Data Management Plan (DMP) Creator

Automatically generate draft Data Management and Sharing Plans (DMSP) compliant with NIH 2023 policy requirements and FAIR principles.

Overview

This Skill generates comprehensive Data Management and Sharing Plans (DMSP) that meet NIH's 2023 Final Policy for Data Management and Sharing. The output follows FAIR principles (Findable, Accessible, Interoperable, Reusable) to ensure research data is properly managed and shared.

Requirements

• Python 3.8+
• No external dependencies required (uses standard library only)

Usage

Command Line

python scripts/main.py \
    --project-title "Your Research Project Title" \
    --pi-name "Principal Investigator Name" \
    --data-types "genomic,imaging,clinical" \
    --repository "GEO,Figshare" \
    --output dmsp_draft.md

Interactive Mode

python scripts/main.py --interactive

As a Module

from scripts.main import DMSPCreator

creator = DMSPCreator(
    project_title="Cancer Genomics Study",
    pi_name="Dr. Jane Smith",
    institution="National Cancer Institute",
    data_types=["genomic sequencing", "clinical metadata"],
    estimated_size_gb=500,
    repositories=["dbGaP", "GEO"],
    sharing_timeline="6 months after study completion"
)

dmsp = creator.generate_plan()
creator.save_to_file("dmsp_output.md")

Parameters

NIH DMSP Required Elements

The generated plan addresses all six required elements per NIH policy:

1. Data Type - Types and estimated amount of scientific data
2. Related Tools, Software and/or Code - Tools needed to access/manipulate data
3. Standards - Standards for data/metadata to be applied
4. Data Preservation, Access, and Associated Timelines - Repository selection and sharing timeline
5. Access, Distribution, or Reuse Considerations - Factors affecting subsequent access
6. Oversight of Data Management and Sharing - Plans for compliance monitoring

FAIR Principles Implementation

Findable

• Persistent identifiers (DOIs)
• Rich metadata with standard vocabularies
• Registration in searchable repositories

Accessible

• Standardized communication protocols
• Metadata available even if data is no longer available
• Access procedures clearly documented

Interoperable

• Standard data formats
• Standard terminologies and vocabularies
• Qualified references to other data

Reusable

• Detailed provenance information
• Clear usage licenses
• Domain-relevant community standards

Example Output

The generated DMSP includes:

• Executive summary
• NIH-compliant section headers
• Specific language for data type descriptions
• FAIR-aligned metadata standards
• Repository recommendations
• Timeline for data sharing
• Access control procedures
• Roles and responsibilities

References

• NIH Data Management and Sharing Policy
• NIH DMSP Template
• FAIR Principles

License

MIT License - See project root for details.

Risk Assessment

Security Checklist

• No hardcoded credentials or API keys
• No unauthorized file system access (../)
• Output does not expose sensitive information
• Prompt injection protections in place
• Input file paths validated (no ../ traversal)
• Output directory restricted to workspace
• Script execution in sandboxed environment
• Error messages sanitized (no stack traces exposed)
• Dependencies audited

Prerequisites

# Python dependencies
pip install -r requirements.txt

Evaluation Criteria

Success Metrics

• Successfully executes main functionality
• Output meets quality standards
• Handles edge cases gracefully
• Performance is acceptable

Test Cases

1. Basic Functionality: Standard input → Expected output
2. Edge Case: Invalid input → Graceful error handling
3. Performance: Large dataset → Acceptable processing time

Lifecycle Status

• Current Stage: Draft
• Next Review Date: 2026-03-06
• Known Issues: None
• Planned Improvements:
  • Performance optimization
  • Additional feature support