code-review-skill
言語共通のコードレビュースキル。コメント最適化、マジックナンバー検出、構造改善のレビューを実施。コードレビュー、PRレビュー、コード品質チェックを依頼された際に使用。
Découvrez les skills tools code quality, comparez leurs dépôts et consultez leurs instructions.
言語共通のコードレビュースキル。コメント最適化、マジックナンバー検出、構造改善のレビューを実施。コードレビュー、PRレビュー、コード品質チェックを依頼された際に使用。
Serena MCP expert for efficient code editing and analysis. Use when starting projects, editing code, or refactoring. Prioritize symbol-based operations over full-file reads.
Core code review logic. Trigger when invoked by review commands. Do not trigger directly from user requests - use /df:review or /df:azdo:review instead.
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.
Review documentation for accuracy against implementation and compliance with documentation standards. Use when auditing docs, verifying ground truth, or ensuring documentation quality.
This skill validates i18n (internationalization) key consistency across Go source and TOML locale files. Use when adding, modifying, or reviewing i18n keys in this project to ensure `internal/i18n/keys.go` stay...
Strict guidelines and enforcement of markdownlint rules. Use this skill to ensure all generated markdown files are syntactically correct and render flawlessly across platforms.
Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component --json` shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexi...
Automatically detect and fix TypeScript unused imports/variables errors (TS6133). Use when encountering "declared but its value is never read" errors during tsc, build, or CI checks.
Code quality review skill focusing on readability, maintainability, and consistency (non-architectural). Checks for naming conventions, code duplication, type consistency, unused code, and other clean code issu...
Style Guardian - Unified Design System Enforcement Tool. Use for: (1) Preventing hardcoded styles (colors, spacing, typography), (2) Preventing hardcoded text (i18n violations), (3) Guiding unified configuratio...
修復前強制評估系統. Use for: (1) 測試失敗自動評估, (2) 編譯錯誤分類處理, (3) 強制 Ticket 開設流程
Analyze codebase for existing implementations, test coverage, and code patterns. Use when checking what's already implemented, finding related code, or assessing test coverage for features.
Check and enforce project policies from CLAUDE.md and POLICIES.md. Use when validating implementations against project standards, checking code style requirements, or ensuring compliance with development guidel...
Analyze plans and code quality for any file or change set. Use when asked to review a plan, assess implementation quality, score completeness against a checklist, or provide actionable QA feedback (correctness,...
Validate model correctness using MCP tools. Checks element references, relationships, view definitions, and syntax.
Load when reviewing code, writing code examples, or ensuring code quality. Contains coding standards for Python, JavaScript, SQL, and general best practices for publication-quality code.
Perform comprehensive security analysis to identify vulnerabilities. Integrates with codex-review for automatic security checks. Covers OWASP Top 10, common vulnerabilities, and secure coding practices. Output:...
MANDATORY quality gate. Run this skill BEFORE: (1) asking user "Is this okay?", (2) git commit, (3) creating PR, (4) presenting any implementation or design to user. Codex reviews in read-only sandbox, iterates...
Ensure complete compliance with code quality standards. Use before commit, before PR creation, or when quality issues are detected.
Prevents "lazy" coding habits by enforcing full implementation and banning placeholders.
Enforce the "Premium" aesthetic and accessibility standards.
Enforces high-level architectural thinking, separation of concerns, and scalability checks before coding.
驗證 maihouses 專案的 TypeScript/React 代碼品質,確保符合 CLAUDE.md 的最高規格標準。當修改或審查代碼時自動使用。
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.