What standards does this skill use for auditing?

It uses a comprehensive style guide focused on the Diataxis framework, emphasizing action-oriented learning, clear prerequisites, and mapped learning objectives.

What is the output of a Cookbook Audit?

You receive a detailed report including an executive summary, numerical scores for various dimensions, and prioritized actionable recommendations for improvement.

Can it detect leaked API keys in my notebooks?

Yes, it integrates with detect-secrets to automatically scan code cells for hardcoded credentials and API keys during the audit process.

Do I need to provide the style guide manually?

The skill expects a style_guide.md file in the workspace to use as the canonical reference for templates and scoring rubrics.

How does it handle complex Jupyter Notebook files?

The skill converts .ipynb files into clean Markdown, excluding noisy outputs but preserving code, to provide a more readable and reviewable format.

Cookbook Audit Pro

Name: Cookbook Audit Pro
Author: Microck

byMicrock

•

Learning & Documentation

Audits technical Jupyter notebooks against standardized rubrics to ensure educational quality, security compliance, and technical accuracy.

About

Cookbook Audit is a specialized skill designed to evaluate and improve educational Jupyter Notebooks, specifically those following the Anthropic Cookbook style. It automates technical checks—such as credential scanning via detect-secrets—while providing a structured framework for manual pedagogical review. By enforcing the Diataxis framework and specific learning patterns like Terminal Learning Objectives (TLOs), this skill helps developers transform raw code into high-quality, action-oriented learning materials that emphasize both practical implementation and conceptual understanding.

Key Features

Standardized 20-point scoring system across narrative, code, and accuracy
Jupyter to Markdown conversion for streamlined context-aware reviews
Structural enforcement of setup patterns, dependency management, and conclusions
Automated security scanning to detect hardcoded API keys and credentials
Pedagogical validation of learning objectives (TLOs and ELOs)
81 GitHub stars

Use Cases

Automating security and style audits for large repositories of Jupyter Notebooks
Reviewing technical tutorials before publication to ensure high pedagogical standards
Refactoring existing code examples into structured, action-oriented documentation

About

Key Features

Standardized 20-point scoring system across narrative, code, and accuracy
Jupyter to Markdown conversion for streamlined context-aware reviews
Structural enforcement of setup patterns, dependency management, and conclusions
Automated security scanning to detect hardcoded API keys and credentials
Pedagogical validation of learning objectives (TLOs and ELOs)
81 GitHub stars

Use Cases

Automating security and style audits for large repositories of Jupyter Notebooks
Reviewing technical tutorials before publication to ensure high pedagogical standards
Refactoring existing code examples into structured, action-oriented documentation