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.
92
92%
Does it follow best practices?
Impact
88%
1.49xAverage score across 3 eval scenarios
Passed
No findings from the security scan
Tutorial notebook structure and teaching flow
Uses helper script
30%
100%
uv run invocation
0%
0%
Kind = tutorial
0%
100%
Output path convention
100%
100%
Audience and prerequisites
100%
100%
Learning goals
100%
100%
Numbered outline
25%
100%
Markdown+code step pairs
100%
100%
Exercise present
100%
100%
Answer scaffold
0%
100%
Pitfall called out
100%
100%
Optional extension
12%
100%
Notebook refactoring and JSON structure rules
Analysis intent preserved
100%
100%
Cell order preserved
100%
100%
No large noisy output
100%
100%
Summary dict instead of prints
100%
100%
Minimal imports
100%
100%
Seed and config in one cell
0%
100%
Markdown cells explain steps
100%
100%
execution_count null
100%
100%
Markdown cell structure correct
100%
100%
nbformat preserved
100%
100%
Execution status noted
100%
100%
Skimmable narrative
100%
100%
Experiment notebook scaffolding workflow
Uses helper script
0%
100%
uv run invocation
0%
0%
CODEX_HOME set
0%
62%
JUPYTER_NOTEBOOK_CLI set
0%
62%
Kind = experiment
0%
100%
Output path convention
100%
100%
Descriptive filename
100%
100%
Experiment objective cell
75%
100%
Seed and config cell
37%
100%
Plan cell present
12%
100%
Results and next-steps sections
100%
100%
uv for deps
0%
0%
f627ab5
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.