Skip to content
Get packs

Jupyter Notebooks

Build clean, reproducible SQL or Python Jupyter notebooks that run top-to-bottom and are easy to review.

Source Download skill
Repository
XiaomiMiMo/MiMo-Code
Stars
13,743
Licence
MIT
Files
2 files

What it does

Once installed, the agent builds or edits Jupyter notebooks as reader-friendly analysis documents rather than messy scratch files. It follows a fixed structure (summary, methods, data, results, takeaways), keeps code cells short and focused, records where data came from, and tries to execute the notebook top-to-bottom to confirm it works. If it cannot run the notebook, it is expected to say so and give the exact steps to reproduce the run.

Great for

  • Analysts who need a rerunnable, reviewable record of how a number was produced
  • Teams writing shared SQL or Python exploration that others must audit or repeat
  • Educators or tutorial writers who want a consistent teaching-notebook layout

Skip it if

  • Quick one-off throwaway queries where a full notebook structure is unnecessary overhead
  • Work that needs live database access without review: the skill asks the agent to query connected data sources, so confirm permissions and query cost first
  • Situations where no Python or Jupyter environment is available and the user expects a fully executed notebook; the agent may only produce an unrun file

Try asking

  • “Create a reproducible notebook analysing monthly churn from our exported CSV, with a tl;dr and takeaways”
  • “Edit my existing exploration notebook to split the large cells and add section headers without changing its results”
  • “Turn this SQL query and chart into a tutorial notebook with Goal, Setup, Steps, Checks and Next Steps sections”
  • “Validate that this notebook runs top-to-bottom and tell me exactly what to install if it does not”
Step-by-step guide: how to use Jupyter NotebooksInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    jupyter-notebooks.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip jupyter-notebooks.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip jupyter-notebooks.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the reader and the decision the notebook supports, so the agent picks the right mode and structure.
  • Provide a sample or export and the table names up front to avoid broad, costly live-source queries.
  • Review the executed outputs yourself before relying on the tl;dr, since the summary is only as good as the run.

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from XiaomiMiMo/MiMo-Code under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.