nature-data

The nature-data skill helps researchers prepare, audit, and revise Data Availability statements for Nature-family journal submissions and other academic publications. It addresses the critical challenge of meeting journal requirements for research data sharing, repository selection, dataset citations, and FAIR metadata compliance. The skill operates through a structured routing protocol that loads versioned content fragments on demand, ensuring accurate and up-to-date guidance without hallucinating policy details or repository information.

This skill provides comprehensive support for inventorying datasets, classifying them into appropriate access routes (public repository, controlled access, within paper, reused public, third-party restricted, justified request, or not applicable), selecting suitable repositories with proper identifiers, and drafting ready-to-paste statements with explicit dataset-to-location mapping. It includes formal DataCite-style dataset citations, FAIR metadata audits, and handles sensitive data scenarios with proper justification. The skill maintains a clear source hierarchy and default stance on data availability, never inventing DOIs, accession numbers, or repository details.

Primary users include academic researchers preparing manuscripts for Nature-family journals, research data managers supporting publication workflows, and Chinese-speaking authors who need bilingual support (accepting Chinese input while producing English output with precise terminology conversion). The skill is particularly valuable for handling complex data sharing scenarios involving restricted access, embargo periods, ethics approvals, commercial restrictions, or third-party data reuse, while ensuring compliance with journal policies and FAIR principles.