code-review
Reviews code against project standards and reports high-confidence issues with specific improvement suggestions.
Install
mkdir -p .claude/skills/code-review-feel-flow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10477" && unzip -o skill.zip -d .claude/skills/code-review-feel-flow && rm skill.zipInstalls to .claude/skills/code-review-feel-flow
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
プロジェクトガイドラインへの準拠をチェックし、バグ、スタイル違反、コード品質問題を検出する。PRレビュー時に使用。Key capabilities
- →Check bugs
- →Detect style violations
- →Identify quality issues
- →Enforce naming conventions
How it works
It checks code against project guidelines and reports only critical or important issues with high confidence.
Inputs & outputs
When to use code-review
- →Performing pull request reviews
- →Checking implementation pattern compliance
- →Identifying critical logic bugs
- →Enforcing naming conventions
About this skill
Code Review スキル
目的
プロジェクトガイドラインへの準拠をチェックし、高信頼度の問題のみを報告する。
参照ガイドライン
AGENTS.mdの「よくある間違いと回避方法」docs-template/MASTER.mdのコード生成ルールdocs-template/03-implementation/PATTERNS.mdの実装パターン
検出対象
- バグ（ロジックエラー、off-by-one、null参照）
- 禁止パターン違反（any型、マジックナンバー、console.log、エラー握りつぶし）
- 命名規則違反（camelCase、UPPER_SNAKE_CASE、PascalCase）
- 未使用のインポート・変数
- 30行を超える関数
信頼度スコア
各問題には0-100の信頼度スコアを付与してください：
| スコア | 意味 | 報告 |
|---|---|---|
| 0-25 | 誤検出または既存の問題 | 報告しない |
| 26-50 | マイナーな指摘（ガイドラインに明記なし） | 報告しない |
| 51-79 | 有効だが低影響 | 報告しない |
| 80-90 | 重要な問題 | 報告する |
| 91-100 | クリティカルなバグまたは明示的な違反 | 必ず報告 |
報告閾値: 信頼度80以上のみ報告
出力形式
結果は以下のMarkdown形式で出力してください。Copilot CLI からのファイル出力に使用されます。
# Code Review Results
## Critical Issues (信頼度 91-100)
- [ファイル名:行番号] 問題の説明
- 信頼度: XX
- 理由: なぜこれが問題か
- 修正提案: どう修正すべきか
## Important Issues (信頼度 80-90)
- [ファイル名:行番号] 問題の説明
- 信頼度: XX
- 理由: なぜこれが問題か
- 修正提案: どう修正すべきか
## Summary
- 検出された問題数: X
- Critical: X
- Important: X
注意事項
- 信頼度80未満の問題は報告しない
- 既存のコード（変更されていない部分）の問題は報告しない
- 推測や曖昧な指摘は避ける
- 具体的な修正提案を含める
When not to use it
- →Reporting low-confidence issues
- →Reviewing existing code
Prerequisites
Limitations
- →Only reports confidence > 80%
- →Ignores existing code
How it compares
It uses a confidence score threshold, filtering out minor or ambiguous issues to reduce noise.
Compared to similar skills
code-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| code-review (this skill) | 0 | 6mo | No flags | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| fix-bug | 11 | 7mo | Review | Intermediate |
| test-fixing | 1 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by feel-flow
View all by feel-flow →You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
fix-bug
tddworks
Guide for fixing bugs in ClaudeBar following Chicago School TDD and rich domain design. Use this skill when: (1) User reports a bug or unexpected behavior (2) Fixing a defect in existing functionality (3) User asks "fix this bug" or "this doesn't work correctly" (4) Correcting behavior that violates the user's mental model
test-fixing
mhattingpete
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
fixing-bugs-systematically
CaptainCrouton89
Diagnose and fix bugs through systematic investigation, root cause analysis, and targeted validation. Use when something is broken, errors occur, performance degrades, or unexpected behavior manifests.
moai-workflow-testing
modu-ai
Comprehensive development workflow specialist combining DDD testing, debugging, performance optimization, code review, PR review, and quality assurance into unified development workflows
investigate
MadAppGang
Unified entry point for code investigation. Auto-routes to specialized detective based on query keywords. Use when investigation type is unclear or for general exploration.