build-notebook

name	build-notebook
argument-hint	[spec-path]
description	This skill should be used when the user asks to "build the notebook", "launch the dashboard", "generate the marimo notebook", or when an analysis_plan.md artifact exists and the user wants to assemble or regenerate the dashboard. Reads chart specs with ibis queries and altair code from analysis_plan.md, assembles a marimo Python file, validates, and launches. Do NOT use for exploring data or planning charts (use explore-data), building pipelines (use rest-api-pipeline toolkit), or deploying (use dlthub-platform toolkit).

Build notebook from spec

Read a <date>_<pipeline_name>_analysis_plan.md artifact and assemble a marimo notebook with all charts.

Parse $ARGUMENTS:

• spec-path (optional): path to the analysis_plan.md file. If omitted, look for *_analysis_plan.md in the working directory. If multiple found, ask the user and stop.

Step 1: Read analysis_plan.md

Parse the analysis plan file for:

• Connection section: pipeline name, dataset name, destination type
• Chart N sections: each chart's question, type, SQL code, and altair code
• Count the total number of charts to assemble

If the analysis plan file is missing or has no charts, tell the user to run explore-data first and stop.

Step 2: Assemble notebook

Generate <pipeline_name>_dashboard.py. Read references/notebook-patterns.md for the complete notebook structure, cell templates, and naming conventions before generating. Every chart cell must end with on a bare line, then — without the bare expression line, nothing renders.