dataset-audit

Community

Ground-truth auditing of medical imaging datasets.

AuthorBraveDistribution
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill outputs ground-truth reports detailing the actual contents of medical imaging datasets, preventing misinterpretations by verifying headers, file types, and documentation.

Core Features & Use Cases

  • Reconciles on-disk contents with official dataset documentation to report modality, dimensionality, views, frames, sensors, and subjects.
  • Produces structured audit results (NIfTI, DICOM, meshes, contours) to support reproducibility and data governance.
  • Use Case: Before a study, audit a dataset directory to confirm available data types and annotations.

Quick Start

Run the audit on a dataset directory to generate a ground-truth report.

Dependency Matrix

Required Modules

nibabelpydicomnumpytrimesh

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: dataset-audit
Download link: https://github.com/BraveDistribution/claude-skills/archive/main.zip#dataset-audit

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.