All skills
openai avatar

/jupyter-notebook

@0ed635a official
by openaiopenai/skills28k stars
1,891

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Use this Skill: https://skilld.dev/gh/openai/skills/jupyter-notebook

This session only. Nothing lands on disk.

referencesquality-checklist.md

≈143 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Quality Checklist

Before delivering a notebook:

  • Run it top-to-bottom at least once (or as much as the environment allows).
  • Ensure early cells set all required state; avoid hidden state from prior runs.
  • Keep outputs tidy. Avoid giant outputs when a short summary works.
  • Prefer small tables, key metrics, or short printouts.
  • Keep the narrative skimmable. Use headings and short bullets, and avoid long paragraphs.
  • Leave helpful TODOs only when necessary, and label them clearly.
  • If execution is not possible, call out the risk and how to validate locally.

Source: SKILL.md on GitHub

1 warning17d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill provides a structured framework for creating Jupyter notebooks using templates and a helper script. It includes security considerations regarding the processing of user-supplied content into executable notebook files and the installation of standard external packages. These processes are managed through bundled templates and local scripts. See the detailed analysis for context.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    10/10 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 0ed635a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Activeupdated 8 months ago
  • Python
  • jupyter
  • notebook
  • ipynb
  • experimentation
  • tutorial
  • analysis
  • exploration

README badge

README badge for openai/skills/jupyter-notebook

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.

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.