← Back to list

working-with-marimo
by pymc-labs
A Python package for causal inference in quasi-experimental settings
⭐ 1,093🍴 91📅 Jan 21, 2026
SKILL.md
name: working-with-marimo description: Interactive development in marimo notebooks with validation loops. Use for creating/editing marimo notebooks and verifying execution.
Working with Marimo
Follows a Plan-Execute-Verify loop to ensure notebook correctness.
Feedback Loop
-
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).
- Sessions:
-
Execute:
- Edit the
.pyfile directly usingwriteorsearch_replace. - Rule: Follow Best Practices (e.g.,
@app.cell, no global state).
- Edit the
-
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).
- Lint:
Common Commands
- Start/Sync: Marimo automatically syncs file changes.
- SQL: Use
mo.sqlfor DuckDB queries. - Plots: Use
plt.gca()or return figure. Noplt.show().
Reference
See Best Practices for code formatting, reactivity rules, and UI element usage.
Score
Total Score
80/100
Based on repository quality metrics
✓SKILL.md
SKILL.mdファイルが含まれている
+20
✓LICENSE
ライセンスが設定されている
+10
○説明文
100文字以上の説明がある
0/10
✓人気
GitHub Stars 1000以上
+15
✓最近の活動
1ヶ月以内に更新
+10
✓フォーク
10回以上フォークされている
+5
○Issue管理
オープンIssueが50未満
0/5
✓言語
プログラミング言語が設定されている
+5
✓タグ
1つ以上のタグが設定されている
+5
Reviews
💬
Reviews coming soon
