Generated banner for Jupyter Notebook
Generated logo for Jupyter Notebook

Jupyter Notebook

OpenAIOfficialPublished by OpenAI

  • Skill
  • Content generator
  • Data and AI
  • Apache-2.0
  • Low risk
  • Has scripts

From the author

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.
— the description by OpenAI

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The Jupyter Notebook skill provides a standardized approach to generating and maintaining .ipynb files. By utilizing bundled templates and a dedicated helper script, it ensures that notebooks are structured consistently, reducing errors associated with manual JSON editing. The skill supports two primary modes: experiments, which focus on hypothesis-driven analysis, and tutorials, which prioritize instructional flow. It emphasizes reproducibility, clear documentation, and logical cell organization to ensure that notebooks remain readable and functional for others.

What it does

  • Generates new Jupyter notebooks using predefined experiment or tutorial templates.
  • Provides a helper script to scaffold notebook files without manual JSON authoring.
  • Offers structured patterns for exploratory data analysis and instructional walkthroughs.
  • Guides the refactoring of existing notebooks to improve readability and reproducibility.
  • Includes a quality checklist for validating notebook structure and content.
  • Supports safe, targeted editing of notebook cells to preserve intent.

When to use it

  • When you need to start a new data experiment or exploratory analysis project.
  • When creating educational content or step-by-step tutorials in notebook format.
  • When converting rough scripts or notes into a clean, shareable notebook.
  • When refactoring an existing notebook to make it more skimmable and reproducible.

Advantages

  • Ensures consistent notebook structure through template-based generation.
  • Reduces manual errors by automating the creation of notebook JSON.
  • Promotes best practices for reproducibility and documentation.
  • Provides clear, distinct patterns for different notebook use cases.

Usage examples

“Create a new notebook for an experiment comparing different prompt variants.”
The agent uses the helper script to generate a new .ipynb file based on the experiment template, pre-configured with sections for objectives, setup, and results.
“Start a tutorial notebook about how to use embeddings.”
The agent scaffolds a tutorial-style notebook, providing a structured layout suitable for step-by-step instructional content.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/openai/jupyter-notebook/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip jupyter-notebook.zip -d .agents/skills

Documentation by OpenAI

Jupyter Notebook Skill

Create clean, reproducible Jupyter notebooks for two primary modes:

  • Experiments and exploratory analysis

  • Tutorials and teaching-oriented walkthroughs

Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.

When to use

  • Create a new .ipynb notebook from scratch.

  • Convert rough notes or scripts into a structured notebook.

  • Refactor an existing notebook to be more reproducible and skimmable.

  • Build experiments or tutorials that will be read or re-run by other people.

Decision tree

  • If the request is exploratory, analytical, or hypothesis-driven, choose experiment.

  • If the request is instructional, step-by-step, or audience-specific, choose tutorial.

  • If editing an existing notebook, treat it as a refactor: preserve intent and improve structure.

Skill path (set once)

export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export JUPYTER_NOTEBOOK_CLI="$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py"

User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).

Workflow

  1. Lock the intent. Identify the notebook kind: experiment or tutorial. Capture the objective, audience, and what "done" looks like.

  2. Scaffold from the template. Use the helper script to avoid hand-authoring raw notebook JSON.

uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" \
  --kind experiment \
  --title "Compare prompt variants" \
  --out output/jupyter-notebook/compare-prompt-variants.ipynb
uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" \
  --kind tutorial \
  --title "Intro to embeddings" \
  --out output/jupyter-notebook/intro-to-embeddings.ipynb
  1. Fill the notebook with small, runnable steps. Keep each code cell focused on one step. Add short markdown cells that explain the purpose and expected result. Avoid large, noisy outputs when a short summary works.

  2. Apply the right pattern. For experiments, follow references/experiment-patterns.md. For tutorials, follow references/tutorial-patterns.md.

  3. Edit safely when working with existing notebooks. Preserve the notebook structure; avoid reordering cells unless it improves the top-to-bottom story. Prefer targeted edits over full rewrites. If you must edit raw JSON, review references/notebook-structure.md first.

  4. Validate the result. Run the notebook top-to-bottom when the environment allows. If execution is not possible, say so explicitly and call out how to validate locally. Use the final pass checklist in references/quality-checklist.md.

Templates and helper script

  • Templates live in assets/experiment-template.ipynb and assets/tutorial-template.ipynb.

  • The helper script loads a template, updates the title cell, and writes a notebook.

Script path:

  • $JUPYTER_NOTEBOOK_CLI (installed default: $CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py)

Temp and output conventions

  • Use tmp/jupyter-notebook/ for intermediate files; delete when done.

  • Write final artifacts under output/jupyter-notebook/ when working in this repo.

  • Use stable, descriptive filenames (for example, ablation-temperature.ipynb).

Dependencies (install only when needed)

Prefer uv for dependency management.

Optional Python packages for local notebook execution:

uv pip install jupyterlab ipykernel

The bundled scaffold script uses only the Python standard library and does not require extra dependencies.

Environment

No required environment variables.

Reference map

  • references/experiment-patterns.md: experiment structure and heuristics.

  • references/tutorial-patterns.md: tutorial structure and teaching flow.

  • references/notebook-structure.md: notebook JSON shape and safe editing rules.

  • references/quality-checklist.md: final validation checklist.

Files

scripts/new_notebook.py

from __future__ import annotations

import argparse
import json
import re
from pathlib import Path
from typing import Any


def slugify(text: str) -> str:
    lowered = text.strip().lower()
    cleaned = re.sub(r"[^a-z0-9]+", "-", lowered)
    collapsed = re.sub(r"-+", "-", cleaned).strip("-")
    return collapsed or "notebook"


def find_repo_root(start: Path) -> Path:
    for candidate in (start, *start.parents):
        if (candidate / ".git").exists():
            return candidate
    return start


def load_template(skill_dir: Path, kind: str) -> dict[str, Any]:
    asset_name = "experiment-template.ipynb" if kind == "experiment" else "tutorial-template.ipynb"
    template_path = skill_dir / "assets" / asset_name
    if not template_path.exists():
        raise SystemExit(f"Missing template: {template_path}")
    with template_path.open("r", encoding="utf-8") as f:
        data = json.load(f)
    if not isinstance(data, dict):
        raise SystemExit(f"Unexpected template shape: {template_path}")
    return data


def update_title(notebook: dict[str, Any], kind: str, title: str) -> None:
    prefix = "Experiment" if kind == "experiment" else "Tutorial"
    expected = f"# {prefix}: {title}\n"

    cells = notebook.get("cells")
    if not isinstance(cells, list) or not cells:
        raise SystemExit("Template notebook has no cells")

    first_cell = cells[0]
    if not isinstance(first_cell, dict) or first_cell.get("cell_type") != "markdown":
        raise SystemExit("Template notebook must start with a markdown title cell")

    source = first_cell.get("source", [])
    if isinstance(source, str):
        source_lines = [source]
    elif isinstance(source, list):
        source_lines = [str(line) for line in source]
    else:
        source_lines = []

    if source_lines:
        source_lines[0] = expected
    else:
        source_lines = [expected]

    first_cell["source"] = source_lines

    metadata = notebook.setdefault("metadata", {})
    if not isinstance(metadata, dict):
        raise SystemExit("Notebook metadata must be a mapping")

    language_info = metadata.setdefault("language_info", {})
    if isinstance(language_info, dict):
        language_info.setdefault("name", "python")
        language_info.setdefault("version", "3.12")


def default_output(repo_root: Path, title: str) -> Path:
    filename = f"{slugify(title)}.ipynb"
    return repo_root / "output" / "jupyter-notebook" / filename


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="Scaffold a Jupyter notebook for experiments or tutorials.")
    parser.add_argument(
        "--kind",
        choices=["experiment", "tutorial"],
        default="experiment",
        help="Notebook style to scaffold (default: experiment).",
    )
    parser.add_argument(
        "--title",
        required=True,
        help="Human-readable notebook title used in the first markdown cell.",
    )
    parser.add_argument(
        "--out",
        type=Path,
        default=None,
        help="Output path for the notebook. Defaults to output/jupyter-notebook/<slug>.ipynb.",
    )
    parser.add_argument(
        "--force",
        action="store_true",
        help="Overwrite the output file if it already exists.",
    )
    return parser.parse_args()


def main() -> None:
    args = parse_args()

    script_path = Path(__file__).resolve()
    skill_dir = script_path.parents[1]
    repo_root = find_repo_root(skill_dir)

    notebook = load_template(skill_dir, args.kind)
    update_title(notebook, args.kind, args.title)

    out_path = args.out or default_output(repo_root, args.title)
    out_path = out_path.resolve()

    if out_path.exists() and not args.force:
        raise SystemExit(f"Refusing to overwrite existing file without --force: {out_path}")

    out_path.parent.mkdir(parents=True, exist_ok=True)
    with out_path.open("w", encoding="utf-8") as f:
        json.dump(notebook, f, indent=2)
        f.write("\n")

    print(f"Wrote {out_path} using kind={args.kind}.")


if __name__ == "__main__":
    main()

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

What our scanner noticed· Low risk

  • Instructions that use the network
  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
OpenAI
Publisher
OpenAI (Official)
Source
openai/skills · skills/.curated/jupyter-notebook · commit 49f948f
Licence
Apache License 2.0 (redistribution allowed)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by OpenAI.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download jupyter-notebook.zip