The problem

Manuscript submissions often stall when researchers cannot reconcile conflicting data-sharing requirements from journals, funders, and ethics boards. Scattered records like consent forms, repository drafts, and code scripts make it difficult to prove what can be shared and what must be restricted.

What it does

• Builds a traceable source register from consent forms, ethics approvals, and data inventories.
• Classifies research assets into public, controlled-access, or restricted categories.
• Flags discrepancies between draft availability statements and actual evidence.
• Generates a data and code deposit ledger to track identifiers, licenses, and versions.
• Surfaces gaps in code documentation, such as missing environment lockfiles or local file paths.

Why this beats prompting it yourself

This skill enforces a rigid structure that prevents the LLM from hallucinating compliance or making dangerous legal interpretations. It maintains a strict boundary between data organization and data transformation, ensuring you never accidentally publish sensitive participant information.

Use cases

• Preparing a Data Availability Statement for a high-impact journal submission.
• Organizing evidence for a funder's end-of-grant data-sharing report.
• Drafting a controlled-access procedure for sensitive clinical or ecological data.
• Auditing a research code package for portability and environment documentation.

Known limitations

Does not perform data anonymization, validate live DOIs, or interpret legal contracts. Requires all records to be provided as text or file inputs.