nature-data Skill for Claude: Data Availability Statements and FAIR Checks

nature-data makes Claude draft or audit a paper's Data Availability statement, repository plan and FAIR metadata in the Nature style.

Installs: 15.7K; on skills.sh
Stars: 51.7K; on GitHub
Files: 14; besides SKILL.md
Updated: Nov 2026; last repo commit

nature-data is a skill in the nature-skills collection by Yuan1z0825. Claude follows an eight-step workflow: identify the journal, inventory every dataset, classify each into an access route, pick repositories and identifiers, draft the statement, add dataset citations, run a FAIR and metadata audit, and return ready-to-paste text with unresolved fields.

It does not invent DOIs, accession numbers, repository names, licences or embargo dates, and it flags "available upon request" as weak unless a legal, ethical, commercial or third-party restriction applies. It is for availability and metadata, not general data cleaning or statistics.

The repo README marks this skill Draft, meaning its rules are defined but not yet tested on real cases.

Good for

Authors preparing a Nature or Springer Nature submission
Researchers who must say where their datasets live and who may access them
Authors turning Chinese data notes into submission-ready English

Install nature-data

Claude Code

Copy this prompt.

Install the nature-data skill in Claude Code. Run this command:

npx skills add Yuan1z0825/nature-skills --skill nature-data --skill nature-shared

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

Install nature-shared with nature-data. The skill reads ../nature-shared/journal-formats/nature-machine-intelligence.md when the target is Nature Machine Intelligence, and the repo README says installing one skill does not add its shared package. The Claude app is left out because the README does not describe it.

From the project README. Source.

What's in the skill

When it loads

Draft or audit manuscript Data/Code Availability statements, dataset access routes, repository plans, and FAIR metadata. Use for 数据可用性声明、数据共享、数据仓库选择 and dataset citations; not general data cleaning or statistical analysis.

Sections in SKILL.md

Routing protocol
1. Load the manifest and the core layer
2. No content axis — confirm journal and language inline
3. Run the workflow
4. Reach for references only when needed

Key facts

License (per GitHub): Apache-2.0
Author: yuan1z0825 (repo owner)
Repository: yuan1z0825/nature-skills, folder skills/nature-data
Installs on skills.sh: 15,743 as of 2026-11-02
Repo stars: 51,696 as of 2026-11-02 (whole repo)
Last repo commit: 2026-11-01
Files in the skill folder: 15 files including SKILL.md
Status in the repo README: Draft (rules defined, not yet tested on real cases)
skills.sh audits: Gen Agent Trust Hub: pass; Socket: pass; Snyk: pass

What it includes

Follow the journal if it conflicts
Journal-specific instructions win over the skill.
1. Identify journal and article type
List every dataset behind the results
Raw, processed, figure source data, secondary data, software outputs, models, tables and images.
2. Inventory datasets
Seven routes per dataset
Public repository, controlled access repository, within paper or supplement, reused public source, third-party restricted, available on justified request, or not applicable.
3. Classify access route
Before any drafting
Prefers a DOI, accession number, Handle, ARK or stable repository record over personal sites and temporary cloud links.
4. Choose repository and identifiers
Dataset-to-location mapping and formal citations
Writes the statement with explicit locations and adds formal citations for public data that support conclusions.
5-6. Draft statement and citations
Run before finalizing
Uses references/fair-metadata-checklist.md for FAIR checks, README metadata, licences, provenance and DataCite fields.
7. FAIR and metadata audit
Statement, actions, flags, 中文核对 block
Returns Data Availability text, repository and citation actions, missing information and risk flags, plus a Chinese confirmation block for Chinese-speaking users.
8. Output
Nature Article and Nature Machine Intelligence rules
references/nature-article-requirements.md covers Nature. For Nature Machine Intelligence the skill reads a file in the nature-shared folder.
Journal references

From the official docs

Questions

What does nature-data do?

It makes Claude write or check a Data Availability statement. Claude maps each dataset to a repository, accession, DOI, licence or access condition, and lists what you still need to confirm.

How do I install it?

Use the install box above. It installs nature-data together with nature-shared from the Yuan1z0825/nature-skills repo, because the skill reads a file from nature-shared when the target is Nature Machine Intelligence.

Does it need nature-shared?

Only for one case. For Nature Machine Intelligence, SKILL.md says to open ../nature-shared/journal-formats/nature-machine-intelligence.md. The install box includes nature-shared because the repo README says installing one skill does not add its shared package.

Will it invent accession numbers?

No. The SKILL.md says it must not invent DOIs, accession numbers, repository names, licences, embargo dates, ethics approvals, access committees or data-use conditions. Missing facts become a confirmation list.

Does it need an API key?

The SKILL.md names no key and the nature-data folder has no scripts.

Is it safe to install?

The nature-data folder bundles no scripts. The README marks it Draft, so check any statement it writes against the journal's own instructions before you submit.

Is it a Nature journal product?

The repo owner is Yuan1z0825, a GitHub user. The README describes Nature / Springer Nature-style output, and the skill tells Claude to follow the target journal's own instructions when they differ.

Information

updated Nov 2, 2026

Repository: yuan1z0825/nature-skills
Folder: skills/nature-data

yuan1z0825/nature-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 6

nature-data SKILL.md · github.com
nature-skills README · github.com
nature-data README (English) · github.com
static/core/workflow.md · github.com
static/core/stance.md · github.com
manifest.yaml · github.com