Topics
- Python
- jupyter
- notebook
- ipynb
- experimentation
- tutorial
- analysis
- exploration
What it does
Scaffolds clean Jupyter notebooks for experiments and tutorials using a bundled template and helper script. Handles both exploratory analysis and instructional walkthroughs with consistent structure and JSON safety.
Generated from the current SKILL.md.
Frequently asked
What types of notebooks does this skill create?
The skill scaffolds two types: experiment notebooks for exploratory analysis and hypothesis-driven work, and tutorial notebooks for step-by-step instruction. Use the `--kind` flag with the helper script to choose between them.
Do I need to install dependencies to use this skill?
No. The bundled scaffold script uses only the Python standard library. JupyterLab and ipykernel are optional and only needed if you want to run notebooks locally.
How do I create a new notebook with this skill?
Run the bundled `new_notebook.py` helper script with `--kind`, `--title`, and `--out` flags. For example: `uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" --kind experiment --title "Compare prompt variants" --out output/jupyter-notebook/compare-prompt-variants.ipynb`.
Can I edit existing notebooks with this skill?
Yes. The skill includes patterns for refactoring existing notebooks while preserving their intent. Refer to `references/notebook-structure.md` before editing raw JSON to avoid mistakes.
Where should I save the final notebook?
Save final notebooks under `output/jupyter-notebook/` with stable, descriptive filenames. Use `tmp/jupyter-notebook/` for intermediate files and clean them up when done.
Generated from the current SKILL.md. These answers refresh after source changes.