codex-review
codex review CLIを使用したコードレビュー。セルフレビュー、PR作成前チェック、コミット確認に使用。「レビューして」「変更を確認して」で発動
codex review CLIを使用したコードレビュー。セルフレビュー、PR作成前チェック、コミット確認に使用。「レビューして」「変更を確認して」で発動
コードレビュー結果の出力フォーマットを定義。重要度レベル、出力構造、GitHubコメント形式のMarkdownテンプレートを提供します。
Automated code validation for diff review, change hygiene, and red flag detection. Use when reviewing git diffs, PRs, or changed files for test disabling patterns, secrets, path portability issues, security flags, and large deletions. Supports Python, TypeScript, JavaScript, HTML, and CSS.
Request and process code review efficiently with a simple rubric and patch plan
Reviews code for best practices, bugs, security issues, and provides improvement suggestions
Enhanced docs linting with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
Automatically generates and updates API documentation from code changes with multiple format support
Proactively monitors file sizes and suggests refactoring BEFORE editing. Auto-invoked when files exceed size thresholds (150/200/300 lines) or complexity patterns detected. Works across JavaScript/TypeScript, Python, and general codebases. Prevents accidental complexity growth.
Automatically invoked when analyzing code quality, refactoring, or maintainability. Triggers on mentions of "code smell", "refactor", "code quality", "technical debt", "complexity", "maintainability", "clean code", "SOLID", "DRY", "improve code", "simplify", "extract method", "extract class", "long method", "large class", "duplication". Provides Ruby refactoring patterns and code smell identification based on Ruby Science methodology for recently written Ruby/Rails code.
Provides code formatting best practices and granular edit operation guidelines. Use when formatting code, making edits to files, or when determining the proper approach for code modifications. Emphasizes using external formatting tools and breaking down large modifications into atomic, sequential edits for reliability.
Reviews Python code for PEP8 compliance, type hints, modern best practices (Python 3.9+), and code quality. Detects anti-patterns, validates documentation, and provides severity-based recommendations. Integrates with modern tooling (ruff, mypy, uv).
Automatic code review and fixes before showing to user. Use when: code generation is complete, before preview. Triggers: internal use only.
Enforces project React coding conventions automatically when creating or modifying React components. This skill should be used proactively whenever working with .tsx/.jsx files to ensure consistent code style, naming conventions, component structure, and TypeScript patterns across the codebase.
AST-based code analysis using tree-sitter. Use for parsing code structure, extracting symbols, finding patterns with tree-sitter queries, analyzing complexity, and understanding code architecture. Supports Python, JavaScript, TypeScript, Go, Rust, C, C++, Swift, Java, Kotlin, Julia, and more.
Formatting and linting standards using GTS, ESLint, and Prettier. Use when writing or formatting TypeScript code in this project.
Python code quality with ruff linter. Fast linting, rule selection, auto-fixing, and configuration. Use when checking Python code quality, enforcing standards, or finding bugs.
ADVISORY validation of code against design principles, accessibility, and best practices that linters cannot fully enforce. Use after linter passes and tests pass to validate design quality. Categorizes findings as Design Debt, Readability Debt, or Polish Opportunities. Does NOT block commits.
Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis.
代码简化与优化专家。Use this agent when you need to simplify, optimize, refactor, or clean up code. This agent helps reduce complexity, improve readability, and ensure code follows best practices like YAGNI, KISS, and DRY principles. Supports two modes: analysis mode (provides simplification suggestions) and execution mode (directly modifies code). Works with any programming language. Examples: <example>Context: User wants to simplify complex code. user: "这段代码太复杂了,帮我简化一下" assistant: "Let me analyze and simplify this code using the code-simplifier agent" <commentary>Use code-simplifier to reduce complexity and improve readability.</commentary></example> <example>Context: User wants a code review for optimization opportunities. user: "Review this function for optimization" assistant: "I'll use code-simplifier to identify optimization opportunities and suggest improvements" <commentary>Code-simplifier can analyze and provide optimization recommendations.</commentary></example>
Biome all-in-one formatter and linter for JavaScript, TypeScript, JSX, TSX, JSON, and CSS. Zero-config setup, 15-20x faster than ESLint/Prettier. Use when working with modern JavaScript/TypeScript projects, setting up formatting/linting, or migrating from ESLint+Prettier to a faster alternative.
Expert coding agent for this codebase. Learns from every session to improve code quality, catch edge cases, and apply proven patterns. Use for ANY coding task: writing, debugging, refactoring, testing. Accumulates project knowledge.
Analyze codebases for anti-patterns, code smells, and quality issues using ast-grep structural pattern matching. Use when reviewing code quality, identifying technical debt, or performing comprehensive code analysis across JavaScript, TypeScript, Python, Vue, React, or other supported languages.