Neurokit

What it does

When your agent uses it

• You need to clean
• Extract physiological features for HRV
• Event-related responses
• Complexity metrics

Example prompts

• “/neurokit”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Run end-to-end ECG/PPG pipelines (cleaning → peak detection → feature extraction) for cardiovascular monitoring and HRV.
2. 2Compute HRV metrics (time/frequency/nonlinear) for autonomic nervous system assessment in resting-state or continuous recordings.
3. 3Analyze EEG for band power, microstates, and complexity measures in cognitive/neuroscience experiments.
4. 4Decompose EDA into tonic/phasic components and quantify SCRs for arousal/stress and psychophysiological paradigms.
5. 5Perform multimodal biosignal processing (e.g., ECG + RSP + EDA + EMG) with unified outputs for integrated analyses.

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Neurokit loads about 1.8k tokens when it runs, and up to ~47k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 464 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~61

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~47k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 464 words, ~1,780 tokens.

name

neurokit

description

Comprehensive biosignal processing for ECG/PPG/EEG/EDA/RSP/EMG/EOG; use when you need to clean, segment, and extract physiological features for HRV, event-related responses, complexity metrics, or multimodal psychophysiology pipelines.

license

MIT

author

AIPOCH

uv pip install neurokit2

uv pip install https://github.com/neuropsychology/NeuroKit/zipball/dev

import neurokit2 as nk
import numpy as np

# -----------------------------
# 1) Simulate example signals
# -----------------------------
sampling_rate = 1000
duration = 60  # seconds

ecg = nk.ecg_simulate(duration=duration, sampling_rate=sampling_rate, heart_rate=70)
rsp = nk.rsp_simulate(duration=duration, sampling_rate=sampling_rate, respiratory_rate=15)
eda = nk.eda_simulate(duration=duration, sampling_rate=sampling_rate, scr_number=8)

# Create a simple trigger channel with 5 events
trigger = np.zeros(len(ecg))
event_times_s = [10, 20, 30, 40, 50]
for t in event_times_s:
    trigger[int(t * sampling_rate)] = 1.0

# -----------------------------
# 2) ECG processing + HRV
# -----------------------------
ecg_signals, ecg_info = nk.ecg_process(ecg, sampling_rate=sampling_rate)
rpeaks = ecg_info["ECG_R_Peaks"]
hrv = nk.hrv(rpeaks, sampling_rate=sampling_rate)

# -----------------------------
# 3) Multimodal processing
# -----------------------------
bio_signals, bio_info = nk.bio_process(
    ecg=ecg,
    rsp=rsp,
    eda=eda,
    sampling_rate=sampling_rate
)
bio_results = nk.bio_analyze(bio_signals, sampling_rate=sampling_rate)

# -----------------------------
# 4) Event-related epoching
# -----------------------------
events = nk.events_find(trigger, threshold=0.5)
epochs = nk.epochs_create(
    bio_signals,
    events,
    sampling_rate=sampling_rate,
    epochs_start=-0.5,
    epochs_end=2.0
)
grand_average = nk.epochs_average(epochs)

# -----------------------------
# 5) Minimal outputs
# -----------------------------
print("HRV (first columns):")
print(hrv.iloc[:, :8].round(3))

print("\nBio analysis keys:", list(bio_results.keys())[:10])
print("Grand average shape:", grand_average.shape)

filtered = nk.signal_filter(x, sampling_rate=1000, lowcut=0.5, highcut=40)
psd = nk.signal_psd(filtered, sampling_rate=1000)

indices = nk.complexity(x, sampling_rate=1000)
apen = nk.entropy_approximate(x)
dfa = nk.fractal_dfa(x)

© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (references) in scientific-skills/Data Analysis/neurokit2 of aipoch/medical-research-skills.

• SKILL.md
• neurokit2_audit_result_v1.json
• 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

Open the folder on GitHubat commit 686e09d