in skills/nature-*; do
  cp -R "$d" ~/.codex/skills/
done

Finish

Restart Codex so newly added skills are picked up.
Then ask naturally, for example: Translate this paper into a full markdown reader. or

Make this paper into a Chinese journal-club PPT.

If you prefer not to use the terminal, copying the skills/nature-* folder(s) into

~/.codex/skills/ manually works as well; also copy skills/_shared/ once. For a longer walkthrough, see install.md.

2. Claude Code

Claude Code does not consume Codex skill folders directly. The recommended Claude Code setup is a thin subagent or slash-command wrapper that points to a stable clone of this repository, so supporting files such as references/,

static/, assets, scripts, and skills/_shared/ remain available.

mkdir -p ~/ai-skills
cd ~/ai-skills
git clone https://github.com/Yuan1z0825/nature-skills.git

Create a user-level subagent wrapper:

mkdir -p ~/.claude/agents
cat > ~/.claude/agents/nature-reader.md <<'EOF'
---
name: nature-reader
description: Full-paper bilingual, figure-aware, source-grounded Markdown reader for journal or conference papers. Use proactively when the user asks to translate an entire paper or generate a complete markdown reader.
---

When invoked, first read `~/ai-skills/nature-skills/skills/nature-reader/SKILL.md`.
Treat that file as the governing workflow.
If the skill references supporting files, read only the specific files you need from
`~/ai-skills/nature-skills/skills/nature-reader/` and
`~/ai-skills/nature-skills/skills/_shared/`.
Do not replace the skill with a generic paper-summary response.
EOF

After that, start a new Claude Code session or open /agents, and invoke it naturally or explicitly:

Use the nature-reader subagent to turn this PDF into a full markdown reader.

If you prefer commands instead of subagents, create a project or user command under

.claude/commands/ or ~/.claude/commands/ that tells Claude Code to read the real SKILL.md from the cloned repository.

Official Claude Code docs:

3. Other agents or manual use

If your agent supports reusable prompt files, system prompts, or agent profiles, the minimum portable unit is the skill directory itself:

skills/
├── _shared/              # keep this when a skill references ../_shared
└── nature-<topic>/
    ├── README.md
    ├── SKILL.md
    ├── manifest.yaml     # present for router-style skills
    ├── static/           # present for router-style skills
    └── references/...

In that case:

1. Copy the whole skill directory into your prompt library or project. 2. Preserve SKILL.md, manifest.yaml, static/, references/, scripts, assets, and any needed skills/_shared/ files together. 3. Adapt the frontmatter and body to the target agent's native format if needed.

Star History

![Star History Chart](https://star-history.com/#Yuan1z0825/nature-skills&Date)

Skill index

| Skill | Status | Purpose | Trigger keywords | |-------|--------|---------|-----------------| | nature-figure | Stable | Nature/high-impact Python or R figure workflow with bundled figures4papers demos | "Nature figure", "publication plot", "scientific figure", "figures4papers" | | nature-polishing | Stable | Academic prose polishing to Nature style | "Nature style", "polish", "academic writing" | | nature-writing | Draft | Nature-style manuscript section drafting and argument restructuring | "Nature writing", "write abstract", "write introduction", "manuscript draft" | | nature-reviewer | Draft | Nature-style reviewer assessment with 3 referee reports and a cross-review synthesis | "Nature reviewer", "pre-submission review", "reviewer report", "peer-review critique", "审稿人视角评估" | | nature-citation | Beta | Strict Nature / CNS-family citation retrieval with ENW, RIS, and Zotero RDF export | "Nature citation", "CNS citation", "text citation", "supporting references", "Zotero RDF" | | nature-data | Draft | Nature Data Availability statements, repository plans, and FAIR checks | "Data Availability", "repository", "FAIR metadata", "data availability statement" | | nature-reader | Beta | Full-paper bilingual Markdown reader with source anchors and figure grounding | "nature reader", "full markdown", "paper md", "原文对照", "图文对应", "全文翻译" | | nature-response | Beta | Point-by-point reviewer response letters with comment triage, action mapping, and risk checks | "response to reviewers", "rebuttal letter", "major revision", "审稿意见回复" | | nature-paper2ppt | Beta | Chinese PPTX decks from scientific papers | "paper PPT", "journal club", "paper to slides", "paper presentation" | | nature-academic-search | Beta | Multi-source literature search, citation verification, and reference management | "search papers", "find articles", "academic search", "literature search", "verify DOI" |

> Adding a new skill? Follow the contribution guide at the bottom of this file.

---

nature-figure

What it does — Generates multi-panel matplotlib figures that match Nature journal visual standards: correct typography, semantic colour palette, editable SVG output, and non-redundant panel information architecture.

Example output gallery — Five dense, simulated Nature-style result figures are included in the nature-figure gallery: material/mechanism, spatial imaging, in vivo efficacy, single-cell systems and perturbation validation.

Chart-type atlas — The nature-figure chart atlas classifies 10 supported chart families, including bar, line, heatmap, scatter/bubble, radar/polar, distribution, forest/interval, area/stacked, image-plate and network/matrix layouts.

| !Material design and physical validation | !Spatial imaging and uptake | !In vivo efficacy and tolerability | !Single-cell systems figure | !Perturbation validation | |---|---|---|---|---|

Built from — Production scripts from papers published in Nature Machine Intelligence and top ML/bioinformatics venues (figures4papers). The figures4papers demo scripts and preview assets are bundled inside

skills/nature-figure/assets/figures4papers/, with a routing guide at

skills/nature-figure/references/demos.md.

Key rules enforced

Three mandatory rcParams must always appear first:

  plt.rcParams['font.family'] = 'sans-serif'
  plt.rcParams['font.sans-serif'] = ['Arial', 'DejaVu Sans', 'Liberation Sans']
  plt.rcParams['svg.fonttype'] = 'none'   # text stays as <text> nodes, not paths

Primary output is always .svg; .png at 300 dpi is a secondary raster preview.
Multi-panel figures follow a three-level information hierarchy: overview → deviation → relationship. No two panels may answer the same scientific question.

Reference files

skills/nature-figure/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
└── references/
    ├── api.md            PALETTE, helper signatures, validation rules
    ├── design-theory.md  Typography, layout, export policy, anti-redundancy rules
    ├── common-patterns.md Ultra-wide panels, legend axes, print-safe bars
    ├── tutorials.md      End-to-end walkthroughs (bars, trends, heatmaps)
    ├── chart-types.md    Radar, 3D sphere, scatter, fill_between, log-scale
    └── demos.md          Bundled figures4papers scripts and preview routing

Supported chart types — Stacked bar, grouped bar, horizontal ablation bar, trend/line, sequential heatmap, diverging z-score heatmap, bubble scatter, radar/polar, 3D sphere illustration, fill-between area, log-scale bar, GridSpec multi-panel.

---

nature-polishing

What it does — Transforms academic draft text (including Chinese → English translation) into prose matching Nature journal conventions: ≤ 30-word sentences, section-aware tense and hedging, precise vocabulary, correct citation practice, and British English.

Built from — A graduate-level scientific English writing course, Academic Phrasebank, and close reading of curated Nature and Nature Communications research articles across materials, energy systems, construction decarbonization and machine learning.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Sentence length | Every sentence ≤ 30 words; count individually; last sentence most likely to fail | | Hedging calibration | Match claim strength to evidence: demonstrate → suggest → may reflect | | Section tense | Results = past tense + quantitative detail; Discussion = hedging + mechanism | | Citation integrity | Cite only sources personally read and verified; four attribution types | | Overclaim detection | Flag absolutes, unwarranted causation, scope expansion, unverified "first" claims | | British English | signalling, colour, analyse, programme, modelling, behaviour |

12-step polishing workflow

Sentence split → Section ID → Hourglass check → Tense audit → Sentence edit → Vocabulary upgrade → Template check → Citation audit → House style → Overclaim → Proofreading → Plain-text output

Reference files

skills/nature-polishing/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
└── references/
    ├── latex-layout.md
    ├── published-article-patterns.md
    ├── phrasebank-playbook.md
    ├── section-moves.md
    ├── style-guardrails.md
    └── writing-strategy.md

---

nature-writing

What it does — Drafts or rebuilds manuscript sections from author-provided claims, results, figures, notes, or Chinese drafts. It is for argument construction: abstracts, introductions, Results narratives, Discussions, Conclusions, titles and full manuscript outlines, method sections, experiment sections and reviewer-facing self-review.

Built from — Close reading of curated Nature and Nature Communications articles, especially how published papers move from field-scale stakes to a narrow gap, then to evidence, interpretation and bounded implication. It also integrates open research-writing notes for paragraph flow, section logic and adversarial paper review.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Evidence first | Do not invent data, mechanisms, references, statistics, novelty or limitations | | Abstract | Context/problem → gap → approach → key result → implication → boundary | | Introduction | Field scale → bottleneck → prior attempts → unresolved gap → present study | | Method | Module motivation → module design → forward process → technical advantage | | Results | Build an evidence ladder, not a chronological lab diary | | Experiments | Tie claims to baselines, ablations, metrics, stress tests and readable tables | | Discussion | Explain meaning, relation to prior work, constraints and future use | | Review | Run claim-evidence and rejection-risk checks before submission | | Chinese notes | Translate intent and argument, not clause order |

Reference files

skills/nature-writing/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
├── agents/
│   └── openai.yaml
└── references/
    ├── abstract.md
    ├── article-architecture.md
    ├── chinese-author-workflow.md
    ├── conclusion.md
    ├── experiments.md
    ├── introduction.md
    ├── method.md
    ├── paper-review.md
    ├── paragraph-flow.md
    ├── related-work.md
    └── examples/

---

nature-reviewer

What it does — Simulates a Nature-style pre-submission reviewer assessment from the referee perspective. It returns three reviewer reports plus a cross-review synthesis, focusing on novelty, significance, technical soundness, presentation, and likely editorial risk.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Reviewer role | Assess as external referees, not as an author rebuttal writer | | Evidence grounding | Use only the manuscript/material supplied by the user and the local reviewer source basis | | Multi-reviewer output | Produce three distinct reviewer reports plus a synthesis | | Editorial relevance | Separate novelty, significance, technical confidence, presentation, and decision risk | | Boundaries | Do not invent experiments, citations, journal policy, or manuscript content |

Reference files

skills/nature-reviewer/
├── README.md
├── SKILL.md
└── references/
    ├── source-basis.md
    ├── reviewer-workflow.md
    ├── review-axes.md
    ├── report-structure.md
    ├── role-boundaries.md
    └── qa-checklist.md

---

nature-citation

What it does — Converts manuscript text or standalone claims into strict Nature / CNS-family citation candidates, then exports one reference-manager-ready file in ENW, RIS, or Zotero

RDF. It can also generate an HTML screening page for year filtering, citation selection, and format-specific download.

Built from — Crossref metadata retrieval, DOI record export, and journal-family filtering logic for Nature Portfolio, the AAAS Science family, and Cell Press.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Scope filtering | Restrict to Nature Portfolio, Science family, Cell Press, or flagship-only journals | | Segmentation | Split long text into citable claim units with stable segment IDs | | Search discipline | Translate Chinese claims into English scientific concepts; prefer precision over volume | | Support grading | Distinguish strong, partial, background, limiting, and metadata-only support | | Export integrity | Do not fabricate DOI, pages, volume, issue, or journal metadata | | Download options | Support one-file export in ENW, RIS, or Zotero RDF |

Reference files

skills/nature-citation/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
├── references/
│   ├── journal-scope.md
│   ├── ris-endnote.md
│   ├── script-usage.md
│   └── search-strategy.md
└── scripts/
    └── nature_citation.py

Example workflow — Segment a paragraph, search in-scope citations, review candidates in the HTML browser, then download only the selected records as ENW, RIS, or Zotero RDF.

---

nature-data

What it does — Prepares and audits Data Availability statements, repository plans, dataset citations, and FAIR metadata checks for Nature-family and Springer Nature submissions. It is bilingual-aware: Chinese author notes such as "data availability statement", "request from corresponding author", "raw data", "restricted data", and "public database" are converted into precise submission-ready English with Chinese action notes.

Built from — Springer Nature research data policy, Nature Portfolio reporting standards, Scientific Data repository and citation practice, the FAIR Guiding Principles, and DataCite metadata conventions.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Data Availability | Map every result-supporting dataset to a durable access route | | Repository strategy | Prefer mandated or discipline-specific repositories with persistent identifiers | | Restricted data | State the restriction reason, controller, review route, and access conditions | | Dataset citations | Cite public datasets with DataCite-style creator, title, repository, year, and identifier metadata | | FAIR metadata | Check identifiers, licence, README/data dictionary, provenance, version, and reuse conditions | | Chinese alignment | Translate intent rather than literal wording; flag vague "reasonable request" phrasing |

Reference files

skills/nature-data/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
├── agents/
│   └── openai.yaml
└── references/
    ├── chinese-author-alignment.md
    ├── fair-metadata-checklist.md
    ├── policy-principles.md
    ├── repository-and-identifiers.md
    ├── source-basis.md
    └── statement-patterns.md

---

nature-response

What it does — Drafts, audits, and revises point-by-point reviewer response letters for Nature-family and high-impact journal manuscript revisions. It treats the response letter as an editor-facing verification document: every reviewer concern is assigned a stable ID, classified, mapped to an action, and tied to manuscript evidence, a revision location, or an unresolved author-input flag.

Built from — Nature editorial process guidance, Nature-family revision-package instructions, Springer Nature rebuttal advice, and transparent peer-review considerations.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Completeness | Every reviewer comment receives an ID and a response, cross-reference, or unresolved flag | | Action mapping | Each reply maps to a concrete manuscript action such as ACCEPT_TEXT, ACCEPT_ANALYSIS, SOFTEN_CLAIM, or AUTHOR_INPUT_NEEDED | | Traceability | Claimed changes must cite a section, page, line, figure, table, supplement, citation, or visible placeholder | | Factuality | Do not invent experiments, analyses, citations, line numbers, figure panels, editor instructions, or manuscript changes | | Tone | Use cooperative, evidence-forward language; disagree only with scientific or scope-based reasoning | | Chinese alignment | Convert Chinese author notes into English response prose plus Chinese confirmation items when needed |

Reference files

skills/nature-response/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
├── references/
│   ├── action-mapping.md
│   ├── chinese-author-alignment.md
│   ├── comment-taxonomy.md
│   ├── difficult-cases.md
│   ├── intake-and-routing.md
│   ├── qa-checklist.md
│   ├── response-structure.md
│   ├── source-basis.md
│   └── tone-and-stance.md
├── tests/
    ├── conflicting-reviewers.md
    ├── defensive-draft-audit.md
    ├── evaluation-summary.md
    ├── impossible-experiment.md
    ├── major-revision-missing-evidence.md
    ├── minor-revision.md
    └── rubric.md
└── examples/
    ├── conflicting-reviewers.md
    ├── major-revision-with-missing-evidence.md
    └── minor-revision.md

---

nature-paper2ppt

What it does — Turns a scientific paper, preprint, PDF, article text, abstract, figure legends, or reading notes into a concise Chinese .pptx presentation for journal club, group meeting, lab meeting, paper sharing, or thesis seminar.

The skill identifies the paper type and central argument, selects only figures and tables that support the evidence chain, writes Chinese slide titles, bullets, captions, takeaways and speaker notes, creates the actual PPTX deck, and runs lightweight package QA.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Narrative | Use the paper's scientific argument as the slide spine, not the manuscript section order | | Paper type | Classify the paper before choosing claim-first, problem-to-solution, workflow-to-validation, or evidence-map logic | | Figures | Use figures as evidence; crop or split dense panels rather than shrinking them into unreadable slots | | Output | Build a real .pptx as the primary deliverable, with Chinese text and speaker notes | | QA | Reopen or inspect the PPTX package, record slide count, embedded media, notes, and any rendering limits | | Integrity | Do not fabricate results, methods, numbers, datasets, mechanisms, or figure details |

Reference files

skills/nature-paper2ppt/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
└── references/
    ├── design-and-layout.md
    ├── figure-assets.md
    └── self-review.md

---

nature-academic-search

What it does — Provides a multi-source academic search and reference-management workflow backed by a local MCP server. It searches PubMed, CrossRef and arXiv in parallel, fetches records by DOI, PMID or arXiv ID, formats citations, looks up MeSH terms, verifies bibliographic identifiers, and supports .nbib, .ris, .bib and

.enw reference-file workflows.

Built from — A unified MCP server with source adapters for PubMed E-utilities, CrossRef REST metadata and arXiv Atom metadata, plus reusable workflow notes for source-tier routing, search strategy, citation parsing, deduplication, RIS/BibTeX field mapping and reference-file conversion.

Setup note — For Claude Code MCP use, run

bash skills/nature-academic-search/install.sh your-email@example.com, restart Claude Code, and optionally set NCBI_API_KEY for higher PubMed rate limits. For plain prompt use, copy the whole skills/nature-academic-search/ directory like the other skills.

Key rules enforced

| Domain | Core rule | |--------|-----------| | Source routing | Start with structured API-backed sources: PubMed for biomedical searches, CrossRef for DOI and cross-disciplinary metadata, and arXiv for preprints | | Fallback discipline | Escalate from T1 sources to limited APIs or scraped/manual sources only when needed, and warn when results may be incomplete | | Deduplication | Merge multi-source hits by DOI, PMID, arXiv ID and normalized title rather than counting duplicate records as separate evidence | | Citation verification | Resolve DOI, PMID and arXiv IDs before citation formatting; expose missing or failed metadata instead of filling fields by guesswork | | MeSH strategy | Use MeSH lookup for biomedical PubMed queries when the task needs recall, controlled vocabulary or systematic search structure | | File integrity | Preserve bibliographic fields when converting .nbib, .ris, .bib and .enw; do not fabricate volume, issue, pages, DOI or PMID values |

MCP tools

| Tool | Purpose | |------|---------| | search_papers | Search CrossRef, PubMed and arXiv with optional source selection and per-source result limits | | get_paper_by_id | Fetch paper metadata by DOI, PMID or arXiv ID with automatic ID-type detection | | get_citation | Generate formatted citations in styles such as APA, Nature, IEEE, Vancouver, Chicago and MLA | | lookup_mesh | Query PubMed MeSH descriptors for biomedical search-term expansion |

Reference files

skills/nature-academic-search/
├── README.md
├── SKILL.md
├── manifest.yaml
├── static/
├── install.sh
├── config/
│   ├── mcp-snippet.json
│   ├── settings-snippet.json
│   └── triggers-academic-search.toml
├── mcp-server/
│   ├── academic_search_server.py
│   ├── sources/
│   ├── tests/
│   └── utils/
├── references/
│   ├── citation-parser.md
│   ├── dedup-engine.md
│   ├── ris-bibtex-format.md
│   ├── search-strategy.md
│   ├── source-tiers.md
│   └── workflows/
└── scripts/
    ├── converters.py
    ├── format-converter.py
    └── preflight.py

Example workflow — Search the same topic across PubMed, CrossRef and arXiv, merge and deduplicate candidate papers, verify key identifiers, look up MeSH terms for the biomedical subset, then export or convert the selected references for Zotero, EndNote or BibTeX.

---

Shared design principles

All skills in this collection adhere to the following:

1. Primary sources only — rules are grounded in published Nature content or official journal guidelines, not general style preference. 2. Explicit over implicit — every rule is stated with a rationale, not just asserted. 3. Section-aware — academic writing and figures both require context-sensitivity; each skill applies different logic depending on which part of a paper is being handled. 4. Output-first — every skill returns something immediately usable: copy-paste prose, a .svg file, a .pptx deck, or a concrete recommendation. No intermediate planning documents. 5. Extensible by design — each skill is self-contained in its own directory; adding a new skill requires no changes to existing ones.

---

Adding a new skill

To add a skill to this collection:

1. Create a directory

skills/nature-<topic>/

2. Minimum required files

| File | Required | Purpose | |------|----------|---------| | SKILL.md | Yes | Frontmatter (name, description) + rules + workflow; loaded by the agent after triggering | | README.md | Yes | Human-readable reference in full English | | references/*.md | Recommended for complex skills | Modular rule files (api, design theory, tutorials, chart types, …) |

3. SKILL.md frontmatter template

---
name: nature-<topic>
description: >-
  One-sentence description of what the skill does and when to trigger it.
  Include the output format and the primary use case.
---

4. Update this index

Add a row to the Skill index table above:

| [`nature-<topic>`](skills/nature-<topic>/README.md) | Draft / Stable | One-line purpose | trigger keywords |

5. Status labels

| Label | Meaning | |-------|---------| | Draft | Rules defined; not yet tested on real examples | | Beta | Tested on examples; edge cases may remain | | Stable | Validated on real academic content; rules are settled |

---

Candidate skills (not yet built)

The following are documented gaps. Contributions welcome.

| Candidate | Scope | Priority | |-----------|-------|----------| | nature-stats | Statistical reporting conventions for Nature (effect sizes, confidence intervals, p-value formatting, sample size statements) | High | | nature-methods | Deep-dive Methods writing assistant — reproducibility checklist, forbidden phrases, ethical approval templates, supplementary organisation | Medium | | nature-cover | Cover letter drafting — hook paragraph, significance framing, fit-to-journal argument, ≤ 500-word limit | Medium |

☕ 如果内容对你有帮助，欢迎随缘支持一下

---

| 微信赞赏 | 来自粉丝的小感动 | | --- | --- | | <img width="320" alt="微信赞赏" src="https://github.com/user-attachments/assets/83c101e7-2370-46e9-a840-cb506df98cf4" /> | <img width="320" alt="粉丝的鼓励" src="https://github.com/user-attachments/assets/0484300a-95e8-4cb3-ad73-478ba9bd19d6" /> |

</div>

💬 想说的话

项目会长期免费维护，大家正常使用就好。很多朋友还是学生党，所以完全不需要有任何“必须打赏”的压力。

如果这些内容刚好帮你节省了一些时间、解决了一点问题，又恰好想请作者喝杯咖啡，那我会非常开心 ☕

你的支持会用于：

持续更新内容
服务器与工具费用
熬夜写文档时的续命奶茶（认真）

无论是否赞赏，都非常感谢你的关注与支持 ❤️

nature-skills

Summary

Install to Claude Code

nature-skills

📢 课题组诚招“医学 + AI”实习生

Installation

1. Codex

2. Claude Code

3. Other agents or manual use

Star History

Skill index

nature-figure

nature-polishing

nature-writing

nature-reviewer

nature-citation

nature-data

nature-response

nature-paper2ppt

nature-academic-search

Shared design principles

Adding a new skill

Candidate skills (not yet built)

☕ 如果内容对你有帮助，欢迎随缘支持一下

💬 想说的话

Related plugins

Plugins by category