Total 53,555 skills, Code Quality has 2423 skills
Showing 12 of 2423 skills
Discourse 패턴으로 다관점 리뷰를 수행한다. Tech Spec 리뷰와 에픽 통합 코드 리뷰를 모두 처리하며, 쟁점 해소 프로토콜에 따라 합의/미합의를 분리한다.
C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.
Analyze Python code for style improvements including naming, structure, nesting, and cognitive load reduction
Clean Code practices for TypeScript/JavaScript. Identify code smells, apply refactoring patterns, and write maintainable code. Use when reviewing code quality, refactoring messy code, or ensuring code follows best practices. Triggers on requests like "clean up this code", "refactor for readability", "identify code smells", or "make this more maintainable".
Audit repos for architectural drift, dead code, and abstraction bloat.
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.
Write, fix, and standardize Python docstrings in Google style. Use whenever the user asks to add or improve docstrings, convert mixed docstrings to Google format, add missing Args/Returns/Raises/Attributes/Example sections, or make docstrings concise and API-focused.
Implement the tasks in a spec-driven change. Works through incomplete tasks one by one, marking each complete as it goes.
Parse, don't validate - using sealed classes for type-safe validation and state representation. Model valid/invalid states explicitly, validate at boundaries, operate on valid types internally.
Split a large ***plain module into smaller modules grouped by logical domain. The resulting modules are connected via a requires chain so that functionality is 100% preserved. Use when a module has grown too large and its functional specs span multiple distinct concerns that would be clearer as separate modules.
Run /debug to find and fix the root cause of a bug (something failing, broken, throwing, or behaving wrong) when a test fails for a reason that is not obvious, /check verify finds a failure, or behavior is unexpected. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
Runtime performance audit worker (L3). Checks blocking IO in async, unnecessary allocations, sync sleep in async, string concat in loops, missing to_thread for CPU-bound, redundant data copies. Returns findings with severity, location, effort, recommendations.