Research Data Documentation Generator
Generate FAIR-compliant dataset documentation and metadata
What You Can Do
You can create comprehensive, standards-compliant documentation for research datasets including data dictionaries, metadata records, and institutional compliance reports. The skill generates structured documentation following FAIR principles (Findable, Accessible, Interoperable, Reusable), validates against disciplinary standards like DDI, DataCite, or Dublin Core, and produces documentation your institution and publishers require for data archival and discovery.
Features
Automatically checks your documentation against all FAIR principles and flags missing elements (persistent identifiers, licenses, provenance, access rights)
Converts raw dataset metadata into structured variable descriptions with data types, value ranges, units, missing value codes, and controlled vocabulary mappings
Produces metadata in multiple formats (JSON-LD, XML, Dublin Core, MIARC) compatible with institutional repositories and data discovery services
Adapts documentation to match standards in your field—DDI-C for social science, MIAME for genomics, FGDC for geospatial, domain-specific vocabularies
Generates compliance checklists and documentation required by your institution's data management policies, IRB protocols, or funder mandates
Tracks and documents data provenance, processing steps, software versions, and transformation logic for full reproducibility
Generates automated quality checks on metadata completeness, consistency, and compliance with specified standards, with actionable recommendations
Example Output
Data Dictionary (tabular format):
| Variable | Type | Range | Unit | Missing Value | Description |
|---|---|---|---|---|---|
| temperature_c | float | -40 to 50 | Celsius | NA | Daily mean temperature measured at 14:00 UTC |
| precipitation_mm | float | 0 to 200 | mm | 999 | Total 24-hour precipitation, quality-controlled |
Metadata Record (Dublin Core):
<dc:creator>Smith, John; Lee, Maria</dc:creator>
<dc:issued>2026-01-15</dc:issued>
<dc:title>Climate Station Data 2025</dc:title>
<dc:identifier>https://doi.org/10.5281/zenodo.1234567</dc:identifier>
<dc:language>en</dc:language>
<dc:rights>CC-BY-4.0</dc:rights>
<dcat:keyword>climate, temperature, precipitation, station-data</dcat:keyword>
FAIR Compliance Checklist:
- ✓ Dataset has persistent identifier (DOI)
- ✓ Metadata includes creation date and responsible party
- ✓ License is explicitly stated (CC-BY-4.0)
- ✓ Data dictionary describes all variables and units
- ✗ Missing: Access restrictions and embargo dates
- ✗ Missing: Related publications and citations
What's Included
- Data Dictionary Template: Pre-formatted tables for variables with fields for type, range, units, missing value codes, definitions, and validation rules
- Metadata Generation System: Structured prompts to extract, organize, and standardize metadata from your dataset description and produce standards-compliant output
- FAIR Compliance Validator: Automated checklist testing documentation against FAIR principles and disciplinary standards with gap analysis and remediation guidance
- Institution-Specific Templates: Customizable templates aligned with common data management requirements from funders, IRBs, and institutional repositories
- Data Lineage Worksheet: Guided template to document data sources, processing steps, software versions, parameters, and decision logic for reproducibility
- Quality Assurance Checklist: Verification guide ensuring all required metadata fields are present, internally consistent, and machine-readable for archival systems
Who It's For
- Research Data Scientists and Data Stewards
- Data Librarians and Repository Curators
- Research Administrators and Compliance Officers
- Institutional Repository and Archive Managers
- Grant-Funded Researchers Preparing Data for Submission
Best For
- Creating documentation for datasets destined for institutional or disciplinary archives
- Ensuring FAIR compliance before publication or funder submission
- Standardizing metadata across multi-site or institutional research programs
- Preparing data for long-term preservation, discovery, and reuse
You might also like
You design and validate information architectures that align with how users actually search and think about content. This skill analyzes user mental models, search patterns, and existing structures to identify discoverability gaps and recommend strategic improvements that make finding information intuitive and fast.
by kanta13jp1
You'll design scalable, hierarchical content taxonomies tailored to your organization's structure and compliance needs. This skill generates comprehensive governance frameworks that define roles, responsibilities, approval workflows, and decision-making authority. You'll receive implementation roadmaps, metadata standards, stewardship models, and compliance matrices ready to deploy across departments.
by kanta13jp1
You can create, validate, and optimize taxonomies specifically designed for legal information systems that account for jurisdiction-specific variations, regulatory hierarchies, and legal domain complexity. Claude helps you build hierarchies that map correctly across different legal systems, identify taxonomy conflicts, and ensure your legal taxonomy is searchable, maintainable, and compliant with legal information standards.
by kanta13jp1
Create comprehensive technical specifications for ophthalmic instruments with built-in regulatory compliance markers, systematically analyze competitor instruments to identify market gaps and clinical differentiators, and develop value-based positioning statements that support pricing strategy and sales enablement. This skill transforms product knowledge into actionable competitive intelligence and positioning documents tailored for product managers, sales teams, and executive stakeholders in vision care.
by kanta13jp1
You can read PDFs directly from disk, extract text and embedded content, identify document structure (text-based vs. scanned), list images and attachments, and choose the right extraction strategy based on document type. This skill helps you understand what's in a PDF before processing it, diagnose extraction issues, and pull specific content like tables, forms, and embedded files.
by seifbenayed
You can audit healthcare taxonomies and data models against clinical standards like SNOMED CT, ICD, and HL7 to identify gaps, overlaps, and semantic inconsistencies. Claude analyzes your taxonomy structure, suggests remediation strategies, and generates compliance reports. This ensures your clinical data is interoperable, standards-compliant, and semantically consistent across systems.
by kanta13jp1
Automate the curation of research datasets by generating standardized metadata, performing compliance verification, and producing quality assessments. This skill standardizes your data documentation process, ensures datasets meet regulatory requirements, and prepares them for repository publication—reducing manual work and improving consistency across your research organization.
by kanta13jp1
You can upload geospatial datasets (shapefiles, GeoJSON, rasters) and receive comprehensive validation reports, metadata standardization recommendations, and ISO 19115 compliance checks. The skill identifies data quality issues like projection mismatches, missing attributes, invalid geometries, and inconsistent coordinate systems, then generates standardized metadata templates ready for data catalogs.
by kanta13jp1