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

nature-citation

Skill20 starsChanged 48 days agoMITView on GitHub

Strict Nature/CNS-family citation retrieval, verification, and export. Given a topic, claim, or list of papers, finds real citations, verifies DOIs, checks retraction status, and exports in BibTeX, RIS, ENW, or Zotero RDF format. Trigger when user needs citations, wants to verify references, or needs to export a reference list.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use nature-reviewer, nature-paper-to-patent and 7 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.
  • dragonadamSkill

    nature-reviewer

    Simulate a Nature-style reviewer assessment from the referee perspective rather than an author rebuttal. Use when the user wants a pre-submission review, reviewer report, peer-review style critique, novelty/significance/technical soundness assessment, reviewer-style manuscript evaluation, 审稿人视角评估, 预审稿意见, or Nature reviewer report. Return 3 reviewer reports plus a cross-review synthesis, grounded only in the local Nature reviewer source basis.

    Also in 6 projects that use this

  • 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

  • Galaxy-DawnSkill

    nature-response

    Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review reports, 审稿意见回复, 逐点回复, 修回信, 大修回复, 小修回复, or 如何回复 reviewer.

    Also in 6 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

  • dragonadamSkill

    nature-academic-search

    Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv). Use when the user needs coordinated multi-step literature workflows beyond a single MCP call.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If results found: use these as primary citations (already in user's library)

    line 28
  2. Very specific:

    If DOI present: web_fetch("https://api.crossref.org/works/<DOI>")

    line 44
  3. Very specific:

    If no DOI: web_search('"<author>" "<year>" "<journal>" "<title keywords>"')

    line 46

“Common” is measured: kept by at least 6 in 10 of the 10 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-citation

Purpose

Find, verify, and export citations for Nature-series manuscripts. Strict accuracy: every reference must be real, accessible, and support the cited claim.


Trigger Conditions

  • "找参考文献" / "引用" / "citation" / "reference"
  • "验证引用" / "verify DOI" / "check references"
  • "导出文献" / "export BibTeX" / "Zotero" / "RIS" / "ENW"
  • "这个说法有文献支持吗" / "find supporting papers for..."
  • User pastes a claim and asks for citations

Workflow

Mode 1: Find citations for a claim

  1. User provides: a scientific claim or topic
  2. First: search the local papers index (data/papers-index.json). If a personal literature API is configured via the LITREVIEW_API env var, also web_fetch(f"{LITREVIEW_API}?q=<URL-encoded-query>"). Never call a hardcoded private host.
    • If results found: use these as primary citations (already in user's library)
  3. CrossRef full-text search — web_fetch("https://api.crossref.org/works?query=<query>&filter=has-full-text:true&rows=5&sort=relevance")
    • Extract: DOI, title, authors, year, journal, is-referenced-by-count
  4. Broader web search — web_search("<claim> site:nature.com OR site:science.org OR site:cell.com")
  5. arXiv — web_search("arxiv <topic> <year>")
  6. For each candidate paper:
    • Verify via CrossRef: web_fetch("https://api.crossref.org/works/<DOI>") → confirms: real DOI, correct metadata, citation count
    • Check retraction via RetractionWatch: web_search("site:retractionwatch.com \"<title keywords>\"")
    • Also check: web_search("<title> retraction OR retracted OR correction")
    • Confirm it actually supports the claim (not just related)
  7. Return ranked list: most relevant first, with support assessment and citation count

Mode 2: Verify existing reference list

For each reference the user provides:

  1. CrossRef DOI lookup (most reliable):
    • If DOI present: web_fetch("https://api.crossref.org/works/<DOI>")
    • Compare returned metadata with user's reference — flag any discrepancy
  2. If no DOI: web_search('"<author>" "<year>" "<journal>" "<title keywords>"')
  3. Retraction check: web_search("site:retractionwatch.com \"<first author> <year>\"")
  4. Assess: does this ref support the claim it's cited for?
  5. Flag: ✅ verified via CrossRef | ⚠️ found but unverified | ❌ wrong metadata or retracted

Mode 3: Export reference list

Convert verified references to the requested format (see below).


Nature Reference Style (numbered, Vancouver)

Format:

[number]. LastName, A. B., LastName, C. D. & LastName, E. F. Title of article. 
Journal Abbrev. Vol, first–last page (Year).

Rules:

  • Up to 6 authors, then "et al."
  • Journal names abbreviated (e.g., Nat. Mater., Nat. Commun., Science, J. Am. Chem. Soc.)
  • Volume in bold (in final typeset, not manuscript)
  • Pages with en-dash (–), not hyphen (-)
  • Year in parentheses at end
  • DOI optional in manuscript, required for online submission

Example:

1. Liu, Z., Zhang, X. & Wang, Y. High-performance electrocatalysts for 
   oxygen evolution. Nat. Catal. 5, 234–243 (2022).
2. Chen, H. et al. Atomically dispersed metal catalysts. Science 375, 
   eabh1885 (2022).

Export Formats

BibTeX (for LaTeX/Overleaf):

@article{Liu2022,
  author  = {Liu, Zhen and Zhang, Xiao and Wang, Yong},
  title   = {High-performance electrocatalysts for oxygen evolution},
  journal = {Nature Catalysis},
  year    = {2022},
  volume  = {5},
  pages   = {234--243},
  doi     = {10.1038/s41929-022-00000-0}
}

RIS (for Mendeley/Zotero import):

TY  - JOUR
AU  - Liu, Zhen
AU  - Zhang, Xiao
AU  - Wang, Yong
TI  - High-performance electrocatalysts for oxygen evolution
JO  - Nature Catalysis
PY  - 2022
VL  - 5
SP  - 234
EP  - 243
DO  - 10.1038/s41929-022-00000-0
ER  -

ENW (EndNote):

%0 Journal Article
%A Liu, Zhen
%A Zhang, Xiao
%A Wang, Yong
%T High-performance electrocatalysts for oxygen evolution
%J Nature Catalysis
%D 2022
%V 5
%P 234-243
%R 10.1038/s41929-022-00000-0

Zotero RDF:

Generate standard Zotero RDF XML format with rdf:type bib:Article entries.


Journal Abbreviations (Nature Portfolio)

Full nameAbbreviation
NatureNature
Nature MaterialsNat. Mater.
Nature ChemistryNat. Chem.
Nature EnergyNat. Energy
Nature CatalysisNat. Catal.
Nature CommunicationsNat. Commun.
Nature MethodsNat. Methods
Nature SustainabilityNat. Sustain.
Nature Computational ScienceNat. Comput. Sci.
Journal of the American Chemical SocietyJ. Am. Chem. Soc.
Angewandte Chemie International EditionAngew. Chem. Int. Ed.
Advanced MaterialsAdv. Mater.
ACS NanoACS Nano
ScienceScience
CellCell

Verification Checklist

For each reference, confirm:

  • Author names correct (spelling, order)
  • Year matches published version (not preprint)
  • Journal name and abbreviation correct
  • Volume and page numbers accurate
  • DOI resolves to correct paper
  • Not retracted (search "[title] retraction")
  • Actually supports the cited claim

Output

  1. Verified reference list in Nature numbered style
  2. Export file in requested format (BibTeX / RIS / ENW / Zotero RDF)
  3. Verification report: ✅ confirmed / ⚠️ uncertain / ❌ problem found

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.