Jupyter Notebook taste — ChatGPT prompt: what it does, how to install
Jupyter Notebook taste is a ChatGPT prompt for clean, repeatable notebooks. It applies when an analysis is prepared for review or a commit.
CC0-1.0 ★ 178,201 updated 2026-10-24
Open on GitHubWhat Jupyter Notebook taste does
Jupyter Notebook taste sets working rules for notebooks that pass a top-to-bottom run after “Restart and Run All”. Imports, configuration, constants, and random seeds belong in the opening cells, while reusable logic moves into a Python package. During package development, %load_ext autoreload and %autoreload 2 keep changes visible in the notebook.
The prompt covers lock files such as uv.lock, poetry.lock, and a conda lock, plus project-based kernel names, Jupytext pairs, and output removal through nbstripout or a pre-commit hook. Paths and parameters come from one config cell or Papermill, while credentials come from environment variables or a secrets manager. It also calls for assert checks after transformations, Parquet caches for expensive steps, focused cells, labeled charts, and sampled data during exploration. A notebook that relies on cells run out of order can still hide a state error until it is restarted and rerun.
What it helps with
- verify that a notebook runs from top to bottom
- move imports and configuration into the opening cells
- prepare analysis notebooks for review and commits
- replace hard-coded paths with parameters
- check row counts, nulls, and key uniqueness after transformations
Example prompts for the agent
- Check
03-churn-features.ipynband make it run top to bottom after “Restart and Run All”. - Reorganize the notebook so imports, configuration, and constants come first, then move reusable logic into a Python package.
- Prepare this notebook for a commit: strip outputs with
nbstripout, add transformation checks, and remove credentials from the file.
How to install Jupyter Notebook taste
How to use
Paste the text at the start of a chat or into project instructions
Manually: put the files in place
.claude/commands/prompts.csv.mdQuestions about Jupyter Notebook taste
How do I install Jupyter Notebook taste in Claude Code?
Place the prompt file at .claude/commands/prompts.csv.md. ChatGPT has no separate install command here.
What does Jupyter Notebook taste do?
It defines practices for repeatable Jupyter notebooks: a clean top-to-bottom run, organized setup cells, package-based reusable logic, stripped outputs, and data checks.
What should happen to notebooks that run on a schedule?
The prompt calls for turning them into scripts or Papermill jobs with tests instead of opening them by hand.
Source text
prompts.csv · CC0-1.0
# Jupyter Notebook taste of a data scientist who wants notebooks that rerun cleanly - Make every notebook run top to bottom with "Restart and Run All" before sharing or committing it. Confidence: 0.95 - Put imports, configuration and constants in the first cells, never scattered through the notebook. Confidence: 0.85 - Move reusable logic into a normal Python package in the repo and import it, keeping notebooks for exploration and storytelling. Confidence: 0.90 - Use `%load_ext autoreload` and `%autoreload 2` while developing that package alongside the notebook. Confidence: 0.75 - Pin the environment with a lock file such as `uv.lock`, `poetry.lock` or a conda lock, and name the kernel after the project. Confidence: 0.85 - Strip outputs before committing with `nbstripout` or a pre-commit hook, unless the notebook is a published report. Confidence: 0.85 - Pair notebooks with plain-text versions through Jupytext so diffs and code reviews stay readable. Confidence: 0.70 - Read data paths and parameters from one config cell or Papermill parameters, not hard-coded absolute paths. Confidence: 0.85 - Never store credentials in a notebook; load them from environment variables or a secrets manager. Confidence: 0.95 - Set random seeds for NumPy, Python and any ML library in one place so results can be reproduced. Confidence: 0.85 - Give each notebook one clear question, and start it with a short markdown cell that states the goal and data sources. Confidence: 0.80 - Use markdown cells to explain decisions and findings, not just to label code. Confidence: 0.80 - Keep cells short and focused, with the final expression showing a result instead of long `print` chains. Confidence: 0.70 - Avoid relying on hidden state from cells run out of order; if a variable is redefined, restart and rerun. Confidence: 0.90 - Cache expensive steps to Parquet files with clear names rather than recomputing them on every run. Confidence: 0.80 - Sample large datasets during exploration and run the full data only once the analysis is settled. Confidence: 0.75 - Label every chart with a title, axis names and units so it makes sense when pasted into a slide. Confidence: 0.85 - Add small `assert` checks on row counts, nulls and key uniqueness after each major data transformation. Confidence: 0.80 - Name notebooks with a number and topic like `03-churn-features.ipynb` so the order of work is obvious. Confidence: 0.70 - Turn notebooks that run on a schedule into scripts or Papermill jobs with tests, instead of opening them by hand. Confidence: 0.80 - Clean up dead experiments before sharing; keep only the path that leads to the conclusion. Confidence: 0.75
© f · CC0-1.0 · f/prompts.chat