Verified:GitHub

nature-data

Generates data availability statements and related documents for scientific publications.

4|Updated Jun 4, 2026

Search Tags:#nature #academic publishing #data availability #repository planning #bilingual writing #fair metadata #dataset citation

Ready to run

npx skills add https://github.com/lijiandao/lightest-skills --skill nature-data-lijiandao

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nature-data
Source: https://github.com/lijiandao/lightest-skills/tree/main/community/nature-skills/nature-data
Command: npx skills add https://github.com/lijiandao/lightest-skills --skill nature-data-lijiandao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps authors turn manuscript data notes into clear, submission-ready Data Availability text, repository plans, dataset citations, and FAIR metadata checks for Nature-style and other academic papers.

Core Features & Use Cases

Drafts publication-ready Data Availability statements for public, controlled-access, third-party, supplementary, and request-based data.
Maps each dataset to the right repository, identifier, access route, and citation format without inventing missing metadata.
Handles bilingual Chinese-to-English wording for authors who need precise availability language for journals, reviewers, and editors.

Quick Start

Ask for a Nature-style Data Availability statement from your data notes and tell me which datasets, repositories, and access restrictions need to be checked.

Frequently Asked Questions about nature-data

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I draft a Nature-ready Data Availability statement for my manuscript?▼

A Nature-ready Data Availability statement is drafted by mapping each manuscript dataset to its repository, identifier, and access route. This process generates publication-ready text for public, controlled-access, third-party, or supplementary data without inventing missing metadata.

How do I format dataset citations and FAIR metadata checklists for academic publishing?▼

Formatting dataset citations and FAIR metadata checklists involves validating metadata for each dataset and selecting the appropriate repository and identifier. This ensures your manuscript data meets FAIR principles and provides accurate citation formats for original or reused datasets.

Can I translate Chinese data availability wording to English for journal submissions?▼

Chinese-to-English availability wording is supported for authors needing precise language for journals, reviewers, and editors. This bilingual translation ensures your data availability statements maintain accuracy and compliance when submitting to English-language academic journals.

How do I classify access routes for restricted or controlled-access datasets in a data availability statement?▼

Access routes for restricted or controlled-access datasets are classified by defining the specific conditions for request-based data. This involves explicitly mapping dataset-to-location and validating access conditions without inventing licenses or permissions, ensuring accurate reporting of data restrictions.

What should I do if I am missing DOIs or accessions for my repository planning?▼

Missing DOIs, accessions, licenses, or access conditions are never invented during repository planning. The process requires explicit dataset-to-location mapping and metadata validation, meaning you must provide the actual identifiers to generate a compliant data availability statement.

Does this data availability drafting process work for both original and reused datasets?▼

Data availability drafting applies to both original and reused datasets, including supplementary source data and third-party records. It maps each dataset type to the correct repository, identifier, and citation format to produce accurate availability statements for any manuscript data.