Development

Load when user says "validate docs", "check documentation consistency", "docs vs implementation", or "find documentation mismatches". Systematically compares implementation code against documentation to identify and fix inconsistencies.

add and manage documentation in code, including constants, variables, functions, classes, and modules

ReactでSPAフロントエンドを実装・改修するためのガイド。バックエンド分離前提でNext.jsやサーバーサイド機能に依存せず、React Router中心のクライアント実装を行う時に使う。認証はAuthProviderとuseAuthカスタムフックで統一し、OpenAPIからorvalまたはopenapi-typescriptで型/クライアントを生成して利用する。ESLint+Prettier、zod、shadcn/ui、デザイントークン（CSS変数/Tailwindテーマ）を前提にする場合に適用する。ディレクトリ構成はmodules/components/hooks/providers/servicesなどの直感的な命名で複雑化に耐える構成にする。

Secure-by-design architecture patterns for Kubernetes. Zero trust, defense in depth, least privilege, and fail-secure patterns with implementation examples and threat models.

Expert knowledge of testing Node.js and Express applications including Jest configuration, Supertest for API testing, unit vs integration vs e2e testing, mocking external APIs, test organization, code coverage, CI/CD integration, and TDD practices. Use when writing tests, setting up testing framework, debugging test failures, or adding test coverage.

Git branch management, commits, pull requests, and IJACK Roadmap project board integration. Use when creating feature branches, committing code, creating pull requests, managing git workflows, or adding issues to the IJACK Roadmap project board.

Code review checklist and best practices for thorough quality assessment.

Use this skill when developing Next.js 16+ applications - creating pages, components, layouts, API routes, implementing proxy.ts, adding caching with Cache Components, or refactoring frontend code. This includes working with App Router patterns, Server Components, Server Actions, React 19+ features, and Tailwind CSS v4.

Expert guidance for building LLM applications with LangChain framework - chains, prompts, memory, retrievers, and integrations.

Next.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps.Use when working on Next.js applications, debugging routing, or inspecting app structure.NOT for general React or non-Next.js projects.

Expert Unreal Engine 5 developer and technical artist for complete game development via agentic coding. Enables AI-driven control of Unreal Editor through MCP, Python scripting, Blueprints, and C++ for level design, asset management, gameplay programming, and visual development.

Generate PlantUML diagrams from text descriptions and convert them to PNG/SVG images. Use when asked to "create a diagram", "generate PlantUML", "convert puml to image", "extract diagrams from markdown", or "prepare markdown for Confluence". Supports all PlantUML diagram types including UML (sequence, class, activity, state, component, deployment, use case, object, timing) and non-UML (ER diagrams, Gantt charts, JSON/YAML visualization, mindmaps, WBS, network diagrams, wireframes, and more).

Next.js content model with visual editing for Netlify.

Cloudflare deployment for frontend (Pages) and backend (Workers). Covers secrets, environment variables, custom domains, and production configuration.

scArches 单细胞深度学习参考图谱框架 - 100%覆盖文档（26个HTML文件，包含完整API、教程、模型训练、多模态整合）

Use when configuring Karabiner-Elements keyboard customizations, before writing JSON - provides systematic workflow for complex modifications with correct structure, common patterns, and guidance on manual vs generator approaches

Analyzes code diffs to identify affected endpoints and prioritize regression testing. Focuses QA effort on changed areas.

Performance optimization toolkit for Astro SSG sites. Analyzes and applies optimizations including resource preloading (fonts, images, CSS), page prefetching, image loading strategies (lazy/eager, fetchpriority), and configuration improvements. Use when the user asks to optimize an Astro site, improve Astro performance, add preloading, configure prefetching, or speed up their Astro build. Handles both automatic safe optimizations and user-confirmed risky optimizations.

Use quality dependencies freely - default to using existing libraries over reinventing. For Python prefer conda over pip, maintain separate requirements-conda.txt and requirements-pip.txt. Use when adding dependencies, installing packages, or evaluating whether to use a library.

Fetches library documentation from Context7 and the web, then saves it to ai_docs/ in organized category-based folders. Supports version management, topic-specific documentation, and refreshing existing docs. Automatically invoked for requests to fetch or save library documentation.