nature-citation

GEO / AI search

yuan1z0825/nature-skillsskills.sh ↗

Installs

9,948

deduplicated, at the last sync

Since we started

+6.5%

40 readings, about 2 hours apart. Not a live curve.

Our category

GEO / AI search

ours

Last read

Sep 3, 2026

from the directory

Our brief

ours

The skill analyzes academic text by splitting long passages or manuscript segments into discrete, citable claims. It then searches for supporting literature specifically within the Nature Portfolio, Science family, and Cell Press journals to help authors add necessary citations to their work.

What it produces
  • claim segmentation table
  • candidate literature list
  • suggested citation placement and support details
  • review artifacts (JSON, TSV, Markdown, HTML)
  • reference-manager export file
What it needs
  • text passage or claim list
  • DOI list
  • PMID list
  • journal scope and time constraints
  • target export format
Paid services

not detected

The evidence does not provide information regarding paid API usage or required subscriptions.

Registration

not detected

The evidence does not mention any requirement for user registration to use the skill.

Limits and human review

The skill only uses academic papers as candidate support and cannot guarantee that suggested citations are suitable for final publication. It will explicitly note evidence deviation if literature supports claims that are adjacent but not identical, and it excludes using blogs or news reports as sole evidence.

Evidenceskills/nature-citation/README.md:1-46skills/nature-citation/references/journal-scope.md:1-66skills/nature-citation/references/ris-endnote.md:1-75skills/nature-citation/references/script-usage.md:1-43+2
skills/nature-citation/README.md1–46
# `nature-citation` 技能

[English](README_EN.md)

`nature-citation` 用于把论文段落、手稿片段或单条科学判断拆成可引用的 claim,并为每个 claim 寻找 Nature Portfolio、Science family 和 Cell Press 范围内的支撑文献。

## 适合用它做什么

- 给 introduction、discussion 或 reviewer response 中的关键判断补引用。
- 将长段落拆成稳定编号的 claim 单元,例如 `S001`、`S002`。
- 限定只查 Nature、Science、Cell 及其子刊,或只保留旗舰刊。
- 为每个候选文献说明支撑位置、证据强度和插入建议。
- 默认导出可检查的 RIS 文件,并在导出前拦截缺失名字、仅有姓氏或作者列表不完整的记录。
- 通过 DOI 或 PMID 获取结构化作者信息,保留作者顺序、名字/首字母、后缀和团体作者。

## 典型请求

- “把这段 introduction 分段补 Nature 系列引用。”
- “只用 CNS 及子刊,为这些 claim 找近五年的支撑文献。”
- “我已经确认这些 DOI,帮我导出 Zotero 可导入文件。”

## 你需要提供

- 待引用的段落、claim 列表、DOI 清单或 PMID 清单。
- 期刊范围、时间范围、是否允许综述、是否只要旗舰刊。
- 目标引用格式和导出格式,例如 `RIS`、`ENW` 或 Zotero `RDF`。

## 产出

- claim 分段表和候选文献表。
- 每个 claim 的建议插入位置、候选 DOI、期刊、年份和支撑说明。
- 可选的 JSON、TSV、Markdown、HTML 审查材料。
- 可导入文献管理器的引用文件。默认使用 RIS,EndNote 导入时选择 `Reference Manager (RIS)`。

## 边界

- 只把论文作为候选支撑,不会替作者保证其必然适合最终引用。
- 不会使用博客、新闻稿或搜索摘要作为唯一依据。
- 当文献只能支撑相邻但不完全相同的 claim 时,会明确标注证据偏差。

## 相关技能

- `nature-academic-search`:更宽范围的文献搜索和引用指标审计。
- `nature-ref-verifier`:校验已选参考文献的元数据。
- `nature-writing`:把引用选择整合回手稿论证。
skills/nature-citation/references/journal-scope.md1–66
# Journal Scope

The skill's default journal-family boundary is intentionally practical rather than exhaustive. Use it
to find likely Nature/CNS-family candidates, then verify exact journal status on official pages if the
author needs a strict portfolio definition.

## Default families

### Nature Portfolio

Include:

- `Nature`
- journals beginning with `Nature `, such as `Nature Medicine`, `Nature Biotechnology`,
  `Nature Methods`, `Nature Materials`, `Nature Genetics`, `Nature Communications`
- `Communications` journals, such as `Communications Biology`, `Communications Chemistry`,
  `Communications Materials`, `Communications Earth & Environment`, `Communications Medicine`
- `npj` journals
- `Scientific Reports`

Be careful with unrelated titles that include the common word "nature".

### Science family

Include by default:

- `Science`
- `Science Advances`
- `Science Translational Medicine`
- `Science Signaling`
- `Science Immunology`
- `Science Robotics`

The AAAS Science Partner Journal program is not included by default unless the user asks for partner
journals or broader AAAS coverage.

### Cell Press

Include the flagship `Cell`, major primary-research Cell Press journal
skills/nature-citation/references/ris-endnote.md1–75 · excerpt truncated
# RIS, EndNote, and Zotero RDF Output

EndNote can import RIS files using the `Reference Manager (RIS)` import option. Use `.ris` as the
default exchange format because it is plain text, widely supported, and easy to inspect.

## Contents

- [RIS mapping for journal articles](#ris-mapping-for-journal-articles)
- [Author-integrity preflight](#author-integrity-preflight)
- [EndNote import instruction](#endnote-import-instruction)
- [Zotero RDF guidance](#zotero-rdf-guidance)

## RIS mapping for journal articles

Use these tags:

```text
TY  - JOUR
TI  - Article title
AU  - Author, Given
AU  - Consortium Name,
T2  - Journal title
JO  - Journal title
PY  - Publication year
Y1  - YYYY/MM/DD when available
VL  - Volume
IS  - Issue
SP  - First page or article number
EP  - Last page
DO  - DOI
AN  - PMID:12345678
UR  - URL
SN  - ISSN
N2  - Abstract or short metadata note, only when safely available
ER  -
```

Rules:

- Write one `AU` line per author and preserve the source order.
- Personal names use `Family, Given` or `Family, Given, Suffix`. Keep source-provided initials and name particles.
- Corporate or consortium authors require a trailing comma, for example `AU  - NMSS Validation Grou
skills/nature-citation/references/script-usage.md1–43 · excerpt truncated
# Script usage and long-article strategy

Open this reference when running `scripts/nature_citation.py` or when the input is long enough to need batching. It expands step 3 of the workflow.

## Running the script

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 ris \
  --with-artifacts
```

### Useful options

- `--text-file manuscript.txt`: read long text from a file.
- `--claim "CLAIM TEXT"` or `--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.
- `--pmid 12345678` or `--pmid-file pmids.txt`: fetch the complete ordered author list and journal metadata directly from PubMed. Prefer this route for biomedical records when Crossref lacks given names or a consortium author.
- `--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.
skills/nature-citation/references/search-strategy.md1–57 · excerpt truncated
# Search Strategy

## Turn claims into searchable concepts

Break each sentence into:

- `phenomenon`: what is being claimed
- `entity`: gene, protein, pathway, compound, intervention, technology, population, or ecosystem
- `relationship`: increases, decreases, predicts, regulates, causes, associates with, improves, detects
- `context`: species, tissue, disease, cell type, geography, time period, device, method, or dataset
- `boundary`: "in cancer cells", "after treatment", "in older adults", "under drought", etc.

Create search queries at three levels:

1. `precise`: entity + relationship + outcome + context
2. `synonym`: alternate names and abbreviations
3. `broad`: field context if no direct paper is found

For Chinese claims, translate the scientific concepts, not the sentence literally. Keep acronyms and
standard nomenclature unchanged.

## Support grading

Use the smallest support grade that is defensible:

| Grade | Meaning | Good use |
|---|---|---|
| strong support | Directly tests the same core relationship in a similar context | Experimental, mechanistic, or quantitative manuscript claims |
| partial support | Supports one component or a narrower setting | Carefully qual
skills/nature-citation/SKILL.md1–71
---
name: nature-citation
description: >-
  Add strict Nature/CNS citations to manuscript text by splitting long passages into citable
  segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the
  AAAS Science family, and Cell Press, filtering by publication time range, and exporting one
  reference-manager-ready output by default. Use this skill whenever the user asks to input text and
  automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS
  support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用",
  "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF.
  Also trigger on general academic-writing citation needs even without the word "Nature", such as
  adding references while writing a paper, finding sources/literature for a claim, building a
  reference list, citation/referencing for academic writing, and Chinese phrasings like
  学术写作引用、写论文加引用、写paper找文献、加参考文献、配文献、引用文献、文献支撑.
metadata:
  author: Yuan1z skill, refactored into static/dynamic layers
---

# Nature Citation — Router

This skill is split into two layers:

- A **static layer** under `static/`

Read 6 of 6 text files in the skill.

Checked September 2026 · GemmaWritten from the skill's published files. Check the source before relying on access or cost details.

Installfrom the directory

npx skills add https://github.com/yuan1z0825/nature-skills

Installing happens there, not here. We are an index with an opinion, not a mirror.

What is inside itfrom the directory

agents/openai.yaml
evals/evals.json
manifest.yaml
README_EN.md
README.md
references/journal-scope.md
references/ris-endnote.md
references/script-usage.md
references/search-strategy.md
scripts/nature_citation.py
SKILL.md
static/core/chinese-mode.md
static/core/principles.md
static/core/workflow.md
tests/test_author_exports.py

15 files — names only. The directory does not report sizes.

What the auditors foundfrom the directory

A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.

Gen Agent Trust HubThe skill is a citation search tool that turns manuscript text into formatted references. It includes a Python script that queries the Crossref API for bibliographic metadata and generates reference files (ENW, RIS, RDF) and an HTML report. No malicious patterns, obfuscation, or dangerous execution were found.May 9, 2026 · SAFEpass
SocketNo alertsMay 9, 2026pass
SnykRisk: LOW · No issuesMay 10, 2026 · LOWpass

Installs, reading by readingours

9.3k
9.9k
Aug 30, 202640 readings over 5 days, drawn as the last reading of each day.Sep 3, 2026

Axis starts at 9.3k, not zero — the range is 9.3k to 9.9k.

Asked out loudspoken, not typed

The same skill in the words people use speaking to an assistant rather than typing into a box. Each one carries the situation it came from, and each answer says only what the skill's own files support.

asking about costDo I need to pay for this skill?

The evidence provided does not mention any fees or paid requirements for using the skill.

writing a paperCan it help me add citations to my manuscript text?

Yes, it can take a passage and split it into citable claims while searching for supporting literature from Nature-series journals. It provides suggested insertion points and support details.

checking journal scopeWhat kind of journals does it look at?

It focuses on the Nature Portfolio, Science family, and Cell Press titles, allowing users to restrict searches to flagship publications only if desired.

Filed alongside itours