NeuroKit2 (Claude Skill)

Claude skill wrapping the NeuroKit2 biosignal processing toolkit — analysis pipelines for cardiovascular, neural, electrodermal, respiratory, muscle, and eye-movement signals.


Type	Claude Skill
Supplier	K-Dense Inc. (wraps the MIT-licensed NeuroKit2 library)
Availability	GA — distributed with the K-Dense marketplace at v2.27.0
Pricing	Free / OSS
Capabilities	Read/Write — local computation on user-supplied physiological recordings

How to install

Also packaged in the SciAgent-Skills collection (jaechang-hits (community OSS, CC BY 4.0)): clone jaechang-hits/SciAgent-Skills and run /plugin install sciagent-skills in Claude Code (or copy skills/scientific-computing/neurokit2 into ~/.claude/skills/).
Claude Code / Claude.ai — Skills CLI (recommended):
```
npx skills add K-Dense-AI/scientific-agent-skills
```
Installs the K-Dense collection; enable the neurokit2 skill when prompted (also works in Cursor/Codex via the Agent Skills spec; requires Node ≥ 18).

Claude Code / Claude Desktop — manual clone:

git clone https://github.com/K-Dense-AI/scientific-agent-skills
cp -r scientific-agent-skills/skills/neurokit2 ~/.claude/skills/
pip install neurokit2

What it does

ECG: R-peak detection, HRV (time / frequency / non-linear domain)
EEG: bandpower, microstates, complexity measures
EDA: skin-conductance response decomposition
RSP: respiration rate, RSA
PPG, EMG, EOG processing
Multi-modal event-related analysis (nk.events_find, nk.epochs_create, nk.events_plot)
Signal cleaning helpers usable upstream of fMRI connectivity analyses

Primary use cases: HRV studies, EEG feature extraction, biosignal QC, multi-modal psychophysiology, resting-state fMRI nuisance regression.

Notes

Pure Python; pairs with the BIDS skill for organizing the raw signals beforehand. Cite Makowski et al. 2021 (Behavior Research Methods) when publishing.

Sources

Installed this tool?

Share feedback — install path, OS, errors, workarounds. The form opens with this tool pre-selected and a link back to this page.