pyMEA-codegen

Generates Jupyter notebooks with pyMEA code for MEA data analysis from natural language.

1|Updated Mar 16, 2023
One-click install
npx skills add https://github.com/kkito0726/MEA_modules --skill pymea-codegen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pyMEA-codegen
Source: https://github.com/kkito0726/MEA_modules/tree/main/.claude/skills/pyMEA-codegen
Command: npx skills add https://github.com/kkito0726/MEA_modules --skill pymea-codegen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates the generation of MEA data analysis code in a Jupyter Notebook using the pyMEA library, enabling researchers to convert natural language requirements into runnable analysis scripts without manual, repetitive coding.

Core Features & Use Cases

  • Automated MEA analysis code generation that reads .hed/.bio data, performs peak detection, plots waveforms, computes ISI and FPD, estimates conduction velocity, and creates color maps and videos.
  • Supports both cardiac and neural MEA workflows, with guidance on API usage and notebook organization for reproducibility.
  • Use Case: A researcher describes the desired workflow in natural language and receives a ready-to-run Jupyter Notebook that encapsulates data loading, processing, visualization, and export.

Quick Start

Provide a natural language request describing the MEA analysis you want, and the skill will generate corresponding PyMEA code in a Jupyter Notebook.

Frequently Asked Questions about pyMEA-codegen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate Jupyter notebook code for MEA data analysis from natural language?

MEA data analysis code generation translates natural language specifications into runnable Jupyter Notebook scripts. You describe the desired workflow, and it automatically produces PyMEA code to load data, detect peaks, and plot waveforms.

Can I compute ISI, FPD, and conduction velocity from .hed and .bio files in a Jupyter notebook?

Yes, you can compute ISI, FPD, and conduction velocity from .hed and .bio files. The generated Jupyter notebook uses the pyMEA library to load the data and automatically apply these specific cardiac and neural analysis metrics.

What is the best way to automate peak detection and waveform plotting for multi-electrode array data?

Automating peak detection and waveform plotting for multi-electrode array data is done by specifying your requirements in natural language. The skill generates a ready-to-run Jupyter Notebook that encapsulates the entire pyMEA processing and visualization workflow.

Do I need the pyMEA library to visualize color maps and conduction velocity for cardiac MEA workflows?

Yes, the pyMEA library is required to visualize color maps and conduction velocity for cardiac MEA workflows. The generated analysis scripts depend on PyMEA to process the .hed/.bio data and render the visual outputs.

How do I customize electrode distance and analysis parameters for my MEA data processing script?

You customize electrode distance and analysis parameters by including these specific details in your natural language request. The skill uses these specifications to tailor the generated Jupyter Notebook for your particular MEA dataset.

Are there limitations when generating reproducible MEA analysis code for neural and cardiac workflows?

Limitations include dependency on the pyMEA library and support restricted to .hed/.bio data formats. The generated code focuses on standard neural and cardiac MEA workflows like peak detection, ISI, and FPD computation.