Total 30,768 skills, Code Quality has 1625 skills
Showing 12 of 1625 skills
Pull request and code review with diff-based routing across five dimensions: code quality and guideline compliance, test coverage analysis, silent failure detection, type design and invariant analysis, and comment quality auditing. Classifies changed files and loads only relevant review methodologies. Produces severity-ranked findings (Critical, Important, Suggestion) with confidence scoring. Replaces pr-review-toolkit plugin. Trigger phrases: "review my PR", "review this code", "check my changes", "is this ready to merge", "audit this PR", "review before committing", "check code quality", "any issues with this code", "pre-merge review", "look over my changes", "code review". Use this skill when reviewing code before commit or merge, checking PR quality, or when the user asks for feedback on recent modifications.
Receive and process code review feedback effectively. Applies suggestions, addresses comments, and iterates on implementation improvements.
Apply feedback and implement review suggestions. Incorporates reviewer comments into code changes systematically.
Request peer review with proper context and preparation. Structures review requests with clear description of changes and testing status.
Guidelines that help developers design maintainable, scalable, reusable, and loosely coupled software systems. Use when the user asks about design principles, clean code, refactoring, code structure, SOLID, DRY, dependencies, or maintaining software systems.
Use before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.
Interactively fix any type checking issues in Python code
Post-implementation reality check. Run after tests pass, before declaring done. Use when completing a feature, bug fix, refactor, or integration — or when asked to verify, sanity check, or confirm something actually works.
Detect codebase bloat through progressive analysis: dead code, duplication, complexity, documentation bloat. Use when context usage high, quarterly maintenance, pre-release cleanup, before refactoring. Do not use when active feature development, time-sensitive bugs, codebase < 1000 lines.
Audits project physical structure: file hygiene, ignore file quality, framework convention compliance, domain/layer organization, naming conventions. Stack-adaptive via auto-detection.
SOLID principles for object-oriented design — Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion. Covers motivation, violations, fixes, and multi-language examples (PHP, Java, Python, TypeScript, C++) for building maintainable, extensible software.
Use when writing similar code in multiple places. Use when copy-pasting code. Use when making the same change in multiple locations.