Terminal
Terminal/Skill
Creates, inspects, edits, and runs Jupyter notebook (.ipynb) files for experiments and tutorials.
By Kilo Code
Works with
npx skills add kilo-org/skills --skill jupyter-notebookCreate 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.Before inspecting, editing, or executing a notebook, check whether suitable Jupyter MCP tools are available.
references/manual-editing.md before editing raw notebook JSON.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. Resolve scripts/new_notebook.py against the base directory supplied when this skill is loaded; do not assume the skill is installed under the project's .kilo directory.
python3 "<SKILL_BASE_DIR>/scripts/new_notebook.py" \
--kind experiment \
--title "Compare prompt variants" \
--out "compare-prompt-variants.ipynb"
python3 "<SKILL_BASE_DIR>/scripts/new_notebook.py" \
--kind tutorial \
--title "Intro to embeddings" \
--out "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, follow references/manual-editing.md.
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.ablation-temperature.ipynb).Optional Python packages for local notebook execution:
python3 -m 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.references/manual-editing.md: manual editing and execution fallback when Jupyter MCP is unavailable.references/quality-checklist.md: final validation checklist.