nature-citation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Nature Citation

Nature引用

Use this skill to turn manuscript text into a defensible citation export:

segmented text with citation candidates for each segment
a reference-manager import file in
```
.enw
```
,
```
.ris
```
, or Zotero
```
.rdf
```
conservative evidence notes explaining whether each candidate truly supports the segment

使用本技能可将手稿文本转换为合规的引用导出文件：

拆分后的文本，每个片段对应候选引用
可导入参考文献管理工具的
```
.enw
```
、
```
.ris
```
或Zotero
```
.rdf
```
格式文件
严谨的支撑说明，解释每个候选文献是否真正支撑对应片段

Chinese-user operating mode

中文用户操作模式

When the user writes in Chinese, asks for "Nature系列", "CNS及其子刊", "支撑文献", "补引用", "自动给出引用", "分段引用", "导出EndNote", "RIS", "Zotero", "RDF", or provides Chinese manuscript text:

Accept the text in Chinese, but search using English concept queries unless the topic is explicitly China-specific or Chinese-language scholarship.
Return segment notes and evidence notes in Chinese by default.
Preserve the exact source segment and translate it into one or more English search claims.

Flag overclaiming clearly in Chinese:

强支撑

部分支撑

背景支撑

不建议引用为该句支撑

Do not present a paper as supporting the claim merely because its title is related.

当用户使用中文提问，提及“Nature系列”“CNS及其子刊”“支撑文献”“补引用”“自动给出引用”“分段引用”“导出EndNote”“RIS”“Zotero”“RDF”，或提供中文手稿文本时：

接受中文文本，但默认使用英文概念检索，除非主题明确为中国特定内容或中文学术成果
默认返回中文的片段说明和支撑说明
保留原始片段内容，并将其转换为一个或多个英文检索语句

用中文明确标注支撑等级：

强支撑

、

部分支撑

、

背景支撑

、

不建议引用为该句支撑

不得仅因标题相关就将某篇文献列为论点支撑

Default scope

默认检索范围

Interpret journal scope from the user's wording, but keep the filter strict:

Nature系列

: search Nature Portfolio first. Include

Nature

Nature [field]

Nature Communications

Communications [field]

Scientific Reports

, and

npj

journals.

```
CNS
```
: search
```
Cell
```
,
```
Nature
```
, and
```
Science
```
plus their major sister journals.
```
CNS及其子刊
```
or
```
CNS/sister journals
```
: search only accepted flagship and subjournal titles in Nature Portfolio, the AAAS Science family, and Cell Press.

只要Nature/Science/Cell正刊

: restrict to the flagship journals

Nature

Science

, and

Cell

Do not treat merely related journals as in-scope. A title is valid only if it is in the accepted publisher-family whitelist or clearly matches the official naming pattern for that family. If the user needs an exhaustive or submission-critical boundary, verify current official journal pages before finalizing because journal portfolios change.

根据用户表述确定期刊范围，但需严格筛选：

Nature系列

：优先检索Nature Portfolio期刊，包括

Nature

、

Nature [领域]

、

Nature Communications

、

Communications [领域]

、

Scientific Reports

及

npj

系列期刊

```
CNS
```
：检索
```
Cell
```
、
```
Nature
```
、
```
Science
```
及其主要子刊
```
CNS及其子刊
```
或
```
CNS/sister journals
```
：仅检索Nature Portfolio、AAAS Science系列及Cell Press旗下认可的旗舰刊和子刊

只要Nature/Science/Cell正刊

：仅限定为

Nature

、

Science

、

Cell

这三本旗舰期刊

不得将仅相关的期刊纳入检索范围。只有属于认可出版商标白名单或符合该品牌官方命名规则的期刊才有效。若用户需要全面的或投稿关键的期刊范围界定，需在最终确认前查阅官方期刊页面，因为期刊阵容会有所变动。

Source hierarchy

数据源优先级

Use sources in this order:

Structured bibliographic metadata: Crossref, PubMed/NCBI E-utilities, DOI metadata.
Publisher pages:
```
nature.com
```
,
```
science.org
```
,
```
cell.com
```
, and official journal pages.
Full text or abstract pages, if accessible.
Secondary databases such as Google Scholar, Semantic Scholar, Web of Science, or Scopus only as discovery aids, not as the sole support basis.

Prefer structured APIs for metadata and publisher pages for claim verification. If metadata and publisher page disagree, preserve the DOI and journal-page facts and flag the discrepancy.

按以下顺序使用数据源：

结构化文献元数据：Crossref、PubMed/NCBI E-utilities、DOI元数据
出版商页面：
```
nature.com
```
、
```
science.org
```
、
```
cell.com
```
及官方期刊页面
全文或摘要页面（若可访问）
二级数据库（如Google Scholar、Semantic Scholar、Web of Science或Scopus）仅作为检索辅助工具，不得作为唯一支撑依据

优先使用结构化API获取元数据，使用出版商页面验证论点。若元数据与出版商页面内容不一致，保留DOI和期刊页面的事实，并标注差异。

Workflow

工作流程

1. Segment the text

1. 文本分段

For each input text:

Split long text into citable segments. Prefer paragraph boundaries first, then sentence boundaries.
Keep each segment focused on one citable idea when possible.
Preserve original order and stable segment IDs such as
```
S001
```
,
```
S002
```
,
```
S003
```
.
Skip obvious non-citable connective sentences unless the user asks to cite every sentence.
For very long text, process in batches but keep a single final mapping table.

Default segmentation rules:

Use blank lines as paragraph boundaries.
If a paragraph is longer than about 700 characters or contains multiple claims, split into sentences.
Merge very short fragments into neighboring text unless they contain a distinct claim.
Keep section headings as labels, not as citable segments.

针对每段输入文本：

将长文本拆分为可引用片段。优先按段落拆分，其次按句子拆分
尽可能使每个片段聚焦于一个可引用的论点
保留原始顺序及稳定的片段ID（如
```
S001
```
、
```
S002
```
、
```
S003
```
）
跳过明显无引用必要的连接句，除非用户要求为每句添加引用
针对超长文本，可分批处理，但需保留统一的最终映射表

默认分段规则：

以空白行作为段落边界
若段落长度超过约700字符或包含多个论点，拆分为句子
将极短的片段合并至相邻文本，除非其包含独立论点
保留章节标题作为标签，不作为可引用片段

2. Parse each segment

2. 片段解析

For each citable segment:

Extract the core claim in one sentence.

Identify claim type:

mechanism

association

method

clinical

epidemiology

background

definition

, or

review-context

Identify entities, intervention/exposure, outcome, population/model, directionality, and boundary.
Convert the claim into 2-4 English search queries:
- one precise query with all key terms
- one synonym query
- one broader background query
- one methods or model query if relevant

If the claim is too broad, split it into citable subclaims rather than searching the whole sentence.

针对每个可引用片段：

用一句话提取核心论点
识别论点类型：
```
mechanism
```
（机制）、
```
association
```
（关联）、
```
method
```
（方法）、
```
clinical
```
（临床）、
```
epidemiology
```
（流行病学）、
```
background
```
（背景）、
```
definition
```
（定义）或
```
review-context
```
（综述背景）
识别实体、干预/暴露因素、结果、人群/模型、方向性及边界
将论点转换为2-4个英文检索语句：
- 包含所有关键词的精准检索语句
- 同义词检索语句
- 更宽泛的背景检索语句
- 相关的方法或模型检索语句（若适用）

若论点过于宽泛，将其拆分为可引用的子论点，而非检索整句。

3. Search candidate papers

3. 检索候选文献

Start with

scripts/nature_citation.py

when internet access is available:

bash

python scripts/nature_citation.py \
  --text "PASTE MANUSCRIPT TEXT HERE" \
  --scope cns \
  --outdir /tmp/nature-citation \
  --format enw \
  --with-artifacts

Useful options:

```
--text-file manuscript.txt
```
: read long text from a file.

--claim "CLAIM TEXT"

--claim-file claims.txt

: treat each claim as a segment.

```
--doi 10.xxxx/xxxxx
```
or
```
--doi-file dois.txt
```
: export known DOI records after screening.
```
--scope nature
```
: Nature Portfolio-style journals only.
```
--scope flagship
```
: Nature, Science, and Cell only.
```
--from-year 2018 --to-year 2026
```
: constrain publication dates.
```
--rows 40
```
: raise for broad searches; keep top candidates manageable.
```
--per-segment 3
```
: number of citation candidates to keep per segment.
```
--format enw|ris|zotero-rdf
```
: export format. If omitted and
```
--output-file
```
is set, infer from suffix.
```
--mailto you@example.com
```
: use Crossref's polite pool.

When the topic is biomedical or PubMed-indexed, also search PubMed with journal filters and compare results against Crossref. Use NCBI E-utilities rate limits and include

tool

email

parameters if running repeated searches.

若可访问互联网，使用

scripts/nature_citation.py

启动检索：

bash

python scripts/nature_citation.py \
  --text "PASTE MANUSCRIPT TEXT HERE" \
  --scope cns \
  --outdir /tmp/nature-citation \
  --format enw \
  --with-artifacts

实用参数：

```
--text-file manuscript.txt
```
：从文件读取长文本

--claim "CLAIM TEXT"

或

--claim-file claims.txt

：将每个论点视为一个片段

```
--doi 10.xxxx/xxxxx
```
或
```
--doi-file dois.txt
```
：筛选后导出已知DOI记录
```
--scope nature
```
：仅检索Nature Portfolio系列期刊
```
--scope flagship
```
：仅检索Nature、Science、Cell三本旗舰期刊
```
--from-year 2018 --to-year 2026
```
：限定发表日期范围
```
--rows 40
```
：针对宽泛检索增加候选数量；保持候选文献数量可控
```
--per-segment 3
```
：每个片段保留的候选引用数量
```
--format enw|ris|zotero-rdf
```
：导出格式。若未设置且指定了
```
--output-file
```
，则从文件后缀推断格式
```
--mailto you@example.com
```
：使用Crossref的礼貌访问池

若主题为生物医学或被PubMed收录，需同时使用期刊筛选条件检索PubMed，并与Crossref结果对比。使用NCBI E-utilities时需遵守速率限制，若进行重复检索需添加

tool

email

参数。

4. Evaluate whether each paper supports the segment

4. 评估文献对片段的支撑程度

Use a conservative support scale:

```
strong support
```
: the paper directly tests the same relationship/mechanism/method and the result supports the segment.
```
partial support
```
: the paper supports part of the segment, a related model, or a narrower condition.
```
background support
```
: the paper supports field context, not the specific claim.
```
contradictory/limiting
```
: the paper conflicts with or narrows the claim.
```
metadata-only candidate
```
: title/metadata suggest relevance, but abstract/full text has not been checked.

Never cite a

metadata-only candidate

as support without checking the abstract or publisher page. If a paper is a review, label it as review/context and avoid using it as primary evidence for an experimental claim when primary articles are available.

采用严谨的支撑等级划分：

```
strong support
```
（强支撑）：文献直接验证了相同的关系/机制/方法，且结果支撑该片段
```
partial support
```
（部分支撑）：文献支撑片段的部分内容、相关模型或更窄的条件
```
background support
```
（背景支撑）：文献支撑领域背景，而非特定论点
```
contradictory/limiting
```
（矛盾/限制）：文献与论点冲突或缩小了论点范围
```
metadata-only candidate
```
（仅元数据候选）：标题/元数据显示相关，但未查阅摘要/全文

未查阅摘要或出版商页面时，不得将

metadata-only candidate

列为支撑文献。若文献为综述，需标注为综述/背景类，且当有原始研究文献时，避免将其作为实验论点的主要证据。

5. Export reference-manager file

5. 导出参考文献管理工具文件

Default behavior:

write one reference-manager file
ALWAYS also generate review artifacts (HTML/TSV/JSON/report) — use
```
--with-artifacts
```
support publication time filters with
```
--from-year
```
and
```
--to-year
```

Default file:

```
references.enw
```
: EndNote tagged export

Optional:

```
references.ris
```
: if the user requests RIS instead of ENW
```
references.rdf
```
: if the user requests Zotero RDF
review artifacts only when explicitly requested

If the user asks to choose the download format, treat

ENW

RIS

, and

Zotero RDF

as the supported options and return only one export file unless they explicitly ask for multiple formats.

Do not invent missing fields. If DOI, pages, volume, or issue are missing, leave them absent rather than fabricating them.

默认行为：

生成一个参考文献管理工具文件
始终同时生成评审文件（HTML/TSV/JSON/报告）——需使用
```
--with-artifacts
```
参数
支持通过
```
--from-year
```
和
```
--to-year
```
参数筛选发表时间

默认文件：

```
references.enw
```
：EndNote标记格式导出文件

可选文件：

```
references.ris
```
：若用户要求RIS格式而非ENW格式
```
references.rdf
```
：若用户要求Zotero RDF格式
仅在明确要求时生成评审文件

若用户要求选择下载格式，仅支持

ENW

、

RIS

和

Zotero RDF

选项，且除非用户明确要求多种格式，否则仅返回一个导出文件。

不得编造缺失的字段。若DOI、页码、卷号或期号缺失，需留空而非伪造。

6. Optional review artifacts

6. 可选评审文件

Generate review artifacts (HTML/TSV/JSON/report) for every run — they are the primary way the user browses, filters, and selects candidates:

ALWAYS use
--with-artifacts
when running the script. The HTML browser is the most useful output for the user to inspect and curate citations.
Always report the HTML visualization path prominently in your final answer (section 7).
Generate TSV/JSON/report alongside the HTML so the user has multiple views.

每次运行均需生成评审文件（HTML/TSV/JSON/报告）——这是用户浏览、筛选和选择候选文献的主要方式：

运行脚本时务必使用
--with-artifacts
参数。 HTML浏览器是用户查看和整理引用的最实用输出
务必在最终结果（第7部分）中突出显示HTML可视化文件路径
与HTML文件同时生成TSV/JSON/报告，为用户提供多种查看方式

7. Report results

7. 结果报告

Unless the user asks for a different format, return:

text

交互式引用浏览器
- [absolute path to citation_visualization.html]  ← 在浏览器中打开此文件，可筛选/选择/下载引用

检索范围
- [Nature Portfolio / Science family / Cell Press / flagship only, plus date limits]

分段引用对应关系
S001: [source segment]
  - [Author, year, title, journal, DOI]
  - 支撑等级: [strong/partial/background/limiting/metadata-only]
  - 插入建议: [e.g. after sentence / after clause]

导出文件
- [absolute path to references.enw / references.ris / references.rdf]

风险和缺口
- [missing full-text check, contradictory evidence, no direct CNS literature, etc.]

Put the HTML browser path FIRST in the report, above everything else, so the user can immediately open and browse candidates. If no suitable CNS/Nature-series paper exists, say so plainly and suggest the best nearby options from non-CNS literature only if the user wants broader coverage.

除非用户要求其他格式，否则返回以下内容：

text

交互式引用浏览器
- [absolute path to citation_visualization.html]  ← 在浏览器中打开此文件，可筛选/选择/下载引用

检索范围
- [Nature Portfolio / Science family / Cell Press / flagship only, plus date limits]

分段引用对应关系
S001: [source segment]
  - [Author, year, title, journal, DOI]
  - 支撑等级: [strong/partial/background/limiting/metadata-only]
  - 插入建议: [e.g. after sentence / after clause]

导出文件
- [absolute path to references.enw / references.ris / references.rdf]

风险和缺口
- [missing full-text check, contradictory evidence, no direct CNS literature, etc.]

将HTML浏览器路径放在报告最顶部，以便用户可立即打开并浏览候选文献。若不存在合适的CNS/Nature系列文献，需明确说明，仅当用户要求扩大范围时，再推荐非CNS文献中的最佳选项。

Search quality rules

检索质量规则

Prefer precision over volume. A useful answer is usually 3-8 candidates, not 50 loosely related papers.
Use exact phrase searches only for distinctive terms; otherwise use concept terms and synonyms.
Check journal identity. Many journals contain the word "nature" but are not Nature Portfolio journals.
Treat citation count as a tie-breaker, not evidence of support.
Capture retractions, corrections, and expressions of concern when visible in Crossref or publisher metadata.
Date-sensitive topics require current searching and explicit search date.
For medical, clinical, or safety claims, search current literature and state that citations do not replace clinical guidance or systematic review.

优先保证精准度而非数量。有效的结果通常为3-8篇候选文献，而非50篇松散相关的文献
仅对独特术语使用精确短语检索；否则使用概念术语和同义词检索
核实期刊身份。许多期刊名称包含“nature”但并非Nature Portfolio旗下期刊
将引用量视为平局时的决胜因素，而非支撑证据
若Crossref或出版商元数据中显示撤稿、更正或关注声明，需予以记录
对时间敏感的主题需进行实时检索，并明确标注检索日期
针对医学、临床或安全相关论点，需检索最新文献，并声明引用不能替代临床指南或系统综述

Related files

File	Open when
references/search-strategy.md	You need help translating a manuscript claim into search queries and support grades
references/journal-scope.md	You need the default Nature/CNS journal-family boundary and official source notes
references/ris-endnote.md	You need RIS, EndNote, or Zotero RDF export guidance
scripts/nature_citation.py	You need to segment text, search Crossref, export ENW/RIS/RDF, and generate HTML

文件	打开场景
references/search-strategy.md	需要将手稿论点转换为检索语句及支撑等级时
references/journal-scope.md	需要获取默认Nature/CNS期刊范围及官方来源说明时
references/ris-endnote.md	需要RIS、EndNote或Zotero RDF导出指导时
scripts/nature_citation.py	需要进行文本分段、Crossref检索、ENW/RIS/RDF导出及HTML生成时

Source notes

来源说明

This skill is based on public bibliographic APIs and official publisher/import documentation: Crossref REST API and filters, NCBI E-utilities, EndNote RIS import options, Nature Portfolio, AAAS Science journals, and Cell Press portfolio descriptions. Verify pages at use time when exact journal coverage or current import behavior matters.

本技能基于公开文献API及官方出版商/导入文档：Crossref REST API及筛选器、NCBI E-utilities、EndNote RIS导入选项、Nature Portfolio、AAAS Science期刊及Cell Press期刊阵容说明。当需要精确的期刊覆盖范围或当前导入行为信息时，需在使用时查阅官方页面。

nature-citation

Original

Translation

Nature Citation

Nature引用

Chinese-user operating mode

中文用户操作模式

Default scope

默认检索范围

Source hierarchy

数据源优先级

Workflow

工作流程

1. Segment the text

1. 文本分段

2. Parse each segment

2. 片段解析

3. Search candidate papers

3. 检索候选文献

4. Evaluate whether each paper supports the segment

4. 评估文献对片段的支撑程度

5. Export reference-manager file

5. 导出参考文献管理工具文件

6. Optional review artifacts

6. 可选评审文件

7. Report results

7. 结果报告

Search quality rules

检索质量规则

Related files

相关文件

Source notes

来源说明