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

hbn-skill

Orchestrates download, BIDS staging, and multimodal processing of Healthy Brain Network neuroimaging data.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Working with the Healthy Brain Network (HBN) dataset requires coordinating many tedious steps: downloading data from the FCP/INDI repository, reorganizing raw NIfTI files into BIDS-compliant layouts, merging scattered phenotype tables, and running separate pipelines for sMRI, fMRI, dMRI, and EEG. This Skill automates that entire orchestration so researchers can go from raw HBN data to analysis-ready outputs without manual file wrangling. ## Core Features & Use Cases - BIDS Staging: Converts raw HBN subject directories (NDAR-format IDs) into BIDS-compliant structures with modality routing for T1w, T2w, dMRI, rs-fMRI, task-fMRI, and EEG, plus dataset_description.json and participants.tsv generation. - Phenotype Extraction: Merges HBN phenotype tables (psychiatric, behavioral, cognitive, genetics, actigraphy) and filters them against imaging subject IDs. - QC Summaries: Generates per-subject quality control reports from fMRIPrep confounds with framewise displacement thresholds and exclusion lists. - Use Case: A researcher downloads the HBN cohort and needs a BIDS-organized dataset with merged phenotype data and motion-based QC exclusions before running connectivity analysis. This Skill coordinates the full workflow, delegating modality processing to specialized pipeline skills. ## Quick Start Ask the agent to download the HBN dataset, reorganize it into BIDS format, and run the multimodal processing pipeline with phenotype extraction and QC summaries.

Frequently Asked Questions about hbn-skill

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

FAQPage Schema
How do I convert HBN raw data to BIDS format?▼

Run the reorganize_hbn.py script with --input pointing to the raw HBN directory and --output for the BIDS destination. It normalizes NDAR subject IDs to sub- labels, detects sessions, routes modalities to anat/func/dwi/eeg folders, and writes dataset_description.json and participants.tsv. Use --dry-run to preview first.

How do I merge HBN phenotype tables with imaging subject IDs?▼

Use the extract_hbn_phenotype.py script with --phenotype-dir pointing to the CSV/TSV phenotype files and --imaging-ids pointing to the BIDS participants.tsv. It normalizes column names, merges tables on subject_id, and filters rows to subjects with imaging data.

What modalities does the Healthy Brain Network dataset include?▼

HBN includes T1w and T2w structural MRI, diffusion MRI, resting-state and task fMRI, and EEG recordings, plus phenotype data covering psychiatric, behavioral, cognitive, lifestyle, genetics, and actigraphy measures. Not all subjects have all modalities since data is released in waves.

How is motion-based QC exclusion done for HBN fMRI data?▼

The hbn_qc_summary.py script scans fMRIPrep confounds files for framewise displacement values and computes per-subject mean and max FD. Subjects exceeding the mean FD threshold (default 0.3) or max FD threshold (default 5.0) are flagged in an exclusion list CSV.

Does the HBN pipeline require downloading data before BIDS staging?▼

No. If raw HBN NIfTI files already exist locally, the download stage can be skipped and the narrow staging path used directly. The reorganize script works on any local HBN-style subject folder structure without requiring a fresh download.

What are the limitations of automated HBN data organization?▼

HBN is a pediatric cohort aged 5-21, so age-appropriate processing parameters may be needed downstream. Files with unrecognized modality naming are skipped and reported as failures, and the orchestration layer delegates actual preprocessing to separate modality skills rather than performing it directly.

Related Skills

Explore More Education & Research Skills→
novuhqnovuhq
39.7k

nv-worktree-cleanup

Audits git worktrees and removes merged, missing, or confirmed stale entries with their branches.

Official
Intermediate
NeuroAIHubNeuroAIHub
269

fmriprep

Execute containerized BIDS-App fMRI preprocessing with motion correction and anatomical registration.

Official
Advanced
CUHK-AIM-GroupCUHK-AIM-Group
78

fmriprep-tool

Generate and execute fMRIPrep preprocessing plans for BIDS datasets.

Official
Advanced
crazymsncrazymsn
22

bids

Organize neuroscience datasets into BIDS-compliant directory structures.

Community
Advanced