PR 作成後に Layer 1 /code-review セルフレビューを必ず実行し、指摘対応 → 自動マージまでを自律実行する。外部 AI レビュアー（Copilot/Gemini）への依頼はしない。CI・人手コメントは subscribe_pr_activity で任意監視する。対応はサイレント（ユーザー報告せず PR スレッド・Issue…
Drives deterministic code red-green-refactor. Use before writing or changing any implementation file — write a failing test first, watch it fail, write minimal code to pa — from…
Complete the required presubmit. Use before declaring a feature finished, after a large refactor or when asked.
Code review heuristics — four-axis review lens (correctness, security, design integrity, test coverage); confidence-based filtering (no finding without a concrete failure…
Design patterns — Gang of Four and beyond. Strategy, factory method, observer, decorator, adapter, facade, template method, command, repository, dependency injection.
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.
Refactoring discipline — Fowler's catalog of behavior-preserving moves (Extract Function, Inline Variable, Move Function, Replace Conditional with Polymorphism, Introduce…
SOLID principles — SRP, OCP, LSP, ISP, DIP (single responsibility, open-closed, Liskov substitution, interface segregation, dependency inversion).
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
Run one PR-processing tick on the current repo's open pull requests, then stop. Finalize your own / agent-authored PRs (rebase-if-needed, /code-review then /review-fix if needed,…
Use when the user wants a Basecamp card fully implemented or continued in the current session (feature, bug, refactor, or review follow-up).
Use when writing, generating, modifying, debugging, reviewing, or refactoring code. Treat code work as rebuilding and preserving the program theory: how real-world affairs map…
index.htmlのコード品質チェックとPROTOTYPE.mdとの整合性確認（自動実行）。CSS/JS/HTMLのバグ防止パターン、 フォントサイズ基準、仕様整合性を検査する。OK後はユーザーレビューへ進み、修正依頼は proto-ticket-lifecycle で管理。 パイプライン: proto-05-html-builder →…
How pwsh-code-review computes diff context using PowerShell's AST. Defines the Ring 0/Ring 1 context model, the AST index format, the call graph algorithm, and the…
How to bootstrap a PowerShell project with pwsh-code-review. Use when the user is setting up the reviewer on a new repo, when /pwsh-review-bootstrap runs, or when the existing…
How to run the deterministic static-analysis pre-pass for pwsh-code-review. Covers PSScriptAnalyzer, InjectionHunter, Gitleaks, Pester, and optional auxiliary tools.
Use when refactoring Python code, cleaning up legacy codebases, optimizing performance, enforcing type safety, or improving clean architecture in a FastAPI backend
Perform automated Python code reviews using Pylint programmatic API and pylint-json2html for report generation.
Loads coding rules from Qodo most relevant to the current coding task by generating a semantic search query from the assignment.
Provides Qwen Coder CLI delegation workflows for coding tasks using Qwen2.5-Coder and QwQ models, including English prompt formulation, execution flags, and safe result handling.
Use when designing or refactoring Snowflake RBAC: choosing a role hierarchy, creating database/schema access roles, setting up functional roles, deciding between primary and…
Readable C/C++/Rust/CUDA code rules inspired by The Art of Readable Code. Use when writing, reviewing, or refactoring C, C++, Rust, or CUDA code.
Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and — from…
Use when designing or refactoring record types across objects with many profiles, business processes, or picklist variations.
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green.
Analyzes a codebase scope for coupling issues, diagnoses coupling types using the Connascence framework, and proposes a comprehensive refactoring plan with concrete code changes.
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type…
Restructure code to improve readability, maintainability, and extensibility without changing external behavior.
Run cargo-coupling and similarity-rs to identify refactoring targets, then create a prioritized plan.
Guide safe, incremental refactoring of existing code. Identify refactoring opportunities, suggest patterns, and ensure behavior is preserved through the process.
Refactor by removing backward compatibility and legacy layers. Use when modernizing APIs, cleaning up migration debt, removing compat shims, or eliminating stale feature flags.
Use when modernizing APIs, removing compat shims, killing feature flags, or rewriting a subsystem cleanly.
코드베이스 대상으로 "분석 → 리팩터 → 테스트 → 리뷰" 4단계 체인을 실행하는 스킬. /refactor-chain {target-path} 명령어 입력 시 반드시 이 스킬을 사용한다. 각 단계는 독립 서브에이전트로 실행되며, 이전 단계 결과가 다음 단계 프롬프트에 주입된다.
Use when legacy prompts or older framework flows reference `refactor-cleaner` and you need the modern runtime to resolve that capability cleanly.
Dead code cleanup via pipeline knip + depcheck + ts-prune + javadoc-coverage (multi-language safe removal)
Improves changed code for reuse, simplification, readability, and efficiency without changing behavior, then re-runs tests to prove behavior is unchanged.
Intelligently refactor and improve code quality with incremental, test-backed changes. Use when the user asks to "refactor", "clean up code", "improve code quality",…
Remove code duplication, extract shared patterns, and eliminate type casts and `any` types. Run after implementing new features.
รีแฟกเตอร์และมาตรฐาน Docker project โดยสร้าง docker-compose.yml และ .env file ที่สะอาด ตามแนวทาง best practice มุ่งเน้น structure, consistency และ production readiness ใช้ skill…
For long functions: break into smaller pieces, extract helper functions, reduce nesting, improve testability and readability.
[Code Quality] Removes code duplication and cleans up dead code. Use to eliminate copy-paste code, consolidate similar logic, and remove unused code paths.
Comprehensive refactoring workflow that combines tactical and architectural passes. Runs /refactor (tactical cleanup), /review-arch (architectural restructuring), then /refactor…
Refactor a FastAPI endpoint from monolithic handler to service layer pattern — extract business logic, add error handling, fix DI
During planning after grill-task, decide whether a preparatory refactor step is needed before implementation — runs four parallel A-rule checks.
Model-only playbook for splitting a multi-responsibility class into single-purpose collaborators.
Modernize and improve legacy codebases while maintaining functionality. Use when you need to refactor old code, reduce technical debt, modernize deprecated patterns, or improve…
Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.
Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.
Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection.
Apply systematic refactoring patterns — strangler fig for legacy migration, seam detection, extract method/class, introduce parameter object, replace conditional with…
Composite: end-to-end refactor with plan, parallel 3-agent implementation, test cleanup, ADR capture, and sync.
Use to plan a behavior-preserving structural improvement — audit the target, ensure test coverage exists, plan small reversible steps, and verify behavior is unchanged.
Kategorizovaný návrh refactoringu (kosmetic / structural / breaking) s per-bucket gates. Generuje proposal dokument, postupně provádí změny po schvalování.
/refactor-rust 커맨드로 실행되는 Rust 코드 리팩토링 스킬. rust-coding-style.md에서 도출된 R-R-01~08 도메인 중심 카탈로그를 기준으로, git worktree 격리 환경에서 코드 냄새를 탐지하고 우선순위 기반 계획을 수립한다.
Use when the goal is to change code structure without changing behavior — this includes extracting a service object from a fat controller or model, splitting a large class,…