Jupyter Notebook Writing

If you're writing Milvus examples as Jupyter notebooks, this handles the ugliness of editing raw ipynb JSON by letting you work in clean Markdown instead. You edit the md file, then convert it to a notebook with jupyter-switch. The format is simple: python code blocks become code cells, everything else becomes markdown. It includes opinionated workflow steps for testing notebooks across different Python environments (conda, venv, system) and explicitly tells you to comment out pip install cells before running, since dependencies should already be in your Jupyter kernel. Comes with two reference docs covering Milvus bootcamp format conventions and pymilvus code style patterns.

skills.sh installs: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add zc277584121/marketing-skills --skill jupyter-notebook-writing --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill: Jupyter Notebook Writing

Write Milvus application-level Jupyter notebook examples as a DevRel workflow. Uses a Markdown-first approach — AI edits .md files, then converts to .ipynb via jupyter-switch.

Prerequisites: Python >= 3.10, uv (uvx command available)

When to Use

The user wants to create or edit a Jupyter notebook example, typically demonstrating Milvus usage in an application context (RAG, semantic search, hybrid search, etc.).

Core Workflow: Markdown-First Editing

Jupyter .ipynb files contain complex JSON with metadata, outputs, and execution counts — painful for AI to edit directly. Instead:

Write/Edit the .md file — AI works with clean Markdown
Convert to .ipynb — using jupyter-switch for runnable notebook
Keep both files in sync — the .md is the source of truth for editing

Format Convention

In the .md file:

Python code blocks (```python ... ```) become code cells in the notebook
Everything else becomes markdown cells
Cell outputs are not preserved in .md (they get generated when running the notebook)