nilearn-tool

Extract ROI time series and connectivity matrices from preprocessed BOLD data.

78|3|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/CUHK-AIM-Group/NeuroClaw --skill nilearn-tool
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nilearn-tool
Source: https://github.com/CUHK-AIM-Group/NeuroClaw/tree/main/skills/nilearn-tool
Command: npx skills add https://github.com/CUHK-AIM-Group/NeuroClaw --skill nilearn-tool

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nibabel, numpy, pandas, nilearn, scikit-learn, scipy, and includes scripts (resource) components.

What problem does it solve?

Provides a reusable base/tool skill implementing concrete Nilearn workflows to turn preprocessed BOLD data into ROI time series, functional connectivity matrices, and optional GLM outputs, enabling researchers to build neuroimaging pipelines without rewriting core routines.

Core Features & Use Cases

  • ROI time series extraction from atlas/parcellation and standardization/detrending for downstream analysis
  • ROI-to-ROI connectivity computation and seed-based connectivity mapping
  • Optional first-/second-level GLM integration and basic model outputs
  • Curated reference snippets and a wrapper CLI routed through claw-shell for deterministic, reproducible results
  • Guidance on using curated snippets when implementing Nilearn-based workflows in larger experiments

Quick Start

Run the Nilearn-based tool to extract ROI timeseries and connectivity from a preprocessed BOLD image using a given atlas and output directory.

Frequently Asked Questions about nilearn-tool

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

FAQPage Schema
How do I extract ROI time series from preprocessed BOLD Nifti images using Nilearn?

To extract ROI time series from preprocessed BOLD Nifti images, this Skill provides reusable Nilearn workflows that apply an atlas parcellation, standardize signals, and detrend data for downstream connectivity analysis.

Can I compute ROI-to-ROI functional connectivity matrices from fMRI data without writing custom Nilearn code?

Yes, you can compute ROI-to-ROI functional connectivity matrices from fMRI data without custom code by using the Skill's built-in Nilearn wrapper interface and curated reference snippets for deterministic results.

Does this Skill support first-level and second-level GLM analysis for fMRI?

This Skill supports optional first-level and second-level GLM integration for fMRI, providing basic model outputs through curated Nilearn workflows within a reproducible wrapper interface.

How does the wrapper interface handle reproducibility for Nilearn connectome and GLM workflows?

The wrapper interface handles reproducibility for Nilearn connectome and GLM workflows by routing deterministic CLI commands through claw-shell, utilizing curated snippets to ensure consistent neuroimaging feature extraction.

What is the best way to standardize and detrend ROI time series for functional connectivity analysis?

The best way to standardize and detrend ROI time series for functional connectivity analysis is using this Skill's implemented Nilearn workflows, which automatically preprocess extracted signals before generating connectome matrices.

Do I need preprocessed BOLD data and a specific atlas to start extracting functional connectivity?

Yes, you need preprocessed BOLD data and a defined atlas or parcellation as inputs to start extracting functional connectivity and ROI time series through the provided Nilearn-based workflows.