code-review
Architecture and quality code review for specified files or directories. Checks standards, patterns, security, and maintainability.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Architecture and quality code review for specified files or directories. Checks standards, patterns, security, and maintainability.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generate customized .claude/ harness framework with Fusion Architecture (GAN-inspired + Domain Specialists). TRIGGER when user wants to set up AI-assisted development structure, create a new project harness, add structure to existing projects, or mentions 'harness', 'scaffold', 'framework setup'. Supports all domains through template + dynamic generation.
Negotiates 'done' criteria between Generator, Evaluator, and architect-lead before implementation begins. Converts subjective goals into testable, gradable criteria with clear domain responsibilities.
Guided database migration workflow — from schema design to rollback documentation.
Production incident response workflow — triage, root cause analysis, and resolution.
Track, categorize, and prioritize technical debt across the codebase.
Save current progress with structured handoff artifact. Enables context reset for long-running tasks and session recovery.
| name | code-review |
| description | Architecture and quality code review for specified files or directories. Checks standards, patterns, security, and maintainability. |
| user-invocable | true |
You are facilitating the Code Review process. Your role is to review code for architecture, quality, security, and maintainability issues.
Code review ensures:
RECEIVE TARGET -> AUTOMATED CHECKS -> ARCHITECTURE REVIEW -> QUALITY REVIEW -> SECURITY REVIEW -> REPORT
Run automated checks:
Check architecture:
Check quality:
Check security:
Create review report with:
# Code Review: [Target]
**Reviewer**: [Agent name]
**Date**: [Date]
**Domain**: [Frontend/Backend/Database]
---
## Summary
| Category | Issues Found | Status |
|----------|--------------|--------|
| Architecture | [count] | PASS/FAIL |
| Quality | [count] | PASS/FAIL |
| Security | [count] | PASS/FAIL |
| Standards | [count] | PASS/FAIL |
**Overall**: PASS / FAIL
---
## Critical Issues (Must Fix)
### [Issue ID]: [Title]
- **File**: [path]
- **Line**: [number]
- **Category**: [Architecture/Quality/Security]
- **Issue**: [description]
- **Recommendation**: [how to fix]
- **Severity**: CRITICAL
---
## Major Issues (Should Fix)
### [Issue ID]: [Title]
- **File**: [path]
- **Line**: [number]
- **Category**: [Architecture/Quality/Security]
- **Issue**: [description]
- **Recommendation**: [how to fix]
- **Severity**: MAJOR
---
## Minor Issues (Nice to Fix)
### [Issue ID]: [Title]
- **File**: [path]
- **Line**: [number]
- **Category**: [Standards]
- **Issue**: [description]
- **Recommendation**: [how to fix]
- **Severity**: MINOR
---
## Positive Findings
- [Good practice 1]
- [Good practice 2]
---
## Action Items
| Priority | Action | Assignee |
|----------|--------|----------|
| P1 | [Action] | [Agent] |
| P2 | [Action] | [Agent] |
---
## Recommendations
1. [Recommendation 1]
2. [Recommendation 2]
---
## Follow-up
- Re-review required: Yes/No
- Re-review after: [action items addressed]
| Severity | Description | Action |
|---|---|---|
| CRITICAL | Must fix before merge | Blocks approval |
| MAJOR | Should fix | Requires documented plan to fix |
| MINOR | Nice to fix | Optional, documented |
/code-review [target]
Example:
/code-review src/backend/api/user_routes.py
/code-review src/frontend/components/