Agent skill · writing content · aiskillstore
marimo-development
Expert guidance for creating and working with marimo notebooks - reactive Python notebooks that can be executed as scripts and deployed as apps. Use when the user asks to create marimo notebooks, convert Jupyter notebooks to marimo, build interactive dashboards or data apps with marimo, work with marimo's reactive programming model, debug marimo notebooks, or needs help with marimo-specific features (cells, UI elements, reactivity, SQL integration, deploying apps, etc.).
Why this skill is useful
Provides specific patterns and examples for marimo notebooks that the AI wouldn't reliably generate on its own.
What it needs
About 3k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Marimo Development Create reactive Python notebooks with marimo's interactive programming environment. Core Workflow 1. Start with fundamentals: Read references/core-concepts.md - contains marimo's cell structure, reactivity model, UI elements, and essential examples 2. Use recipes for common tasks: Check references/recipes.md for code snippets 3. Refer to API docs: Navigate references/api/ for specific function details 4. Troubleshoot issues: See references/faq.md and references/troubleshooting.md Key Marimo Concepts Cell Structure Every marimo cell follows this structure: When editing cells, only modify the code inside the function - marimo handles parameters and returns automatically. Reactivity Rules 1. Automatic execution: When a variable changes, cells using it automatically re-run 2. No redeclaration: Variables cannot be redeclared across cells 3. DAG structure: Cells form a directed acyclic graph (no circular dependencies) 4. Last expression displays: The final expression in a cell is automatically shown 5. UI reactivity: UI element values accessed via .value trigger automatic updates 6. Local variables: Variables prefixed with (e.g., temp) are local to the cell Import Pattern Always import marimo in the first cell: Common Tasks Creating Interactive UIs Working with Data SQL with DuckDB Layouts Visualization Best Practices matplotlib: Use plt.gca() as last expression (not plt.show()) plotly: Return the figure object directly altair: Return the chart object; add tooltips; accepts polars dataframes directly Reference Documentation Use references/NAVIGATION.md to understand the complete documentation structure. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/marimo-development