jupyter-notebook

Savant verdict: Review advised

SkillSpector or the source hub flagged patterns to review before use.

Live evaluation

1 pass · 1 investigate · 4 fail across 6 cases. Jev accepted 6 of 18 LLM-drafted cases. Drafted and run by nvidia/nemotron-3-super-120b-a12b, validated and scored by jev-latest.

• Create a Jupyter notebook for an experiment comparing the effect of learning rates on convergence speed for a simple neural network on MNIST.positive case · fail
• Build a tutorial notebook teaching beginners how to load and visualize CSV data with pandas and matplotlib, including an exercise to plot a histogram.positive case · fail
• Refactor this existing notebook to improve reproducibility by adding a setup cell with imports and seed, and moving all configuration to the top.positive case · fail
• Edit this notebook to add a conclusion section and fix the typo in the third markdown cell.edge case · pass
• Write a Python script that scrapes data from a website and saves it to a CSV file.negative case · fail
• Generate a PowerPoint presentation explaining the results of our A/B test.negative case · investigate

Safety (NVIDIA SkillSpector)

4 patterns found

• Rogue Agent: overwrite existing filehigh · scripts/new_notebook.py:119 · Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
• MCP Least Privilege: Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.medium · SKILL.md:1 · Without declared permissions the skill's intent is opaque and cannot be validated.
• Rogue Agent: Create clean, reproducible Jupyter notebooks for two primary modes: - Experiments and exploratory analysis - Tutorials and teaching-oriented walkthroughs Prefer the bundled templates and the helpermedium · SKILL.md:9 · Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
• Agent Snooping: ls install under `$CODEX_HOME/skills` (default: `~/.codex/skillsmedium · SKILL.md:34 · Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Structure

• 2 referenced files aren't in the packageassets/experiment-template.ipynb, assets/tutorial-template.ipynb. They may be binary, too large to catalog, or missing upstream.
• Ships 1 executable scriptscripts/new_notebook.py. Review what they do before enabling the skill for agents with tool access.

SKILL.md

---
name: "jupyter-notebook"
description: "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."
---


# Jupyter Notebook Skill

Create clean, reproducible Jupyter notebooks for two primary modes:

- Experiments and exploratory analysis
- Tutorials and teaching-oriented walkthroughs

Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.

## When to use
- Create a new `.ipynb` notebook from scratch.
- Convert rough notes or scripts into a structured notebook.
- Refactor an existing notebook to be more reproducible and skimmable.
- Build experiments or tutorials that will be read or re-run by other people.

## Decision tree
- If the request is exploratory, analytical, or hypothesis-driven, choose `experiment`.
- If the request is instructional, step-by-step, or audience-specific, choose `tutorial`.
- If editing an existing notebook, treat it as a refactor: preserve intent and improve structure.

## Skill path (set once)

```bash
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`).

## Workflow
1. Lock the intent.
Identify the notebook kind: `experiment` or `tutorial`.
Capture the objective, audience, and what "done" looks like.

2. Scaffold from the template.
Use the helper script to avoid hand-authoring raw notebook JSON.

```bash
uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" \
  --kind experiment \
  --title "Compare prompt variants" \
  --out output/jupyter-notebook/compare-prompt-variants.ipynb
```

```bash
uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" \
  --kind tutorial \
  --title "Intro to embeddings" \
  --out output/jupyter-notebook/intro-to-embeddings.ipynb
```

3. 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.

4. Apply the right pattern.
For experiments, follow `references/experiment-patterns.md`.
For tutorials, follow `references/tutorial-patterns.md`.

5. 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.

6. 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`.

## Templates and helper script
- Templates live in `assets/experiment-template.ipynb` and `assets/tutorial-template.ipynb`.
- The helper script loads a template, updates the title cell, and writes a notebook.

Script path:
- `$JUPYTER_NOTEBOOK_CLI` (installed default: `$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py`)

## Temp and output conventions
- Use `tmp/jupyter-notebook/` for intermediate files; delete when done.
- Write final artifacts under `output/jupyter-notebook/` when working in this repo.
- Use stable, descriptive filenames (for example, `ablation-temperature.ipynb`).

## Dependencies (install only when needed)
Prefer `uv` for dependency management.

Optional Python packages for local notebook execution:

```bash
uv pip install jupyterlab ipykernel
```

The bundled scaffold script uses only the Python standard library and does not require extra dependencies.

## Environment
No required environment variables.

## Reference map
- `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.