OpenParable
Skip to content
← Back to skills

Working With Marimo

Development
working-with-marimo

Working With Marimo is an Agent Skill for development published in the pymc-labs/CausalPy repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Interactive development in marimo notebooks with validation loops. Use for creating/editing marimo notebooks and verifying execution.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/pymc-labs/CausalPy/blob/HEAD/.agents/skills/working-with-marimo/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/working-with-marimo, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Working with Marimo

Follows a Plan-Execute-Verify loop to ensure notebook correctness.

Feedback Loop

  1. Context & Plan:

    • Sessions: mcp_marimo_get_active_notebooks (Find session IDs).
    • Structure: mcp_marimo_get_lightweight_cell_map (See cell IDs/content).
    • Data State: mcp_marimo_get_tables_and_variables (Inspect DataFrames/Variables).
    • Cell Detail: mcp_marimo_get_cell_runtime_data (Code, errors, local vars).
  2. Execute:

    • Edit the .py file directly using write or search_replace.
    • Rule: Follow Best Practices (e.g., @app.cell, no global state).
  3. Verify (CRITICAL):

    • Lint: mcp_marimo_lint_notebook (Static analysis).
    • Runtime Errors: mcp_marimo_get_notebook_errors (Execution errors).
    • Outputs: mcp_marimo_get_cell_outputs (Visuals/Console).

Common Commands

  • Start/Sync: Marimo automatically syncs file changes.
  • SQL: Use mo.sql for DuckDB queries.
  • Plots: Use plt.gca() or return figure. No plt.show().

Reference

See Best Practices for code formatting, reactivity rules, and UI element usage.