Jupyter Notebook
Data & Analyticsby openai
3/3 audits passApache-2.0
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials;
Jupyter Notebook, published by OpenAI under Apache-2.0, teaches the agent to create and edit clean, reproducible .ipynb notebooks in two modes: experiments for exploratory or hypothesis-driven analysis, and tutorials for step-by-step teaching. Its workflow is to lock the intent (kind, objective, audience, what done looks like), scaffold from a bundled template with the new_notebook.py helper rather than hand-writing notebook JSON, fill in small runnable cells with short markdown explaining each step, apply the matching experiment or tutorial pattern, and validate by running the notebook top to bottom, or say plainly when that was not possible.
Use it to convert rough notes or scripts into a structured notebook, refactor an existing one for readability, or build something other people will re-run. When editing, it asks for targeted changes that preserve the notebook's structure rather than full rewrites. It includes reference files on notebook structure and a quality checklist, and its paths assume OpenAI's Codex skill directory, which you may need to adjust for another agent. It does not perform the analysis itself.
This is mainly a skill for coding agents that work with local files; it can be imported into BusinessMCP as a playbook, but only its instructions come across and the helper script and templates are not run.
What you can do with it
- Scaffold an experiment notebook to compare prompt or model variants
- Turn a rough analysis script into a readable notebook
- Build a step-by-step tutorial notebook for a team
- Refactor a messy notebook without reordering its logic
Run it on your business data
Imported into BusinessMCP, Jupyter Notebook becomes a playbook your AI business analyst applies to your web analytics, funnels and connected databases.
Use Jupyter Notebook in BusinessMCPInstall it in a coding agent
One command adds Jupyter Notebook to your project.
npx skills add https://github.com/openai/skills --skill jupyter-notebookHow we vetted it
- Source
- openai/skills at 49f948f
- Licence
- Apache-2.0
- Security audits (skills.sh)
- Gen Agent Trust Hub: Pass · Socket: Pass · Snyk: Pass
- Bundled scripts
- Yes — read them before installing
Checked 2026-09-25 against its skills.sh listing. How we vet skills
Related skills
All skillschDB Datastore
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas.
Explore Data
Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or…
Data Visualization
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles…
Frequently asked questions
What two kinds of notebook does it make?
Experiment notebooks for exploratory or hypothesis-driven work and tutorial notebooks for instructional walkthroughs, each scaffolded from its own bundled template.
Does the agent run the notebook?
The skill tells it to run the notebook top to bottom when the environment allows, and to say so explicitly and explain how to validate locally when it cannot.
How do I install Jupyter Notebook?
Run `npx skills add openai/skills --skill jupyter-notebook`, or import it from the BusinessMCP dashboard as a playbook (instructions only; the helper script is not run).
Keep exploring
Run Jupyter Notebook against your whole business
Free plan, no credit card.
Use Jupyter Notebook in BusinessMCP