新機能開発統合スキル - 要件分析からPR作成まで、新機能開発の全工程を自動化します。analyze-requirements、develop-backend、develop-frontend、review-architecture、qa-check、create-prの各専門スキルを適切な順序で呼び出し、完全な機能開発を実現します。品質基準（テストカバレッジ80%以上、Lint/ビルド成功）を満たすまで自動的にレビュー・修正を繰り返します。
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →新機能開発統合スキル - 要件分析からPR作成まで、新機能開発の全工程を自動化します。analyze-requirements、develop-backend、develop-frontend、review-architecture、qa-check、create-prの各専門スキルを適切な順序で呼び出し、完全な機能開発を実現します。品質基準（テストカバレッジ80%以上、Lint/ビルド成功）を満たすまで自動的にレビュー・修正を繰り返します。
GitHub Pull Request作成スキル - 変更内容の自動サマリー、PR説明文生成、GitHub PRの作成を行います。git diffでの変更分析、コミットメッセージ取得、変更ファイル分類を行い、高品質なPR説明文を自動生成します。qa-check実行済みであることを前提とし、リモートへのプッシュとgh CLIによるPR作成を実行します。
アーキテクチャレビュースキル（設計整合性、コーディング規約、ドキュメント整合性の確認）
Automated code review with best practices, security checks, and quality standards.
Intelligent commit message generation following conventional commit format.
Generate comprehensive pull request descriptions that help reviewers understand changes quickly a...
Run comprehensive codebase audit for gaps, deprecated code, TODOs, FIXMEs, architectural anti-patterns, type issues, and code smells. Use when user asks to audit code, find issues, check code quality, or identify architectural problems.
Ultra-critical, multi-pass code review that identifies issues, suggests improvements, and provides actionable feedback to prevent runtime failures and improve code quality.
Code review of current git changes, compare to related plan if exists, identify bad engineering, over-engineering, or suboptimal solutions. Use when user asks to review changes, check git diff, validate implementation quality, or assess code changes.
Use when an agent needs to navigate the FirstResponderHomePrograms website UI to find statewide verified programs, under-review signals, free deeper-opportunity teasers, or paid Research Vault and workspace information.
ECサイト開発 - 商品管理、カート、決済、注文フロー、在庫管理の設計・実装支援
Evaluate UI accessibility against WCAG 2.1 guidelines to ensure inclusive design for all users.
Test LogiDocs Certify from customer perspectives to identify UX issues, missing features, and friction points before actual customer feedback.
Perform systematic UX audits using Nielsen's heuristics and UX best practices.
Auto-invoke when reviewing JSX with interactive elements, forms, buttons, or navigation. Enforces WCAG compliance and inclusive design.
Auto-invoke when reviewing API routes, server logic, Express/Node.js code, or backend architecture. Enforces REST conventions, middleware patterns, and separation of concerns.
Auto-invoke when reviewing schema design, database queries, ORM usage, or migrations. Enforces normalization, indexing awareness, query optimization, and migration safety.
> "Code tells you HOW, comments tell you WHY. If you only explain what the code does, you're wasting everyone's time."
Auto-invoke for general code quality review. Enforces naming conventions, function size, DRY principles, SOLID principles, and code organization.
Auto-invoke when reviewing try/catch blocks, API error responses, async operations, or user feedback patterns. Enforces graceful degradation and meaningful error messages.
Verify errors are handled gracefully with meaningful user feedback. Issues result in WARNINGS.
Auto-invoke when reviewing React, Vue, or frontend component code. Enforces component architecture, state management patterns, and UI best practices.
Verify code quality standards are met - naming, structure, DRY principles. Issues result in SUGGESTIONS for improvement.
Auto-invoke when reviewing loops, data fetching, rendering, database queries, or resource-intensive operations. Identifies N+1 queries, unnecessary re-renders, memory leaks, and scalability issues.
Verify performance implications were considered and no obvious anti-patterns exist. Issues result in WARNINGS.
Auto-invoke when reviewing authentication, authorization, input handling, data exposure, or any user-facing code. Enforces OWASP top 10 awareness and security-first thinking.
Verify security considerations were addressed before shipping. Issues result in WARNINGS that strongly recommend fixing.
Auto-invoke when reviewing HTML head, meta tags, or Next.js page components. Enforces semantic HTML and search optimization.
Auto-invoke when reviewing test files or discussing testing strategy. Enforces testing pyramid, strategic coverage, and stack-appropriate frameworks.
Delegates large-context code analysis to Gemini CLI. Use when analyzing codebases, tracing bugs across files, reviewing architecture, or performing security audits. Gemini reads, Claude implements.
Maintains SnowTower project documentation, README, and Claude configuration. Use when updating documentation, auditing .claude folder contents, syncing README with actual project state, or reviewing agent/pattern definitions. Triggers on mentions of documentation, README, maintenance, or .claude folder updates.
Manage security policies, firewall zones, access control rules (ACLs), and guest network access. Perform comprehensive security audits and compliance reviews.
Monitor Ubiquiti Protect surveillance cameras and events. Track camera status, review recordings and alerts, and monitor system health.
This skill should be used when the user requests a code review of changed files. Use this to review git-diffed files for security vulnerabilities (OWASP Top 10), performance issues (O(N) complexity, ORM optimization), bugs, and adherence to project coding standards defined in agents.md and claude.md.
Generate commit messages following project conventions for staged changes. Use when the user asks to commit changes or run /commit.
Frontend coding standards, component patterns, and design system for the Guessimate Angular UI. Reference when writing or reviewing frontend code.
Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.
Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.
Analyzes Move language packages against the official Move Book Code Quality Checklist. Use this skill when reviewing Move code, checking Move 2024 Edition compliance, or analyzing Move packages for best practices. Activates automatically when working with .move files or Move.toml manifests.
UI/UX 设计情报库：50 种风格、21 套配色、50 组字体搭配、20 类图表、8 个技术栈（React、Next.js、Vue、Svelte、SwiftUI、React Native、Flutter、Tailwind）。动作：plan、build、create、design、implement、review、fix、improve、optimize、enhance、refactor、check UI/UX code。项目：website、landing page、dashboard、admin panel、e-commerce、SaaS、portfolio、blog、mobile app、.html、.tsx、.vue、.svelte。元素：button、modal、navbar、sidebar、card、table、form、chart。风格：glassmorphism、claymorphism、minimalism、brutalism、neumorphism、bento grid、dark mode、responsive、skeuomorphism、flat design。主题：color palette、accessibility、animation、layout、typography、font pairing、spacing、hover、shadow、gradient。
code-reviewer
Maintain consistent code formatting, naming conventions, type safety, and automated code quality standards across PHP and TypeScript/JavaScript. Use this skill when writing or editing any PHP files (.php), TypeScript/JavaScript files (.ts, .tsx, .js, .jsx), when implementing type declarations and return types, when running code formatters (Laravel Pint, Ultracite) or linters, when running static analysis tools (Larastan), when naming variables, functions, classes, or files, when applying DRY principles, when removing dead code, or when preparing code for review or commit.
Write minimal, evergreen code comments that explain complex logic without documenting obvious behavior or temporary changes. Use this skill when adding comments to PHP files, TypeScript/JavaScript files, or any code files, when documenting complex algorithms or business logic, when adding PHPDoc blocks or JSDoc comments, when writing self-documenting code with clear naming, or when reviewing existing comments for relevance and necessity. Focus on keeping code self-explanatory through clear structure and naming rather than relying heavily on comments.
Follow consistent project structure, version control practices, environment configuration, code review processes, and development conventions across the entire application. Use this skill when organizing project files and directories, when writing commit messages or creating pull requests, when managing environment variables and configuration, when participating in code reviews, when defining testing requirements, when using feature flags, when maintaining changelogs, when documenting setup instructions, or when establishing consistent development practices across the team.
Remove telltale signs of AI-generated 'slop' writing from README files and documentation. Make your docs sound authentically human.
GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.
Repo Updater - Multi-repo synchronization with AI-assisted review orchestration. Parallel sync, agent-sweep for dirty repos, ntm integration, git plumbing. 17K LOC Bash CLI.
Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side execution with environment inheritance. Go CLI.
Swift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors in a feature or file.
Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.