nature-citation

Use it when:: You need references from Nature, Science or Cell family journals to support specific claims in a manuscript.
It does:: Splits the text into segments, turns each claim into searches, grades how well each paper supports it, and exports one reference file.
You get:: Sources for each segment with a support grade and where to insert them, one RIS, EndNote or Zotero RDF file, optionally an HTML browser.
Needs:: Python and internet access for its bundled search script.

TL;DR

A citation finder restricted to one journal family: Nature Portfolio, CNS (Cell, Nature, Science and their sister journals) or flagship journals only, as you ask. It splits your text into citable segments, extracts each core claim and its type, and turns it into two to four English search queries, then searches with a bundled Python script against Crossref, and PubMed for biomedical topics, with optional year limits. It grades each candidate on a conservative scale, from strong to partial to background to contradictory, and never cites a metadata-only hit without checking the abstract or publisher page. Before writing the single reference-manager file it checks that every author list is complete, refetching by DOI or PMID rather than exporting surname-only entries, and it will not invent missing fields. Long texts are run in batches of about ten segments and merged, with an HTML browser to filter and pick candidates. Notes can be in Chinese while queries stay in English. For unrestricted sources use a broader literature search instead.

Summarizes the skill at d774add.

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

skills.sh page Source on GitHub All skills from yuan1z0825/nature-skills

Total Downloads: 16,500 on skills.sh, Nov 9, 2026
Repo stars: 52,794 yuan1z0825/nature-skills
First seen: May 6, 2026 on skills.sh

Weekly Downloads

424

-58% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	1,002
Sep 28	775
Oct 5	533
Oct 12	667
Oct 19	683
Oct 26	622
Nov 2	467
Nov 9	424

Category	category:science Research reproduction, financial data, charts and diagrams.
Type	type:workflow A multi-step process the agent follows: interview, debug, run a TDD loop, review.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:cli A specific command-line tool or desktop app must be installed, such as gh, agent-browser, LibreOffice, Obsidian or a vendor CLI.
Publisher	by:community Everyone else. Unverified vendor claims default to community.
Topics	research
Stack	stack:crossref stack:pubmed

SKILL.md

From yuan1z0825/nature-skills at d774add. Checked daily, last changed Nov 6, 2026.

Frontmatter

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.