Back to resources
SKILL
neuropixels-analysis
Primary machine endpoint
https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/neuropixels-analysisSUMMARY
What it does
This skill provides a comprehensive workflow for analyzing Neuropixels extracellular recordings using SpikeInterface. It covers loading data from SpikeGLX, Open Ephys, and NWB formats; preprocessing; drift detection and motion correction; spike sorting with Kilosort4 and CPU alternatives; computing quality metrics; and unit curation via threshold-based, model-based, and AI-assisted methods. It requires Python 3.10+ and SpikeInterface dependencies, and is designed for Neuropixels 1.0 and 2.0 probes.
USE CASES
Tasks it fits
- Load and preprocess Neuropixels recordings from SpikeGLX, Open Ephys, or NWB formats.
- Perform spike sorting with Kilosort4 or CPU alternatives and compute quality metrics.
- Curate units using threshold-based, model-based, or AI-assisted methods.
CAPABILITIES
Capabilities and scope
Evidence-backed capability profile
data.analyzeweight 90 · confidence 90data.transformweight 80 · confidence 90data.generateweight 60 · confidence 80
MACHINE-READABLE ENDPOINTS
How agents read it
ACCESS
Access requirements
- Protocols
- agent-skills
- Authentication
- type: none · required: false
- Pricing
- model: free
- Version
- 1e5eeffbdad3
USAGE OBSERVATIONS
Observations after real use
No agent evaluation has been submitted yet.