skills.rest
CUHK-AIM-Group
CUHK-AIM-GroupOFFICIAL
Explore all skills by this author →
WebsiteGitHub

cobre-skill

Orchestrates COBRE dataset download, BIDS organization, and sMRI/rs-fMRI processing for schizophrenia research.

89|5|Updated Mar 25, 2026
Search Tags:#neuroimaging#qc#fmri#bids#schizophrenia#cobre#phenotype extraction
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill cobre-skill-cuhk-aim-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cobre-skill
Source: https://github.com/CUHK-AIM-Group/NeuroDiscovery/tree/main/skills/cobre-skill
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroDiscovery --skill cobre-skill-cuhk-aim-group

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Working with the COBRE schizophrenia neuroimaging dataset requires coordinating multiple manual steps: downloading from the FCP/INDI repository, reorganizing raw NIfTI files into BIDS-compliant structure, extracting phenotype data, and running modality-specific processing pipelines. This Skill automates that entire orchestration workflow. ## Core Features & Use Cases - End-to-End Dataset Orchestration: Coordinates download, BIDS staging, and delegation to sMRI and rs-fMRI processing pipelines for all 147 COBRE participants. - BIDS Reorganization: Converts raw COBRE NIfTI files into BIDS-compliant layout with dataset_description.json and participants.tsv generation. - Phenotype Extraction & QC: Merges phenotype tables (diagnosis, demographics, handedness) and generates per-subject QC summaries with exclusion lists based on framewise displacement thresholds. - Use Case: A researcher wants to run schizophrenia classification with BrainGNN on COBRE. This Skill downloads the data, stages it in BIDS format, extracts diagnosis labels, runs fMRIPrep-based QC, and delegates structural and functional processing to the appropriate modality skills. ## Quick Start Ask the agent to download the COBRE dataset, organize it into BIDS format, and run the sMRI and rs-fMRI processing pipelines with QC summaries.

Frequently Asked Questions about cobre-skill

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

FAQPage Schema
How do I download and process the COBRE dataset for schizophrenia research?▼

Use this Skill to run the full COBRE workflow: it downloads data from the FCP/INDI repository, stages raw NIfTI files into BIDS format, and delegates T1w and rs-fMRI processing to the sMRI and fMRI skills. Confirm the generated plan before execution begins.

How to convert COBRE raw NIfTI files to BIDS format?▼

Run the reorganize_cobre.py script with input and output directories. It detects T1w and resting-state BOLD modalities, normalizes subject IDs to sub-NNNNN labels, copies JSON sidecars, and writes dataset_description.json and participants.tsv.

Does COBRE include task-based fMRI data?▼

No, COBRE only contains T1-weighted structural MRI and resting-state fMRI for its 147 participants (72 schizophrenia patients, 75 healthy controls). Task-fMRI is not available in this dataset.

How do I exclude COBRE subjects with high motion from analysis?▼

Run the cobre_qc_summary.py script against fMRIPrep output. It computes mean and max framewise displacement per subject and generates an exclusion list using configurable thresholds (default mean FD 0.3, max FD 5.0).

What are the limitations of the COBRE dataset for classification studies?▼

COBRE has a small sample size of 147 subjects, so cross-validation strategies must account for limited data. It is a single-site dataset from the University of New Mexico, so no site-effect correction is needed, but generalizability is limited.

Related Skills

Explore More Education & Research Skills→
huggingfacehuggingface
78

hf-cli

Manage Hugging Face Hub repositories, models, datasets, and Spaces via CLI.

Official
Intermediate
learningmatter-mitlearningmatter-mit
144

ml-cluster-expansion

Train a Cluster Expansion model for disordered lattice materials using MCP tools.

Official
Advanced
galeepgaleep

bids

Organize, query, validate, and convert neuroscience datasets to BIDS standards.

Community
Advanced
NeuroAIHubNeuroAIHub
34

Neuroimaging Sample Size Calculator

Simulate neuroimaging sample size planning with effect-size maps and pipeline corrections.

Official
Advanced