MCP HubMCP Hub
← スキル一覧に戻る

code-review-assistant

AsiaOstrich
更新日 Yesterday
165 閲覧
34
4
34
GitHubで表示
開発word

について

このClaudeスキルは、プルリクエストとコード品質を評価するための体系的なコードレビューチェックリストと、コミット前の品質ゲートを提供します。機能性、設計、品質、可読性に分類されたチェックリストと、フィードバックの重大度を分類する標準化されたコメント接頭辞システムを備えています。PRレビュー時やコードコミット前の一貫した品質基準の適用にご利用ください。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/AsiaOstrich/universal-dev-skills
Git クローン代替
git clone https://github.com/AsiaOstrich/universal-dev-skills.git ~/.claude/skills/code-review-assistant

このコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします

ドキュメント

Code Review Assistant

This skill provides systematic checklists for code review and pre-commit verification.

Quick Reference

Comment Prefixes

PrefixMeaningAction Required
❗ BLOCKINGMust fix before merge🔴 Required
⚠️ IMPORTANTShould fix, but not blocking🟡 Recommended
💡 SUGGESTIONNice-to-have improvement🟢 Optional
❓ QUESTIONNeed clarification🔵 Discuss
📝 NOTEInformational, no action⚪ Informational

Review Checklist Categories

  1. Functionality - Does it work?
  2. Design - Right architecture?
  3. Quality - Clean code?
  4. Readability - Easy to understand?
  5. Tests - Adequate coverage?
  6. Security - No vulnerabilities?
  7. Performance - Efficient?
  8. Errors - Properly handled?
  9. Docs - Updated?
  10. Dependencies - Necessary?

Pre-Commit Checklist

  • Build succeeds (zero errors, zero warnings)
  • All tests pass
  • Code follows project standards
  • No security vulnerabilities
  • Documentation updated
  • Branch synced with target

Detailed Guidelines

For complete standards, see:

Example Review Comments

❗ BLOCKING: Potential SQL injection vulnerability here.
Please use parameterized queries instead of string concatenation.

⚠️ IMPORTANT: This method is doing too much (120 lines).
Consider extracting validation logic to a separate method.

💡 SUGGESTION: Consider using a Map here instead of an array for O(1) lookup.

❓ QUESTION: Why are we using setTimeout here instead of async/await?

📝 NOTE: This is a clever solution! Nice use of reduce here.

Core Principles

  1. Be Respectful - Review code, not the person
  2. Be Thorough - Check functionality, not just syntax
  3. Be Timely - Review within 24 hours
  4. Be Clear - Explain WHY, not just WHAT

Configuration Detection

This skill supports project-specific configuration.

Detection Order

  1. Check CONTRIBUTING.md for "Disabled Skills" section
    • If this skill is listed, it is disabled for this project
  2. Check CONTRIBUTING.md for "Code Review Language" section
  3. If not found, default to English

First-Time Setup

If no configuration found and context is unclear:

  1. Ask the user: "This project hasn't configured code review language. Which option would you like? (English / 中文)"
  2. After user selection, suggest documenting in CONTRIBUTING.md:
## Code Review Language

This project uses **[chosen option]** for code review comments.
<!-- Options: English | 中文 -->

Configuration Example

In project's CONTRIBUTING.md:

## Code Review Language

This project uses **English** for code review comments.
<!-- Options: English | 中文 -->

### Comment Prefixes
BLOCKING, IMPORTANT, SUGGESTION, QUESTION, NOTE

License: CC BY 4.0 | Source: universal-doc-standards

GitHub リポジトリ

AsiaOstrich/universal-dev-skills
パス: skills/code-review-assistant
ai-coding-assistantbest-practicesclaude-codeclaude-code-skillscode-reviewdeveloper-experience

関連スキル

content-collections

メタ

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る

llamaindex

メタ

LlamaIndex is a data framework for building RAG-powered LLM applications, specializing in document ingestion, indexing, and querying. It provides key features like vector indices, query engines, and agents, and supports over 300 data connectors. Use it for document Q&A, chatbots, and knowledge retrieval when building data-centric applications.

スキルを見る

canvas-design

メタ

The canvas-design skill generates original visual art in PNG and PDF formats for creating posters, designs, and other static artwork. It operates through a two-step process: first creating a design philosophy document, then visually expressing it on a canvas. The skill focuses on original compositions using form, color, and space while avoiding copyright infringement by never copying existing artists' work.

スキルを見る