notebook-ml-architect

SKILL.md

| audit | Analyze notebook for anti-patterns, leakage, reproducibility issues | | refactor | Transform notebook into modular Python pipeline | | template | Generate new notebook from EDA/classification/experiment template | | report | Create markdown summary from executed notebook | | convert | Extract Python script from notebook |

Step 1: Identify Sections Look for markdown headers that indicate logical sections:

Step 2: Extract Functions Convert repeated or complex cell code into functions:

Expert guidance for auditing, refactoring, and designing machine learning Jupyter notebooks with production-quality patterns. Use when: (1) Analyzing notebook structure and identifying anti-patterns, (2) Detecting data leakage and reproducibility issues, (3) Refactoring messy notebooks into modular pipelines, (4) Generating templates for ML workflows (EDA, classification, experiments), (5) Adding reproducibility instrumentation (seeding, logging, env capture), (6) Converting notebooks to Python scripts, (7) Generating experiment summary reports. Triggers on: ML notebook, Jupyter audit, notebook refactor, data leakage, experiment template, ipynb best practices, notebook to script, reproducibility. Source: bjornmelin/dev-skills.

View raw