PluginBench
Skill
Review
Audit score 70

nature-citation

yuan1z0825/nature-skills

Find and verify Nature/CNS-family literature supporting manuscript claims with claim-to-source mapping.

What is nature-citation?

Nature Citation is a skill for locating and validating peer-reviewed literature from Nature and CNS-family journals that support specific manuscript claims. Use it when you need to map claims to high-impact sources, verify journal scope eligibility, and export citations to reference managers.

  • Segment manuscripts into claims and search for supporting Nature/CNS-family literature
  • Evaluate source quality conservatively against strict journal-scope criteria
  • Map claims to verified sources with complete bibliographic metadata
  • Export citations in RIS/EndNote/Zotero RDF format for reference managers
  • Handle both English and Chinese-language workflows
  • Batch-process long articles with multiple segments

How to install nature-citation

npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-citation
Prerequisites
  • Internet access for literature search and DOI/PMID metadata retrieval
  • Python environment with requests library (for nature_citation.py script)
  • Reference manager software (EndNote, Zotero, or compatible RIS reader) for import
Claude Code
Cursor
Windsurf
Cline

How to use nature-citation

  1. 1.Load the skill manifest and core guidance (principles.md and workflow.md)
  2. 2.State your journal scope (Nature series, CNS, CNS and sub-journals, or flagship-only) and any language preference
  3. 3.Segment your manuscript into individual claims or sections
  4. 4.Run the seven-step workflow: segment → parse → search → evaluate support → validate metadata → export → generate review artifacts
  5. 5.Use scripts/nature_citation.py with appropriate flags (--scope, --language) for automated search and export
  6. 6.Import the exported RIS/EndNote file into your reference manager
  7. 7.Review the generated claim-to-source mapping and validation report

Use cases

Good for
  • Verify that a Nature-track manuscript has adequate high-impact citations before submission
  • Find CNS-family sources to support specific claims in a research paper
  • Map claims across a multi-segment manuscript to appropriate journal-scope literature
  • Export verified citations directly into EndNote or Zotero for manuscript preparation
  • Audit citation quality and journal scope alignment for revision rounds
Who it's for
  • Researchers preparing manuscripts for Nature or CNS-family journals
  • Manuscript authors conducting pre-submission literature verification
  • Research teams managing citation quality and journal scope compliance
  • Bilingual researchers working in English and Chinese contexts

nature-citation FAQ

What is the 'journal scope' and how do I specify it?

Journal scope defines which Nature-family journals count as valid sources: Nature series (flagship only), CNS (Cell, Nature, Science), or CNS and sub-journals. Detect it from your target journal and pass it to the script via --scope flag; see references/journal-scope.md for exact boundaries.

Can I use this for journals outside Nature/CNS?

This skill is optimized for Nature/CNS-family scope. For broader literature search across unrestricted sources, use a general literature-search skill instead.

What happens if a paper title matches my claim but the abstract doesn't support it?

The skill never presents a paper as support based on title alone. It requires abstract or publisher-page verification before including any source in the final export.

How do I handle manuscripts with many segments?

For more than ~10 segments, switch to the batched long-article strategy in references/script-usage.md to process efficiently without losing claim-to-source mapping.

What if DOI metadata is missing author given names?

The skill refetches the record by PMID or verifies it against the publisher rather than exporting surname-only author fields, ensuring complete bibliographic metadata.

Full instructions (SKILL.md)

Source of truth, from yuan1z0825/nature-skills.


name: nature-citation description: "Find and verify Nature/CNS-family literature supporting manuscript claims, with claim-to-source mapping and reference-manager export. Use for Nature系列引用、CNS支撑文献、分段补引用 when this journal scope is requested; use broader literature search for unrestricted sources." metadata: author: Yuan1z skill, refactored into static/dynamic layers

Nature Citation — Router

Routing protocol

For a new task, load the core and matching resources below. Reuse already loaded guidance on follow-ups; load more only when the task needs it.

1. Load the manifest and the core layer

Read manifest.yaml. Then read every file listed under always_load:

  • static/core/principles.md — what the skill produces, the strict journal scope, the source hierarchy, and the search-quality rules.
  • static/core/workflow.md — the seven-step workflow and the final report format.

2. No content axis — confirm scope and language inline

Unlike the other nature-* skills, nature-citation has no fragment axis. Its variation is runtime parameters, not different content bodies:

  • journal scope — Nature系列 / CNS / CNS及子刊 / flagship-only. Read it from the user's wording (see core/principles.md) and pass it to the script as --scope.
  • user language — if the user writes Chinese or requests Chinese guidance, read static/core/chinese-mode.md (Chinese notes, English search queries).
  • input length — if there are more than ~10 segments, switch to the batched long-article strategy in references/script-usage.md.

State the detected scope and date limits in one short line before searching.

3. Run the workflow

Follow the seven steps in core/workflow.md: segment, parse, search, evaluate support conservatively, validate complete structured author metadata, export one reference-manager file, and generate review artifacts when useful. Put the HTML browser path first only when it was generated. Prefer scripts/nature_citation.py for the search/export when internet access is available; open references/script-usage.md for its full flag list and the long-article batch strategy. When DOI metadata lacks given names, refetch the record by PMID or verify it against the publisher rather than exporting surname-only AU fields.

Never present a paper as support merely because its title is related, and never cite a metadata-only candidate without checking the abstract or publisher page. Do not invent missing bibliographic fields.

4. Reach for references only when needed

The files under references/ are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest:

  • running the script, full flags, long-article batching → references/script-usage.md.
  • turning a claim into search queries and support grades → references/search-strategy.md.
  • the exact Nature/CNS journal-family boundary → references/journal-scope.md.
  • RIS / EndNote / Zotero RDF export details → references/ris-endnote.md.