Total 54,373 skills, Code Quality has 2447 skills
Showing 12 of 2447 skills
Runs Sweepi and resolves lint violations using Sweepit rule docs. Trigger when asked to run Sweepi, when linting (or asked to lint), and before proposing commits.
Refactor Django/Python code to improve maintainability, readability, and adherence to best practices. Transforms fat views into Clean Architecture with Use Cases and Services. Applies SOLID principles, Clean Code patterns, Python 3.12+ features like type parameter syntax and @override decorator, Django 5+ patterns like GeneratedField and async views. Fixes N+1 queries, extracts business logic from views, separates Read/Write serializers, and converts exception-based error handling to explicit return values. Use when refactoring Django code, applying Clean Architecture, or modernizing legacy Django projects.
Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims.
Use when reviewing Rust code for craft quality, when writing new Rust code that should follow professional patterns, or when the user asks to judge, audit, or improve Rust code against best practices. Covers type design, function signatures, trait architecture, error handling, visibility, macros, testing, and performance patterns.
Assesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when suggestions are unclear, technically questionable, or scope-expanding. Use before implementing review suggestions to align on intent and keep changes minimal.
Scans codebases for technical debt with AST parsing, prioritizes debt items by impact, and generates trend dashboards. Use when tracking tech debt, prioritizing refactoring, or measuring code quality trends over time.
Run findings-first review for Atlan app changes and synchronize app documentation with implemented behavior. Use when completing a change set, preparing handoff, or auditing regressions.
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.
17 principles of Unix software design, from Eric Raymond's *The Art of Unix Programming*. You can refer to these principles when carrying out software design.
Bence's code style, tech stack, and workflow conventions
Improve code readability without altering functionality using idiomatic best practices
Review code for conceptual errors, wrong assumptions, edge cases, and overcomplication; use after medium/large changes or when risk is high.