What problem does it solve? Writing marimo notebooks requires following specific conventions—cells as decorated functions, PEP 723 dependency headers, reactivity rules, and script-mode handling—that differ significantly from Jupyter. This Skill encodes those conventions so generated notebooks run correctly the first time. ## Core Features & Use Cases - Correct Notebook Structure: Generates marimo notebooks as plain Python files using @app.cell decorators, PEP 723 dependency blocks, and proper input/output variable flow between cells. - Reactivity and State Guidance: Enforces marimo's DAG-based reactivity model, avoiding cross-cell mutations, unnecessary mo.state() usage, and anti-patterns like guarding cells with if statements or hiding errors behind try/except. - Validation and Testing: Runs marimo check as a linter before delivery and supports pytest-based test cells for notebook verification. - Use Case: Ask for an interactive data exploration notebook with sliders and plots; the Skill produces a runnable .py notebook that works both interactively via marimo run and non-interactively as a script with synthetic data. ## Quick Start Create a marimo notebook that loads a CSV file, lets me filter it with a dropdown, and shows an interactive chart of the results.
