copilot-agent
GitHub Copilot CLIをサブエージェントとして活用し、コードベースの解析・調査を行う。 以下の場面で使用: (1) /copilot コマンドで明示的に呼び出された場合 (2) コードベースの広範な調査が必要で、別視点からの分析が有用な場合 (3) 特定の実装パターンや設計についてセカンドオピニオンが欲しい場合
GitHub Copilot CLIをサブエージェントとして活用し、コードベースの解析・調査を行う。 以下の場面で使用: (1) /copilot コマンドで明示的に呼び出された場合 (2) コードベースの広範な調査が必要で、別視点からの分析が有用な場合 (3) 特定の実装パターンや設計についてセカンドオピニオンが欲しい場合
Guidelines for contributing commands in VS Code extensions. Indicates naming convention, visibility, localization and other relevant attributes, following VS Code extension development guidelines, libraries and good practices
Review code and suggest improvements, refactors, and clarifications
Code quality checker skill. This skill should be used when the user wants to: (1) Run static analysis tools (mypy, pyright, ruff) on the codebase - triggered by "/check", "/check q", or "/check quality" (2) Find dead/unused code (functions, imports, variables, unreachable code) - triggered by "/check d" or "/check dead"
Analyze codebase statistics with tokei (line counts by language) and difft (semantic AST-aware diffs). Use for project composition, refactoring scope, codebase metrics.
Analyzes code smells and architectural violations to formulate a concrete Refactoring Plan. Used for (1) identifying technical debt, (2) defining As-Is vs To-Be states, and (3) planning safe, atomic refactoring steps.
Review code written by Claude Code or humans across multiple languages. Use when asked to review, audit, critique, or analyze code quality. Supports R, Python, JavaScript, SQL, C++, Rust, Go, Ansible, Kustomize/Kubernetes, Dockerfiles, Docker Compose, and Bash. Covers correctness, security, performance, testing, documentation, and architecture. Produces actionable output for Claude Code to fix issues plus human-readable REVIEW.md summaries.
Rust coding style guide. Apply automatically when writing or modifying Rust code. Enforces let-else for early returns, variable shadowing, newtypes, explicit matching, and minimal comments.
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
Use after completing file changes - strongest for source code (AST-aware linting, security, tests), lighter support for markdown/config. Dispatches CodeRabbit reviewer subagent. ALWAYS request review before considering work complete.
Apply code quality tools (Ruff, ty, pre-commit) to Python projects. Use PROACTIVELY when code quality issues are detected. Keywords: lint, format, quality, 品質, ruff, type
Use when reviewing code or before commits - runs 25-point quality checklist (structure, errors, security, performance, testing), identifies code smells, suggests refactorings with examples. Activates when user says "review this", "check my code", mentions "refactor", "optimize", "code quality", or before git commits.
Use when performing code reviews. Provides a checklist to verify error handling, TypeScript, CSS, and architecture patterns.
Auto-format code with Prettier and ESLint, fix linting errors, and enforce code style standards. Use when user says "format code", "fix linting", "prettier", "eslint", or when code needs style fixes.
Define canonical dotnet format and analyzer verification commands, and provide scripts that generate a format/analyzer report. Use when checking formatting or Roslyn analyzers without reformatting everything.
Detects code smells, anti-patterns, and common bugs with quantified thresholds and severity scoring. Use when reviewing code quality, finding maintainability issues, detecting SOLID violations, or identifying technical debt.
Parallel lint fixing pattern - runs lint checks, groups issues into independent streams, and dispatches AI agents to fix all issues until the codebase is clean.
Reviews code for best practices, refactoring opportunities, complexity, and dead code
Use when the user asks to "refactor shell script", "fix bash style", "apply Google style guide to shell", "review shell script style", "format bash script", or when writing, reviewing, or refactoring shell/bash scripts. Provides Google Shell Style Guide rules for formatting, quoting, naming, control flow, and common anti-patterns.
Integrate RubyCritic to analyze Ruby code quality and maintain high standards throughout development. Use when working on Ruby projects to check code smells, complexity, and duplication. Triggers include creating/editing Ruby files, refactoring code, reviewing code quality, or when user requests code analysis or quality checks.