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

tcp-skill

Orchestrates BIDS validation and multimodal processing of the Transdiagnostic Connectome Project dataset.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Processing the Transdiagnostic Connectome Project (TCP) dataset requires coordinating BIDS validation, structural MRI, resting-state fMRI, and diffusion MRI pipelines plus phenotype extraction, which is error-prone when done manually across tools. ## Core Features & Use Cases - BIDS Validation: Validates TCP directory structure, modality completeness (T1w, rs-fMRI, dMRI), and generates a compliance report via scripts/validate_tcp.py. - Multimodal Delegation: Delegates sMRI, rs-fMRI, and dMRI processing to dedicated modality skills through a confirmed, numbered execution plan. - Phenotype & QC Integration: Merges diagnostic and RDoC dimensional measures into a phenotype CSV and produces per-subject QC summaries with exclusion lists. - Use Case: A researcher downloads TCP data from the NIMH Data Archive and asks for an end-to-end workflow; the skill validates the BIDS layout, runs all three modality pipelines, and outputs merged phenotype tables and QC exclusion lists under tcp_output/. ## Quick Start Run the TCP skill to validate my BIDS dataset at /data/TCP and process the T1w, resting-state fMRI, and diffusion scans end to end.

Frequently Asked Questions about tcp-skill

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

FAQPage Schema
How do I process the Transdiagnostic Connectome Project dataset end to end?▼

Request the TCP workflow and the skill generates a numbered plan covering BIDS validation, sMRI, rs-fMRI, and dMRI processing. After you confirm with YES or proceed, each step is delegated to the corresponding modality skill and outputs are saved under tcp_output/.

How to validate BIDS structure for TCP neuroimaging data?▼

Run scripts/validate_tcp.py with --input pointing to the BIDS root and --output for the report path. It checks each subject for T1w, task-rest BOLD, and DWI files and writes a CSV compliance report with missing files and warnings.

What modalities does the TCP dataset pipeline support?▼

The pipeline supports T1w structural MRI, resting-state fMRI, and diffusion-weighted imaging from the WashU 3T Siemens scanner. Each modality is delegated to a dedicated skill: smri-skill, fmri-skill, and dwi-skill.

Can I run only BIDS validation without the full TCP pipeline?▼

Yes, for tasks that only ask for validation of local TCP data, the skill skips download and orchestration and runs the narrow path of local discovery, BIDS validation, and report generation. In benchmark mode no confirmation prompt is required.

How does TCP quality control decide which subjects to exclude?▼

The QC script reads fMRIPrep confounds files and computes mean and max framewise displacement per subject. Subjects whose mean FD exceeds the configurable threshold (default 0.3 mm) are flagged with exclusion reasons in the summary CSV.

What are the limitations of the TCP orchestration skill?▼

The skill is orchestration-only and contains no preprocessing implementation; all execution is delegated to modality skills via claw-shell. Its transdiagnostic design also means group comparisons need dimensional rather than categorical analysis handling.

Related Skills

Explore More Education & Research Skills→
xjtulycxjtulyc
33

bids-neuroimaging

Convert raw EEG/MEG/fMRI data into BIDS 1.8 directory layouts with metadata.

Community
Advanced
hiyenwonghiyenwong
2

bridge-neurodivergence-detection

Quantify neural divergence from typical developmental trajectories using graph-regularized modeling and deep generative networks.

Community
Advanced
CUHK-AIM-GroupCUHK-AIM-Group
78

fsl-tool

Orchestrate FSL neuroimaging workflows with installation checks and user-confirmed execution plans.

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

hcp-skill

Orchestrate HCP multimodal processing from data download to modality-specific pipelines.

Official
Advanced