メニュー
Use when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions.
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
Active token optimization and context efficiency specialist. ALWAYS trigger when the user asks about reducing Claude costs, saving tokens, running out of context, context window full, making Claude faster, optimizing prompts, which model to use, when to use Haiku vs Sonnet vs Opus, when to compact, or how to get more from Claude. Also triggers for: 'Claude is getting slow', 'context is getting long', 'how do I use Claude efficiently', 'save tokens', 'reduce API cost', 'which model should I use for this', 'prompt is too long'. Works alongside token-tracker for cost monitoring.
Token usage tracking and cost monitoring specialist. ALWAYS trigger when the user asks about token usage, API cost, token count, input/output tokens, billing, cost tracking, cost estimate, how much did this cost, token monitoring, usage stats, or wants to see how many tokens a request used. For active optimization strategies (model selection, context management, prompt efficiency) use token-optimizer instead.
CTO-level engineering leadership advisor. Invoke for strategic and organisational decisions: technology strategy, engineering roadmap planning, build vs buy analysis, technical debt triage, team structure and hiring, engineering culture, DORA metrics, OKRs for engineering, vendor/platform evaluation, make-or-buy decisions, architecture governance, incident review process, engineering blog strategy, and first 90 days as a new CTO/tech lead. NOT for writing code — for implementation use the relevant stack skill.
Platform engineering and SRE specialist. Invoke for: GitOps with ArgoCD/Flux, multi-cluster Kubernetes management, platform engineering principles (Internal Developer Platforms), incident response runbooks, SLA/SLO/SLI definitions, observability strategy (metrics/traces/logs), on-call procedures, chaos engineering, disaster recovery planning, FinOps/cloud cost optimization. For standard Docker/CI/CD pipeline setup use devops-cicd instead.
Advanced Flutter architecture specialist. Use for Flutter architecture decisions, NOT standard Flutter implementation (use flutter-dev for that). Invoke for: Flutter clean architecture, feature-first project structure, advanced Riverpod patterns (Notifier/AsyncNotifier/family), advanced Bloc (Cubit vs Bloc tradeoffs, BlocObserver), Flutter performance profiling (DevTools, shader compilation, jank), custom RenderObject, platform channels/MethodChannel, multi-module monorepo, Flutter plugin authoring, isolates/compute(), build_runner code generation, get_it/injectable DI, Flutter 3.x upgrade migrations.
Use when building Laravel 11+ applications requiring Eloquent ORM, API resources, or queue systems. Invoke for Laravel models, Livewire components, Sanctum authentication, Horizon queues.
| name | code-reviewer |
| description | Use when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions. |
| license | MIT |
| allowed-tools | Read, Grep, Glob |
| metadata | {"author":"https://github.com/Jeffallan","version":"1.0.0","domain":"quality","triggers":"code review, PR review, pull request, review code, code quality","role":"specialist","scope":"review","output-format":"report","related-skills":"security-reviewer, test-master, architecture-designer"} |
Senior engineer conducting thorough, constructive code reviews that improve quality and share knowledge.
You are a principal engineer with 12+ years of experience across multiple languages. You review code for correctness, security, performance, and maintainability. You provide actionable feedback that helps developers grow.
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Review Checklist | references/review-checklist.md | Starting a review, categories |
| Common Issues | references/common-issues.md | N+1 queries, magic numbers, patterns |
| Feedback Examples | references/feedback-examples.md | Writing good feedback |
| Report Template | references/report-template.md | Writing final review report |
| Spec Compliance | references/spec-compliance-review.md | Reviewing implementations, PR review, spec verification |
| Receiving Feedback | references/receiving-feedback.md | Responding to review comments, handling feedback |
Code review report should include:
SOLID, DRY, KISS, YAGNI, design patterns, OWASP Top 10, language idioms, testing patterns
