Skip to content
Get packs

NeuroKit2 Physiological Signal Analysis

Guides reproducible ECG, EDA, EEG, PPG and HRV analysis with the NeuroKit2 library, with method-aware validation

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
15 files

What it does

This skill gives an AI agent detailed rules for processing body signals such as ECG heartbeats, skin conductance, breathing, EEG, EMG and PPG using the NeuroKit2 Python toolbox. Once installed, the agent inspects recordings before filtering, pins the NeuroKit2 version, records the sampling rate and units, checks signal quality, and computes heart rate variability only when recording length and beat counts are adequate. It also includes two bounded local command-line scripts for inspecting signals and running an ECG/HRV pipeline, and it explicitly warns against presenting results as medical diagnosis or device validation.

Great for

  • Researchers or students who need a reproducible, documented workflow for physiological time-series analysis
  • Python developers writing code that imports neurokit2 and needs correct current API usage
  • Lab staff who must log preprocessing steps, exclusions and sampling metadata for a study

Skip it if

  • Clinical decisions or patient monitoring: the skill states outputs are research and educational only, not diagnosis or alarms
  • Certifying or validating a medical device or new sensor, since the skill's own checks are synthetic and do not establish empirical validity
  • Analysing identifiable patient data: the skill requires deidentified local files and forbids placing PHI in prompts or logs

Try asking

  • “Inspect this deidentified recording.csv for gaps, flatlines and sampling-rate issues before I filter the ECG and RSP channels”
  • “Process my ECG at 250 Hz with NeuroKit2 0.2.13 and compute time-domain HRV with a logged exclusion summary”
  • “Build a reproducible uv project pinning neurokit2 and check which output columns ecg_process returns”
  • “Review my existing neurokit2 script for unit assumptions and HRV duration requirements”
Step-by-step guide: how to use NeuroKit2 Physiological Signal AnalysisInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    neurokit2.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip neurokit2.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip neurokit2.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • State the sampling rate in Hz and the physical unit of each channel up front, since the skill refuses to infer units from column names
  • Use short recordings only for time-domain HRV; avoid interpreting VLF or frequency measures from short records
  • Commit and review the uv.lock file for any optional feature so the environment is reproducible

What's inside

  • references/bio_module.md
  • references/complexity.md
  • references/ecg_cardiac.md
  • references/eda.md
  • references/eeg.md
  • references/emg.md
  • references/eog.md
  • references/epochs_events.md
  • references/hrv.md
  • references/ppg.md
  • references/rsp.md
  • references/signal_processing.md
  • scripts/_common.py
  • scripts/ecg_hrv_pipeline.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.