Skip to main content
skill CX Codex

jupyter — Claude Code skill: what it does, how to install

Read, edit, run, and convert Jupyter .ipynb notebooks programmatically using Python and jupyter nbconvert CLI commands.

MIT 140 installs ★ 185 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add OpenHands/extensions --skill jupyter -a claude-code
Open on GitHub

What jupyter does

Jupyter notebooks are structured JSON files. This skill guides the agent to inspect and edit cell sources directly with Python's standard json module. It avoids opening a browser interface when modifying code or clearing outputs and execution_count before committing to version control.

For execution and file conversion, the instructions rely on jupyter nbconvert. The agent can run notebooks in place or export them to Python scripts, HTML, and Markdown. It also includes commands for searching code inside notebooks using grep or PowerShell Select-String.

Execution and format conversion require jupyter nbconvert to be installed in your environment. Without that CLI tool, the agent can only read or edit the notebook JSON.

What it helps with

  • clear code cell outputs and execution counts before committing
  • execute .ipynb notebooks in place via CLI
  • convert Jupyter notebooks to Python scripts, Markdown, or HTML
  • search text and code across notebook files using grep or PowerShell

Example prompts for the agent

  • Clear all cell outputs in notebook.ipynb
  • Execute notebook.ipynb in place using jupyter nbconvert
  • Convert data_pipeline.ipynb to a Python script

How to install jupyter

1Skills CLI (Vercel)

npx skills add OpenHands/extensions --skill jupyter -a claude-code

2Manually: put the files in place

~/.claude/skills/jupyter/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/jupyter/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about jupyter

How to install jupyter in Claude Code?

Run npx skills add OpenHands/extensions --skill jupyter -a claude-code. The skill definition will be added to ~/.claude/skills/jupyter/SKILL.md.

What does the jupyter skill do?

It teaches coding assistants how to handle .ipynb files programmatically. It covers cell editing with Python json, clearing outputs, searching code, and running conversions with nbconvert.

What dependencies are required?

Editing JSON cells works with Python's standard library. Running notebooks or converting them to Markdown, HTML, and .py scripts requires the jupyter nbconvert CLI tool.

Source text

SKILL.md · MIT
---
name: jupyter
description: Read, modify, execute, and convert Jupyter notebooks programmatically. Use when working with .ipynb files for data science workflows, including editing cells, clearing outputs, or converting to other formats.
triggers:
- ipynb
- jupyter
---

# Jupyter Notebook Guide

Notebooks are JSON files. Cells are in `nb['cells']`, each has `source` (list of strings) and `cell_type` ('code', 'markdown', or 'raw').

## Modifying Notebooks
```python
import json
with open('notebook.ipynb') as f:
    nb = json.load(f)
# Modify nb['cells'][i]['source'], then:
with open('notebook.ipynb', 'w') as f:
    json.dump(nb, f, indent=1)
```

## Executing & Converting
```bash
jupyter nbconvert --to notebook --execute --inplace notebook.ipynb  # Execute in place
jupyter nbconvert --to html notebook.ipynb      # Convert to HTML
jupyter nbconvert --to script notebook.ipynb    # Convert to Python
jupyter nbconvert --to markdown notebook.ipynb  # Convert to Markdown
```

## Finding Code
```bash
grep -n "search_term" notebook.ipynb
```

PowerShell equivalent:

```powershell
Select-String -Path notebook.ipynb -Pattern "search_term"
```

## Cell Structure
```python
# Code cell
{"cell_type": "code", "execution_count": None, "metadata": {}, "outputs": [], "source": ["code\n"]}
# Markdown cell
{"cell_type": "markdown", "metadata": {}, "source": ["# Title\n"]}
```

## Clear Outputs
```python
for cell in nb['cells']:
    if cell['cell_type'] == 'code':
        cell['outputs'] = []
        cell['execution_count'] = None
```

© OpenHands · MIT · OpenHands/extensions

Similar skills

All skills for Data and databases →

From the same set6

Project sponsors

Companies that keep this analytics open