[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-679":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},679,"nature-skills","Yuan1z0825\u002Fnature-skills","Yuan1z0825","符合nature论文学术表达和科研绘图的Skill","",null,"Python",19096,1129,18,1,0,459,4332,14971,2113,119.13,"MIT License",false,"main",true,[],"2026-06-11 04:00:33","# nature-skills \n| Overview | Community |\n| :--- | :---: |\n| **Welcome! Let's co-create nature-skills.**\u003Cbr>\u003Cbr>A growing collection of Claude skills for producing academic work at *Nature*-journal standard.\u003Cbr>\u003Cbr>Currently covering scientific figures, manuscript prose, data availability, and paper-to-presentation workflows; future releases may add related tasks such as statistical reporting, peer‑review responses, and methods writing.\u003Cbr>\u003Cbr>**Our philosophy** — Every skill in this collection shares a common philosophy: rules are derived from **primary sources** (published *Nature* papers, journal author guidelines, and structured writing curricula), not from general style intuition. | \u003Cimg width=\"200\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fc7e93192-5a45-49dd-82b9-8a5fe90b8025\" \u002F>\u003Cbr>\u003Cbr>*The group is currently full. Please contact the administrator if you’d like to join.* |\n\n---\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=Yuan1z0825\u002Fnature-skills&type=Date&cache_bust=2026-05-07T00)](https:\u002F\u002Fstar-history.com\u002F#Yuan1z0825\u002Fnature-skills&Date)\n\n---\n\n## Skill index\n\n| Skill | Status | Purpose | Trigger keywords |\n|-------|--------|---------|-----------------|\n| [`nature-figure`](nature-figure\u002FREADME.md) | Stable | Publication-ready matplotlib figures | \"Nature figure\", \"publication plot\", \"scientific figure\" |\n| [`nature-polishing`](nature-polishing\u002FREADME.md) | Stable | Academic prose polishing to *Nature* style | \"Nature style\", \"polish\", \"academic writing\" |\n| [`nature-citation`](nature-citation\u002FREADME.md) | Beta | Strict Nature \u002F CNS-family citation retrieval with ENW, RIS, and Zotero RDF export | \"Nature citation\", \"CNS citation\", \"分段引用\", \"支撑文献\", \"Zotero RDF\" |\n| [`nature-data`](nature-data\u002FREADME.md) | Draft | Nature Data Availability statements, repository plans, and FAIR checks | \"Data Availability\", \"repository\", \"FAIR metadata\", \"数据可用性声明\" |\n| [`nature-paper2ppt`](nature-paper2ppt\u002FREADME.md) | Beta | Chinese PPTX decks from scientific papers | \"paper PPT\", \"journal club\", \"文献汇报\", \"论文做成PPT\" |\n\n> **Adding a new skill?** Follow the [contribution guide](#adding-a-new-skill) at the bottom of this file.\n\n---\n\n## nature-figure\n\n**What it does** — Generates multi-panel matplotlib figures that match *Nature* journal\nvisual standards: correct typography, semantic colour palette, editable SVG output,\nand non-redundant panel information architecture.\n\n**Example output gallery** — Five dense, simulated *Nature*-style result figures are\nincluded in the [`nature-figure` gallery](nature-figure\u002FREADME.md#example-output-gallery):\nmaterial\u002Fmechanism, spatial imaging, in vivo efficacy, single-cell systems and\nperturbation validation.\n\n**Chart-type atlas** — The [`nature-figure` chart atlas](nature-figure\u002FREADME.md#chart-type-atlas)\nclassifies 10 supported chart families, including bar, line, heatmap, scatter\u002Fbubble,\nradar\u002Fpolar, distribution, forest\u002Finterval, area\u002Fstacked, image-plate and network\u002Fmatrix\nlayouts.\n\n\u003Cp>\n  \u003Ca href=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig1-material-mechanism-rich.png\">\n    \u003Cimg src=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig1-material-mechanism-rich.png\" width=\"19%\" alt=\"Material design and physical validation example\">\n  \u003C\u002Fa>\n  \u003Ca href=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig2-spatial-imaging-rich.png\">\n    \u003Cimg src=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig2-spatial-imaging-rich.png\" width=\"19%\" alt=\"Spatial imaging and uptake example\">\n  \u003C\u002Fa>\n  \u003Ca href=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig3-in-vivo-efficacy-rich.png\">\n    \u003Cimg src=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig3-in-vivo-efficacy-rich.png\" width=\"19%\" alt=\"In vivo efficacy and tolerability example\">\n  \u003C\u002Fa>\n  \u003Ca href=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig4-single-cell-systems-rich.png\">\n    \u003Cimg src=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig4-single-cell-systems-rich.png\" width=\"19%\" alt=\"Single-cell systems figure example\">\n  \u003C\u002Fa>\n  \u003Ca href=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig5-validation-perturbation-rich.png\">\n    \u003Cimg src=\"nature-figure\u002Fassets\u002Fgallery\u002Ffig5-validation-perturbation-rich.png\" width=\"19%\" alt=\"Perturbation validation example\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n**Built from** — Production scripts from papers published in *Nature Machine Intelligence*\nand top ML\u002Fbioinformatics venues ([figures4papers](https:\u002F\u002Fgithub.com\u002FChenLiu-1996\u002Ffigures4papers)).\n\n**Key rules enforced**\n\n- Three mandatory rcParams must always appear first:\n  ```python\n  plt.rcParams['font.family'] = 'sans-serif'\n  plt.rcParams['font.sans-serif'] = ['Arial', 'DejaVu Sans', 'Liberation Sans']\n  plt.rcParams['svg.fonttype'] = 'none'   # text stays as \u003Ctext> nodes, not paths\n  ```\n- Primary output is always `.svg`; `.png` at 300 dpi is a secondary raster preview.\n- Multi-panel figures follow a three-level information hierarchy: **overview → deviation → relationship**. No two panels may answer the same scientific question.\n\n**Reference files**\n\n```\nnature-figure\u002F\n├── README.md\n├── SKILL.md\n└── references\u002F\n    ├── api.md            PALETTE, helper signatures, validation rules\n    ├── design-theory.md  Typography, layout, export policy, anti-redundancy rules\n    ├── common-patterns.md Ultra-wide panels, legend axes, print-safe bars\n    ├── tutorials.md      End-to-end walkthroughs (bars, trends, heatmaps)\n    └── chart-types.md    Radar, 3D sphere, scatter, fill_between, log-scale\n```\n\n**Supported chart types** — Stacked bar, grouped bar, horizontal ablation bar, trend\u002Fline,\nsequential heatmap, diverging z-score heatmap, bubble scatter, radar\u002Fpolar, 3D sphere\nillustration, fill-between area, log-scale bar, GridSpec multi-panel.\n\n---\n\n## nature-polishing\n\n**What it does** — Transforms academic draft text (including Chinese → English translation)\ninto prose matching *Nature* journal conventions: ≤ 30-word sentences, section-aware\ntense and hedging, precise vocabulary, correct citation practice, and British English.\n\n**Built from** — Close reading of five *Nature* s41586 papers (2026) and a graduate-level\nscientific English writing course; 25 rules extracted across sentence architecture,\npaper structure, vocabulary, citation integrity, house style, and AI ethics.\n\n**Key rules enforced**\n\n| Domain | Core rule |\n|--------|-----------|\n| Sentence length | Every sentence ≤ 30 words; count individually; last sentence most likely to fail |\n| Hedging calibration | Match claim strength to evidence: *demonstrate* → *suggest* → *may reflect* |\n| Section tense | Results = past tense + quantitative detail; Discussion = hedging + mechanism |\n| Citation integrity | Cite only sources personally read and verified; four attribution types |\n| Overclaim detection | Flag absolutes, unwarranted causation, scope expansion, unverified \"first\" claims |\n| British English | signalling, colour, analyse, programme, modelling, behaviour |\n\n**12-step polishing workflow**\n\nSentence split → Section ID → Hourglass check → Tense audit → Sentence edit →\nVocabulary upgrade → Template check → Citation audit → House style → Overclaim →\nProofreading → Plain-text output\n\n**Reference files**\n\n```\nnature-polishing\u002F\n├── README.md\n└── SKILL.md    25 rules + 12-step workflow (loaded by Claude automatically)\n```\n\n---\n\n## nature-citation\n\n**What it does** — Converts manuscript text or standalone claims into strict Nature \u002F CNS-family\ncitation candidates, then exports one reference-manager-ready file in `ENW`, `RIS`, or Zotero\n`RDF`. It can also generate an HTML screening page for year filtering, citation selection, and\nformat-specific download.\n\n**Built from** — Crossref metadata retrieval, DOI record export, and journal-family filtering logic\nfor Nature Portfolio, the AAAS Science family, and Cell Press.\n\n**Key rules enforced**\n\n| Domain | Core rule |\n|--------|-----------|\n| Scope filtering | Restrict to Nature Portfolio, Science family, Cell Press, or flagship-only journals |\n| Segmentation | Split long text into citable claim units with stable segment IDs |\n| Search discipline | Translate Chinese claims into English scientific concepts; prefer precision over volume |\n| Support grading | Distinguish strong, partial, background, limiting, and metadata-only support |\n| Export integrity | Do not fabricate DOI, pages, volume, issue, or journal metadata |\n| Download options | Support one-file export in `ENW`, `RIS`, or Zotero `RDF` |\n\n**Reference files**\n\n```text\nnature-citation\u002F\n├── README.md\n├── SKILL.md\n├── references\u002F\n│   ├── journal-scope.md\n│   ├── ris-endnote.md\n│   └── search-strategy.md\n└── scripts\u002F\n    └── nature_citation.py\n```\n\n**Example workflow** — Segment a paragraph, search in-scope citations, review candidates in the\nHTML browser, then download only the selected records as `ENW`, `RIS`, or Zotero `RDF`.\n\n---\n\n## nature-data\n\n**What it does** — Prepares and audits Data Availability statements, repository plans,\ndataset citations, and FAIR metadata checks for Nature-family and Springer Nature\nsubmissions. It is bilingual-aware: Chinese author notes such as \"数据可用性声明\",\n\"可向通讯作者索取\", \"原始数据\", \"受限数据\", and \"公开数据库\" are converted into precise\nsubmission-ready English with Chinese action notes.\n\n**Built from** — Springer Nature research data policy, Nature Portfolio reporting standards,\nScientific Data repository and citation practice, the FAIR Guiding Principles, and DataCite\nmetadata conventions.\n\n**Key rules enforced**\n\n| Domain | Core rule |\n|--------|-----------|\n| Data Availability | Map every result-supporting dataset to a durable access route |\n| Repository strategy | Prefer mandated or discipline-specific repositories with persistent identifiers |\n| Restricted data | State the restriction reason, controller, review route, and access conditions |\n| Dataset citations | Cite public datasets with DataCite-style creator, title, repository, year, and identifier metadata |\n| FAIR metadata | Check identifiers, licence, README\u002Fdata dictionary, provenance, version, and reuse conditions |\n| Chinese alignment | Translate intent rather than literal wording; flag vague \"reasonable request\" phrasing |\n\n**Reference files**\n\n```\nnature-data\u002F\n├── README.md\n├── SKILL.md\n├── agents\u002F\n│   └── openai.yaml\n└── references\u002F\n    ├── chinese-author-alignment.md\n    ├── fair-metadata-checklist.md\n    ├── policy-principles.md\n    ├── repository-and-identifiers.md\n    ├── source-basis.md\n    └── statement-patterns.md\n```\n\n---\n\n## nature-paper2ppt\n\n**What it does** — Turns a scientific paper, preprint, PDF, article text, abstract,\nfigure legends, or reading notes into a concise Chinese `.pptx` presentation for journal\nclub, group meeting, lab meeting, paper sharing, or thesis seminar.\n\nThe skill identifies the paper type and central argument, selects only figures and tables\nthat support the evidence chain, writes Chinese slide titles, bullets, captions, takeaways\nand speaker notes, creates the actual PPTX deck, and runs lightweight package QA.\n\n**Key rules enforced**\n\n| Domain | Core rule |\n|--------|-----------|\n| Narrative | Use the paper's scientific argument as the slide spine, not the manuscript section order |\n| Paper type | Classify the paper before choosing claim-first, problem-to-solution, workflow-to-validation, or evidence-map logic |\n| Figures | Use figures as evidence; crop or split dense panels rather than shrinking them into unreadable slots |\n| Output | Build a real `.pptx` as the primary deliverable, with Chinese text and speaker notes |\n| QA | Reopen or inspect the PPTX package, record slide count, embedded media, notes, and any rendering limits |\n| Integrity | Do not fabricate results, methods, numbers, datasets, mechanisms, or figure details |\n\n**Reference files**\n\n```\nnature-paper2ppt\u002F\n├── README.md\n└── SKILL.md\n```\n\n---\n\n## Shared design principles\n\nAll skills in this collection adhere to the following:\n\n1. **Primary sources only** — rules are grounded in published *Nature* content or official\n   journal guidelines, not general style preference.\n2. **Explicit over implicit** — every rule is stated with a rationale, not just asserted.\n3. **Section-aware** — academic writing and figures both require context-sensitivity;\n   each skill applies different logic depending on which part of a paper is being handled.\n4. **Output-first** — every skill returns something immediately usable: copy-paste prose,\n   a `.svg` file, a `.pptx` deck, or a concrete recommendation. No intermediate planning documents.\n5. **Extensible by design** — each skill is self-contained in its own directory; adding a\n   new skill requires no changes to existing ones.\n\n---\n\n## Adding a new skill\n\nTo add a skill to this collection:\n\n**1. Create a directory**\n```\nnature-\u003Ctopic>\u002F\n```\n\n**2. Minimum required files**\n\n| File | Required | Purpose |\n|------|----------|---------|\n| `SKILL.md` | Yes | Frontmatter (`name`, `description`) + rules + workflow; loaded by the agent after triggering |\n| `README.md` | Yes | Human-readable reference in full English |\n| `references\u002F*.md` | Recommended for complex skills | Modular rule files (api, design theory, tutorials, chart types, …) |\n\n**3. SKILL.md frontmatter template**\n```yaml\n---\nname: nature-\u003Ctopic>\ndescription: >-\n  One-sentence description of what the skill does and when to trigger it.\n  Include the output format and the primary use case.\n---\n```\n\n**4. Update this index**\n\nAdd a row to the [Skill index](#skill-index) table above:\n```markdown\n| [`nature-\u003Ctopic>`](nature-\u003Ctopic>\u002FREADME.md) | Draft \u002F Stable | One-line purpose | trigger keywords |\n```\n\n**5. Status labels**\n\n| Label | Meaning |\n|-------|---------|\n| `Draft` | Rules defined; not yet tested on real examples |\n| `Beta` | Tested on examples; edge cases may remain |\n| `Stable` | Validated on real academic content; rules are settled |\n\n---\n\n## Candidate skills (not yet built)\n\nThe following are documented gaps. Contributions welcome.\n\n| Candidate | Scope | Priority |\n|-----------|-------|----------|\n| `nature-stats` | Statistical reporting conventions for *Nature* (effect sizes, confidence intervals, p-value formatting, sample size statements) | High |\n| `nature-response` | Peer-review response letters — point-by-point reply structure, tone calibration, handling major vs. minor revisions | High |\n| `nature-methods` | Deep-dive Methods writing assistant — reproducibility checklist, forbidden phrases, ethical approval templates, supplementary organisation | Medium |\n| `nature-cover` | Cover letter drafting — hook paragraph, significance framing, fit-to-journal argument, ≤ 500-word limit | Medium |\n| `nature-review` | Writing a literature review or review article in *Nature Reviews* style — synthesis vs. summary, argument-led structure | Low |\n","nature-skills 是一个旨在帮助科研人员按照Nature期刊标准生成学术内容和绘图的技能集合。该项目主要功能包括创建符合Nature风格的科学图表、优化学术写作语言、提供严格格式的引用检索以及从论文到PPT的转换等，所有技能均基于Nature期刊文章、作者指南等权威来源设计，确保遵循最高级别的学术规范。适用于需要在高水平国际期刊上发表研究成果的研究者们，无论是准备投稿材料还是进行学术交流都能从中受益。",2,"2026-06-11 02:38:34","CREATED_QUERY"]