Plan fMRI GLM, masking, connectome, and ML workflows in Python with Nilearn guidance.
npx skills add https://github.com/MarvinCui/NeuroForge --skill nilearn
Please help me install this Agent Skill. Skill: nilearn Source: https://github.com/MarvinCui/NeuroForge/tree/main/NeuroForge/skills/nilearn Command: npx skills add https://github.com/MarvinCui/NeuroForge --skill nilearn
Nilearn skill helps you plan and reason about fMRI statistical modeling, masking, connectome extraction, and machine-learning workflows from neuroimaging inputs without blindly running heavy processing.
Ask your question and include your fMRI image type (e.g., 4D runs vs derivatives) and what result you need (e.g., a first-level contrast map or a connectivity matrix), and the skill will propose a safe, documentation-driven plan.
High-intent search queries and answers about installing and using this skill.
To plan a first-level fMRI GLM, you need design-matrix planning and contrast interpretation workflows. This skill proposes safe, documentation-driven plans for fMRI statistical modeling, guiding you from 4D run images to first-level contrast maps.
Extracting signals for machine learning requires using maskers to handle ROI and atlas operations. This skill guides you through preparing expected inputs, inspecting image compatibility assumptions, and producing ML-ready feature outputs from neuroimaging data.
Routing fMRIPrep derivatives into Nilearn involves computing connectomes and performing image-level operations. This skill helps you inspect image compatibility and draft safe analysis checks to construct connectivity matrices from your preprocessed neuroimaging inputs.
Yes, you can use Nilearn maskers on both 4D fMRI runs and derivatives. The skill helps you specify your fMRI image type and desired result, then proposes a safe plan while addressing image compatibility assumptions for masking and ROI operations.
Running heavy neuroimaging processing blindly risks image incompatibility and invalid GLM assumptions. This skill avoids blind execution by providing validation-like cautions, documentation routing, and safe analysis checks for NIfTI-based workflows.
MarvinCuiInterpret fMRIPrep derivatives, HTML reports, and confounds for downstream fMRI workflow planning.
travisjneumanDesign machine learning pipelines and statistical analyses for data science workflows.
idanmoradarthasAnalyze and visualize sklearn-compatible model performance with metrics and plots.
xjtulycFit nilearn GLMs for task fMRI and compute contrast maps.
