👀Code Review Skills
Browse skills in the Code Review category.
Open Source Contributions
A powerful skill for Claude agents.
Entry Point Analyzer
A powerful skill for Claude agents.
Fix Review
A powerful skill for Claude agents.
Spec To Code Compliance
A powerful skill for Claude agents.
Audit Context Building
A powerful skill for Claude agents.
Differential Review
A powerful skill for Claude agents.
Sharp Edges
A powerful skill for Claude agents.
Swiftui Performance Audit
A powerful skill for Claude agents.
Reducing Entropy
A powerful skill for Claude agents.
Requesting Code Review
A powerful skill for Claude agents.
Gemini
A powerful skill for Claude agents.
Web Design Guidelines
A powerful skill for Claude agents.
Vercel React Best Practices
A powerful skill for Claude agents.
agents-review
Review code changes using src.agents.scripts.review after edits. Use when you need multi-provider feedback on diffs, staged changes, or the last commit, or when focusing on a review theme like security.
deslop
Remove AI-generated code slop from current branch. Identifies and removes inconsistent comments, over-defensive code patterns, and style mismatches introduced by AI. Use when: cleaning up AI-generated code, before committing AI changes, after code generation session.
code-review
专业代码审查技能。当用户需要审查代码、检查 PR、评估代码质量、发现潜在问题或提供改进建议时使用此技能。
smith-stacks
Stacked pull request workflows for large features. Use when creating stacked PRs, managing dependent PRs, or rebasing after parent merges. Covers stack creation, merge order, and squash merge handling.
pr-review-checklist
Use when asked to review a PR, propose review comments, or prepare a merge checklist.
smith-gh-pr
GitHub PR workflows including creation, review cycles, merge strategies, and stacked PRs. Use when creating PRs, reviewing code, merging branches, or managing stacked PR workflows. Covers rebase decision trees and AI-generated descriptions.
python-code-patterns
Python code style and type hinting patterns. Use when writing or reviewing Python code to ensure consistent, modern type annotations and clean code structure. Covers modern type hints, import organization, comment practices, and docstring conventions.
code-reviewer
Review code for correctness, maintainability, performance, and security. Produce actionable, prioritized feedback and concrete fixes aligned with repo standards.
coding-practices
This skill should be used when the user asks about "coding best practices", "code conventions", "code style", "how to write good code", "clean code", or asks for guidance on code quality and patterns. Scaffold skill - expand with your preferred practices.
check-nuxt-ui-v4
ドキュメント内のNuxt UI v3記法を検出し、v4記法への修正を支援します。「ドキュメントをチェックして」「Nuxt UI v4の記法を確認」などで呼び出されます。
gpui-code-quality
Best practices and code quality guidelines for GPUI development. Use when refactoring, reviewing code, or ensuring adherence to GPUI idioms.
performance-optimization
Guides performance analysis and optimization for any application. Use when diagnosing slowness, optimizing code, improving load times, or when asked about performance.
refactoring-specialist
Safely refactor code to reduce complexity, improve structure, and increase maintainability while preserving behavior.
code-review
Expert code reviewer that identifies bugs, security issues, and suggests improvements
code-standards
C# coding conventions, naming patterns, and file organization standards for the MotoRent project.
performance
This skill should be used when the user asks about "Ruby performance", "optimization", "profiling", "benchmarking", "memory", "garbage collection", "GC", "benchmark-ips", "stackprof", "memory_profiler", "slow code", "speed up Ruby", or needs guidance on making Ruby code faster.
security
Security auditor that identifies vulnerabilities using OWASP guidelines
refactor-guide
代码重构指南技能。当用户需要优化代码结构、消除代码异味、改进设计模式、提升代码可维护性或进行架构改进时使用此技能。
perform-forge-review
Create AI-assisted code reviews on GitHub, GitLab, or Forgejo. Use when asked to review a PR/MR, analyze code changes, or provide review feedback.
code-review
Systematic code review guidance covering correctness, maintainability, security, and performance. Activates for PR reviews and code quality checks.
code-investigator
Investigate code to confirm specifications and provide evidence-based reports. Use when: 'what does this do?', 'how is this implemented?', 'where is the spec?', 'explain this behavior', or any request requiring code investigation with documented evidence. Also use for bug investigation requiring current specification understanding.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
code-review
**AUTO-ACTIVATE after code changes** (Write, Edit, NotebookEdit tools used).Comprehensive code review using 15-point checklist. Reviews: completeness,correctness, testability, reusability, consistency, design, error handling,security, documentation, performance, UX, data migration, dependencies.Triggers: code written, files modified, implementation complete, "review code"
security-audit
代码安全审计指南。当用户需要检查代码安全漏洞、实施安全最佳实践、进行安全代码审查或修复安全问题时使用此技能。
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
reviewing-objectstar
Analyze, refactor, and migrate TIBCO Objectstar (Object Service Broker) legacy mainframe applications. Use when working with Objectstar/OSB source code files, rules, screen definitions, or table definitions. Triggers on .osr, .osb file extensions, or code containing Objectstar patterns like condition quadrants (Y N columns), FORALL loops, TRANSFERCALL, parameterized tables, or rules with LOCAL declarations.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
global-coding-style
Follow core coding style principles including SOLID, DRY, KISS, and YAGNI when writing code. Apply consistent naming conventions, meaningful variable names, small focused functions, automated formatting, and proper code organization. Use this skill across all programming languages and file types when writing or refactoring code. Use when creating functions, classes, modules, or components to ensure Single Responsibility Principle, when avoiding code duplication (DRY), when choosing simple over clever implementations (KISS), or when resisting premature optimization and speculative features (YAGNI). Use when establishing naming conventions, removing dead code, or maintaining consistent indentation and formatting. Apply these principles universally across backend (.ts, .js, .py, .java, .go), frontend (.tsx, .jsx, .vue), and configuration files.
pr-code-review-fixer
Systematically fetch, analyze, and fix code review issues from GitHub Pull Requests. Use when the user asks to review and fix code issues from AI code reviewers (like Gemini Code Assist, GitHub Copilot, CodeRabbit) or any PR review comments. Fetches all review comments using gh CLI, attempts to fix all reported issues, commits changes to the PR branch, and generates a comprehensive fix report. Triggers on requests like "fix PR review issues", "address code review feedback", "apply review suggestions", or when given a GitHub PR URL with review comments to address.
review
This skill should be used when the user asks to "review code", "check for anti-patterns", "audit my code", "find issues in code", "review this file", "check this component", or mentions code review, linting, or pattern checking. Identifies CoRATES-specific anti-patterns in SolidJS components and Hono API routes.
review-pr
GitHub PRをレビューする。PR番号を引数として受け取り、変更内容を分析してレビューコメントを提供する。「/review-pr 123」のように使用する。
global-commenting
Write self-documenting code with clear structure and naming, using minimal but helpful comments only when necessary to explain complex logic. Use this skill across all code files when deciding whether to add comments or how to structure code for clarity. Use when refactoring code to be more self-explanatory, when removing outdated or temporary comments, when writing evergreen informational comments that remain relevant over time, or when choosing between adding a comment versus improving variable/function names. Apply when working with any programming language (.ts, .js, .py, .java, .go, .tsx, .jsx, .vue) to maintain clean, understandable code without over-commenting.
deep-dive-analysis
AI-powered systematic codebase analysis. Combines mechanical structure extraction with Claude's semantic understanding to produce documentation that captures not just WHAT code does, but WHY it exists and HOW it fits into the system. Includes pattern recognition, red flag detection, flow tracing, and quality assessment. Use for codebase analysis, documentation generation, architecture understanding, or code review.
pr-tech-spec-generator
Generate comprehensive technical specifications from GitHub Pull Requests. Use when users provide a GitHub PR URL and request documentation, technical specs, or change analysis. Analyzes PR commits and diffs using gh CLI and git commands to produce structured documentation covering folder structure, DB schema changes, API definitions, test changes, and dependency updates.
neuro-check
This skill should be used for quick inline brain-faithfulness validation during coding. Use when the user asks "is this brain-faithful?", "is this naming correct?", "should this be driver or modulator?", or similar quick neuroscience questions. For deep analysis or KB verification, recommend the neuro-expert agent instead.
analyzing-objectstar
Skill for understanding, editing, analyzing, and migrating TIBCO Objectstar (Object Service Broker) code used in mainframe OTP and batch applications. Activate when user is working with Objectstar rules, asks about mainframe modernization, or legacy 4GL code involving GET, FORALL, or EXCEPTION blocks.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements