neuroforge-skills

Brian2 skill for spiking neural network simulation with equation-based neuron models, synapses and plasticity, monitors, runtime and cpp_standalone execution, and multicompartment morphology workflows. Use when working with brian2.NeuronGroup, brian2.Synapses, brian2.SpikeMonitor, brian2.StateMonitor, brian2.PopulationRateMonitor, brian2.PoissonGroup, brian2.TimedArray, brian2.set_device, brian2.SpatialNeuron, or brian2.Morphology; keywords: STDP, event-driven synapses, Poisson input, code generation, standalone C++, morphology.

MNE-Python for MEG/EEG/iEEG/fNIRS analysis pipelines, from loading raw signals to epoching, preprocessing, time-frequency analysis, inverse modeling, and reporting. Use when working with mne.create_info, mne.io.RawArray, mne.Epochs, mne.compute_covariance, mne.preprocessing.ICA, mne.time_frequency.psd_array_welch, mne.make_sphere_model, mne.Report, sensor/source-space workflows, or electrophysiology quality control.

Nilearn skill for neuroimaging ML workflows across datasets, image transforms, maskers, GLM, decoding, connectomes, plotting, surface pipelines, and BIDS/fMRIPrep interfaces using source-verified API signatures and docs-backed usage patterns. Use when working with nilearn.datasets, nilearn.image, nilearn.maskers, nilearn.glm, nilearn.decoding, nilearn.connectome, nilearn.plotting, nilearn.surface, or nilearn.interfaces; keywords: fMRI, Niimg-like, NiftiMasker, FirstLevelModel, Decoder, ConnectivityMeasure, plot_stat_map, view_img, vol_to_surf, load_confounds, first_level_from_bids.

pyNIBS skill for non-invasive brain stimulation (TMS/NIBS) analysis workflows including subject/session containers, HDF5 mesh I/O, ROI structures, stimulation optimization, nonlinear regression mapping, and experiment import/cleanup utilities. Use when working with pynibs.subject, pynibs.hdf5_io, pynibs.mesh, pynibs.roi, pynibs.optimization, pynibs.regression, pynibs.expio, or dosing utilities; keywords: TMS, e-field, coil placement, MEP, SimNIBS, ROI, HDF5, cortical mapping.

Unified extracellular electrophysiology workflows for spike sorting, preprocessing, postprocessing, metrics, curation, and visualization. Use when working with Recording/Sorting objects, building SortingAnalyzer pipelines, running sorters, comparing sortings to ground truth, and applying automated/manual curation in SpikeInterface. Keywords: generate_ground_truth_recording, NumpyRecording, load_extractor, create_sorting_analyzer, quality_metrics, run_sorter, compare_sorter_to_ground_truth, apply_curation, threshold_metrics_label_units, plot_traces.