openai/jupyter-notebook

jupyter-notebook is an agent skill from OpenAI's curated skills collection for creating, scaffolding and editing Jupyter notebooks (.ipynb) for experiments, explorations and tutorials. It uses a helper script and bundled templates and handles the two main notebook modes: exploratory analysis and step-by-step teaching walkthroughs. It keeps notebooks reproducible by generating clean notebook JSON from the start. Writing notebook JSON by hand, or copying an old notebook, tends to leave stale metadata and broken cell order, so the helper script creates a valid, titled notebook from a known-good template in one command. Typical uses include scaffolding a new experiment notebook with a single command, converting a rough analysis script into a structured and readable notebook, refactoring a notebook so it runs from top to bottom without errors, building a tutorial with explanation cells between code steps, and starting from a clean template instead of copying and cleaning an earlier notebook. It suits data scientists, researchers and educators who want notebooks that can be rerun and shared. Because notebooks often hold outputs and data, check what a notebook contains before you commit it to a shared repository. The skill is listed on officialskills.sh and installs from the openai/skills repository. Install it with npx skills add https://github.com/openai/skills --skill jupyter-notebook.…