Validate brain extraction / skull stripping results. Generate a QC PNG mosaic, perform AI visual evaluation against a structured rubric, and produce a matching human verification form for reliability comparison. Invoke after brain extraction completes, or standalone on any existing brain mask with "check brain extraction", "QC the mask", "validate skull strip", "review brain extraction", "evaluate the mask", or "brain-extraction-qc". Also invoke when the user references a file ending in `_brain.nii.gz`, `_mask.nii.gz`, or `_brain_mask.nii.gz` and asks to check, review, or validate it.
Perform brain extraction (skull stripping) on an MRI image in a portable neuroimaging workflow. Invoke on "skull strip", "brain extraction", "remove skull", "strip the brain", "BET", "antsBrainExtraction", "mri_synthstrip", "HD-BET", "3dSkullStrip", "synthstrip", "brain mask", "create brain mask", "whole brain mask", "mask the brain", "strip the skull", or "brain-extraction". Also invoke when the user wants to isolate brain tissue, remove non-brain voxels, or prepare a brain mask for downstream registration or segmentation.
Validate brain extraction / skull stripping results. Generate a QC PNG mosaic, perform AI visual evaluation against a structured rubric, and produce a matching human verification form for reliability comparison. Invoke after brain extraction completes, or standalone on any existing brain mask with "check brain extraction", "QC the mask", "validate skull strip", "review brain extraction", "evaluate the mask", or "brain-extraction-qc". Also invoke when the user references a file ending in `_brain.nii.gz`, `_mask.nii.gz`, or `_brain_mask.nii.gz` and asks to check, review, or validate it.
Perform brain extraction (skull stripping) on an MRI image in the Neurodesk environment. Invoke on "skull strip", "brain extraction", "remove skull", "strip the brain", "BET", "antsBrainExtraction", "mri_synthstrip", "HD-BET", "3dSkullStrip", "synthstrip", "brain mask", "create brain mask", "whole brain mask", "mask the brain", "strip the skull", or "brain-extraction". Also invoke when the user says they want to isolate brain tissue, remove non-brain voxels, or prepare a brain mask for downstream registration or segmentation.
Auto-invoke when the user wants to obtain a copy of a dataset from a URL or path, install a dataset, add a nested subdataset, or link external data as input to a project. Trigger on "clone a dataset", "get a copy of", "install dataset", "add subdataset", "link this data as input", or /datalad-clone. Use instead of `git clone` when working with DataLad datasets. Do NOT trigger for plain git repos without DataLad context.
Auto-invoke when about to execute a command inside a container (Singularity .sif file, Apptainer image, Docker image) that produces output files inside a DataLad dataset. Trigger on "run in container", "run with Singularity", "run with Apptainer", "run with Docker", "containerized analysis", "remove a container", "unregister container", or /datalad-container-run. Records both the command and the container image in dataset provenance. Do NOT trigger for bare datalad run commands without a container — use datalad-run for those.
Auto-invoke when the user needs to set up credentials for a DataLad remote, gets an authentication error pushing to GitHub/OSF/S3/Figshare, or asks how to store tokens for DataLad siblings. Trigger on "set up credentials", "configure token", "authentication error", "credential error", "how do I authenticate", "store my GitHub token for DataLad", "OSF token", "S3 credentials", or /datalad-credentials. Do NOT trigger for general SSH key setup or non-DataLad credential management.
Auto-invoke when a user cannot open a file because content is missing or shows as a broken symlink, wants to download annexed file content, fetch data from a sibling, or initialize an absent subdataset. Trigger on "get this file", "download content", "fetch data", "retrieve", "I can't open this file", "content missing", "file is empty", "broken symlink", or /datalad-get. Do NOT trigger for plain file copies or downloads unrelated to DataLad datasets.