Marimo Notebook is a skill designed for users looking to integrate AI functionalities into their existing notebook environments. This skill facilitates advanced notebook features for enhanced productivity and organization.
$ npx skills add https://github.com/marimo-team/skills --skill marimo-notebookMarimo Notebook skills are a collection of instructions and resources designed for AI agents such as Claude Code, Cursor, and other supported agents to work seamlessly with marimo notebooks. These skills are installed via the npx skills package manager, which allows developers to extend their notebook environments with specialized capabilities. Skills provide dynamic instructions and scripts that improve agent performance on marimo-specific tasks. By installing marimo-team/skills, users can leverage AI agents to enhance their notebook workflows and productivity within the marimo ecosystem.
Install using the provided npm command.
Integrate AI features into Jupyter notebooks
Improve data analysis workflows
Automate notebook documentation processes
$ npx skills add https://github.com/marimo-team/skills --skill marimo-notebookgit clone https://github.com/marimo-team/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Generate a marimo notebook with [TASK_DESCRIPTION] for [COMPANY] in the [INDUSTRY] sector. Include [DATA_SOURCES] and [OUTPUT_FORMAT]. Make it interactive, modular, and optimized for collaboration.
# Marimo Notebook: Sales Performance Analysis
*Generated for TechCorp in the SaaS Industry*
```python
import marimo as mo
__generated_with = "0.7.10"
```
## 📊 Sales Performance Dashboard
### 1. Data Loading & Preprocessing
```python
import pandas as pd
from datetime import datetime
# Load sales data from CRM API
sales_data = pd.read_csv("sales_2024_q2.csv")
sales_data['date'] = pd.to_datetime(sales_data['date'])
sales_data = sales_data.dropna()
```
### 2. Interactive Visualizations
```python
import altair as alt
# Monthly revenue trend
revenue_chart = alt.Chart(sales_data).mark_line().encode(
x='month(date):O',
y='sum(revenue):Q',
color='region:N'
).properties(title="Monthly Revenue by Region")
# Top 10 products by sales
product_chart = alt.Chart(sales_data).mark_bar().encode(
x='sum(revenue):Q',
y='product_name:N',
color='product_category:N'
).properties(height=400)
```
### 3. Predictive Analysis
```python
from sklearn.linear_model import LinearRegression
# Predict next month's revenue
X = sales_data['date'].dt.month.values.reshape(-1, 1)
y = sales_data['revenue'].values
model = LinearRegression().fit(X, y)
next_month_revenue = model.predict([[13]])[0]
```
## 📌 Key Insights
- **Top Performing Region**: EMEA with $2.4M revenue
- **Best Selling Product**: AI Analytics Suite ($1.8M)
- **Predicted Revenue for Next Month**: $1.95M
```python
mo.ui.button(label="Refresh Data", on_click=lambda: mo.reload())
```Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan