agentleFS
Sign inStart free
atsushi-greenatsushi-green/ds-ai-coding-skills/.claude/skills/notebook-workflow/SKILL.md

notebook-workflow

Skill86 starsChanged 51 days agoMITView on GitHub

Use this when creating, editing, executing, or reviewing Jupyter notebooks — including cell structure, kernel management, extracting reusable logic to src/, and ensuring notebooks are restartable.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when creating, editing, executing, or reviewing Jupyter notebooks.

    line 8
  2. Distinctive:

    Keep notebooks restartable from a clean kernel (Kernel → Restart & Run All must work).

    line 17
  3. Distinctive:

    Avoid hidden state — do not rely on cells being run in a non-linear order.

    line 18
  4. Distinctive:

    Do not include secrets or customer-level records in notebook outputs.

    line 19
  5. Very specific:

    Prefer saving final charts and tables to outputs/.

    line 20
  6. Distinctive:

    Use papermill for parameterized notebook execution when automation is needed.

    line 32
  7. Distinctive:

    Imports: All imports in the first code cell.

    line 49
  8. Distinctive:

    Ensure no credentials or PII in cell outputs.

    line 57
  9. Distinctive:

    Verify the notebook runs end-to-end with a fresh kernel.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: Notebook Workflow

Use this skill when creating, editing, executing, or reviewing Jupyter notebooks.

Purpose of Notebooks

  • Notebooks are for exploration and communication.
  • Reusable logic should be extracted to src/analysis_project/.

Rules

  • Keep notebooks restartable from a clean kernel (Kernel → Restart & Run All must work).
  • Avoid hidden state — do not rely on cells being run in a non-linear order.
  • Do not include secrets or customer-level records in notebook outputs.
  • Prefer saving final charts and tables to outputs/.

Naming Convention

NNN_short_description.ipynb

Example: 001_data_exploration.ipynb, 002_feature_analysis.ipynb

Automation

  • Use papermill for parameterized notebook execution when automation is needed.
uv run papermill notebooks/input.ipynb notebooks/output.ipynb -p param_name value

Structure

  1. Header cell (Markdown): Title, author, date, objective.

    # タイトル
- **作成者**: 名前
- **作成日**: YYYY-MM-DD
- **目的**: この分析で明らかにしたいこと
  2. Imports: All imports in the first code cell.
  3. Configuration: Parameters, paths, constants.
  4. Analysis: Exploratory or analytical cells.
  5. Summary: Key findings and next steps.

Cleanup Before Commit

  • Clear large outputs that are not essential for review.
  • Ensure no credentials or PII in cell outputs.
  • Verify the notebook runs end-to-end with a fresh kernel.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free