Assess Python codebases for module depth and progressive disclosure.
npx skills add https://github.com/rockandrolla13/blueprint --skill review-depth
Please help me install this Agent Skill. Skill: review-depth Source: https://github.com/rockandrolla13/blueprint/tree/main/review-depth Command: npx skills add https://github.com/rockandrolla13/blueprint --skill review-depth
Review Python code for deep module design and progressive disclosure. Scores modules on interface-to-implementation ratio, cognitive load at each navigation level, and information hiding. Use this skill whenever the user says "simplify", "too complex", "hard to navigate", "cognitive load", "clean up interfaces", "deep modules", "progressive disclosure", "make it easier to understand", "reduce complexity", "hard to find things", or wants to enforce Ousterhout-style deep module principles. Do NOT trigger for general code review (use code-review), architecture scoring (use review-architecture), or refactoring execution (use refactor).
Phase 1: Module Census to measure interface size and implementation depth for Python modules Phase 2: Progressive Disclosure Audit to map navigation levels and disclose violations Phase 3: Cognitive Load Scoring and Findings generation to quantify reader effort and produce actionable guidance
Run the skill on a Python project to generate a depth and disclosure report.
High-intent search queries and answers about installing and using this skill.
To check a Python codebase for deep modular design, run a module census to measure interface-to-implementation ratios, then map navigation levels to score cognitive load and generate actionable refactoring findings.
A deep module design score quantifies how effectively a module hides information by evaluating its interface-to-implementation ratio and the cognitive load required to navigate its progressive disclosure layers.
Measure cognitive load in Python modules by auditing progressive disclosure levels and calculating the depth ratio of implementation size against interface surface area to identify information hiding gaps.
Yes, you can apply this deep module assessment to Python codebases during both pre-refactor and post-refactor reviews, as well as for onboarding new contributors and planning architecture changes.
A deep module review specifically scores interface-to-implementation ratios and progressive disclosure to reduce cognitive load, whereas a general code review focuses on broader code quality without architectural depth analysis.
Avoid using a deep modules assessment when you need general code review, broad architecture scoring, or automated refactoring execution, as it specifically targets progressive disclosure and cognitive load measurement.
EntroVyxAnalyze repositories with pygount to calculate lines of code and language distribution.
flowelAnalyze codebase architecture and generate an HTML report of refactoring opportunities.
mgd34msuAnalyze code changes for security, performance, and quality issues.
phrazzldIdentify and implement the most impactful codebase simplification in a single pull request.
