mnd-skill

Orchestrates BIDS validation, multimodal fMRI processing, and phenotype extraction for the MND dataset.

89|5|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill mnd-skill-cuhk-aim-group
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mnd-skill
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/mnd-skill
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill mnd-skill-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, and includes scripts (resource) components.

What problem does it solve? Processing the Motor Neuron Disease (MND) dataset from OpenNeuro ds005874 requires coordinating BIDS validation, structural and functional MRI pipelines, clinical phenotype extraction, and quality control across multiple tools, which is error-prone when done manually. ## Core Features & Use Cases - BIDS Validation: Checks MND dataset structure for modality completeness (rs-fMRI and motor task-fMRI) and generates a per-subject compliance report. - Multimodal Processing Delegation: Delegates structural MRI work to smri-skill and resting-state/task fMRI analysis to fmri-skill through a confirmed, numbered execution plan. - Phenotype Extraction and QC: Merges diagnosis and clinical measures (ALSFRS-R, disease duration, FVC) into a single CSV and produces per-subject QC summaries with motion-based exclusion lists. - Use Case: A researcher downloads OpenNeuro ds005874 and asks to run the full MND pipeline; the skill validates the BIDS layout, processes both fMRI modalities, merges clinical phenotypes, and outputs a QC report with excluded subjects. ## Quick Start Run the MND multimodal pipeline on my local BIDS dataset at /data/ds005874, including validation, fMRI processing, phenotype extraction, and QC.

Frequently Asked Questions about mnd-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I process the MND dataset from OpenNeuro ds005874?

Provide the path to your local BIDS-formatted MND data and request the MND pipeline. The skill validates the BIDS structure, delegates sMRI and fMRI processing to modality skills, extracts clinical phenotypes, and writes all outputs to an mnd_output directory.

How to validate BIDS structure for MND fMRI data?

Run scripts/validate_mnd.py with --input pointing to the BIDS directory and --output for the report CSV. It checks each subject for resting-state and motor task BOLD files and reports missing modalities per subject.

What modalities does the MND dataset include?

The dataset contains 59 participants with resting-state fMRI (eyes open/closed, ~8 min) and motor task fMRI (finger tapping, hand grip, ~5 min). Structural T1w is optional, and the data is BIDS-compliant under a CC0 license.

Does the MND pipeline extract clinical measures like ALSFRS-R?

Yes, scripts/extract_mnd_phenotype.py merges diagnosis, ALSFRS-R scores, disease duration, onset details, and FVC from phenotype CSV/TSV files into one table. It can filter results to match your imaging subject list.

What are the limitations of analyzing the MND dataset?

The cohort is small at 59 participants, so statistical power for group comparisons may be limited. Case-control matching should be verified before analysis, and subjects with mean framewise displacement above 0.3 mm are flagged for exclusion by default.