$ loading_
Create, scaffold, or edit Jupyter notebooks for experiments, exploration, and tutorials.
Overall risk is low: this skill requires no credentials and declares no remote endpoints, and is mainly used to generate or edit Jupyter notebooks locally. The materials indicate an auditable open-source GitHub source with strong community adoption, though its local script execution and file-write behavior still warrant attention to local change scope.
The material explicitly states that no keys or environment variables are required. No API keys, tokens, or other sensitive credentials are indicated, so credential exposure or misuse risk appears low.
The material lists no remote endpoint hosts, and the README describes local templates and a helper script for notebook generation. There is no stated behavior of sending user data to external services.
The README explicitly shows running a local Python helper script via `uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI"`, indicating local code execution. This is a normal capability for this type of tool, but it should still be limited to trusted code and controlled directories.
This skill is used to create, scaffold, and edit `.ipynb` files. The README indicates reading templates and writing notebooks under paths such as `output/` and `tmp/`, and it may also modify existing notebooks. There is no sign of overbroad data access beyond its stated purpose, but it does perform local file changes.
The source is an open-source GitHub repository, and the system flags it as `open-source` with about 22k stars, which are strong risk-reducing signals because the code is auditable in principle. The license is undeclared and maintenance status is unknown, leaving some transparency gaps, but not enough on their own to justify a high-risk rating.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "jupyter-notebook" skill from askskill: 1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/jupyter-notebook/SKILL.md 2. Save it as ~/.claude/skills/jupyter-notebook/SKILL.md 3. Reload skills and tell me it's ready
Create clean, reproducible Jupyter notebooks for two primary modes:
Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.
.ipynb notebook from scratch.experiment.tutorial.export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export JUPYTER_NOTEBOOK_CLI="$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py"
User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).
Lock the intent.
Identify the notebook kind: experiment or tutorial.
Capture the objective, audience, and what "done" looks like.
Scaffold from the template. Use the helper script to avoid hand-authoring raw notebook JSON.
uv run --python 3.12 python "$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
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.
Apply the right pattern.
For experiments, follow references/experiment-patterns.md.
For tutorials, follow references/tutorial-patterns.md.
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.
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.
assets/experiment-template.ipynb and assets/tutorial-template.ipynb.Script path:
$JUPYTER_NOTEBOOK_CLI (installed default: $CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py)tmp/jupyter-notebook/ for intermediate files; delete when done.output/jupyter-notebook/ when working in this repo.ablation-temperature.ipynb).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.
No required environment variables.
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.Connect to Figma, fetch design assets, and turn nodes into production code.
Deploy, publish, and host apps and infrastructure on Cloudflare services.
Turn vague intentions into concrete, measurable goals and clear success criteria.
Map Figma design components to code components for consistent implementation.
Generate custom design system rules for your codebase and Figma-to-code workflow.
Capture full-screen, window, or region screenshots at the operating system level.
Create, validate, fix, and deploy Jupyter Book notebooks automatically.
Manage notes and sources, search content, and use AI models in Open Notebook.
Load, edit, search, and save Jupyter notebooks through MCP tools.
Read, modify, and batch-process Jupyter notebooks without running a Jupyter server.
Create NotebookLM notebooks, add sources, and ask grounded questions naturally.
Let AI manage NotebookLM notebooks, sources, queries, and research workflows.