Monitor and refactor the Squisq monorepo for code quality issues.
npx skills add https://github.com/bendyline/squisq --skill developmentarchitect
Please help me install this Agent Skill. Skill: developmentarchitect Source: https://github.com/bendyline/squisq/tree/main/.agents/skills/developmentarchitect Command: npx skills add https://github.com/bendyline/squisq --skill developmentarchitect
This Skill maintains the high quality and correctness of the Squisq codebase, optimized for AI agents to generate code with minimal errors.
Run the developmentarchitect skill to review the Squisq codebase for quality and correctness.
High-intent search queries and answers about installing and using this skill.
Codebase health monitoring identifies quality issues like duplication, drift, ambiguity, and staleness. It scans the monorepo to detect structural degradation, ensuring AI-generated code remains robust and maintainable throughout the development process.
Reviewing AI-generated code for correctness involves checking it against established standards to catch errors and maintainability risks. This process flags proposed improvements for human review, ensuring AI-generated output meets quality benchmarks before integration.
Refactoring a monorepo to fix staleness and ambiguity involves identifying outdated or unclear code segments and proposing targeted improvements. The system flags these areas for human correction, maintaining high code quality and reducing development friction.
You should run a code quality check after adding a new package, before major feature work, or when development friction is noticed. Regular checks ensure the codebase remains robust and that AI-generated code meets correctness standards.
Automated code review works with AI agents in a monorepo by monitoring and refactoring code to maintain high quality. It is optimized for AI agents to generate code with minimal errors, flagging issues like drift and duplication for human review.
AI-generated code can introduce duplication and ambiguity when it creates redundant logic or unclear implementations without full context of the existing codebase. Monitoring these issues catches structural drift early, keeping the codebase maintainable.
factorialcoAudit AI configuration files for instruction duplication and ownership adherence.
rseReview staged Git changes for intent, correctness, design, and clarity.
greencmComputes a weighted composite code quality score from project tool integrations.
jackmcintyreAnalyze Python code for complexity, duplication, and best practices.
