Development

Diagnose and fix third-party library loading failures in Vite, Webpack, or other bundlers. Use when encountering "Failed to fetch dynamically imported module", worker loading failures, CDN 404 errors, "Invalid type" errors when importing library assets, or assets loading in wrong format. Covers version mismatches, worker loading patterns, and bundler-specific solutions.

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

Analyze and optimize web pages for SEO including meta tags, structured data, and performance. Use when improving website SEO or analyzing search optimization.

Create professional diagrams using Mermaid or DOT/Graphviz. Mermaid for flowcharts, sequences, classes, ER, Gantt, architecture with semantic coloring and WCAG AA accessibility. DOT/Graphviz for pure network graphs, semantic webs, and maximum layout control.

新機能調査、提案、設計方針確認時に使用。

Guide for creating and configuring custom OpenCode commands. Use this skill when you need to extend OpenCode capabilities, add custom workflows, or understand how to define commands with templates, arguments, and context injection.

Automatically applies when creating AI tool functions. Ensures proper schema design, input validation, error handling, context access, and comprehensive testing.

Ensures code follows quality standards. Apply when reviewing or writing production code.

Use when writing JavaScript for Discourse core, themes, or plugins - covers jQuery phaseout, Ember patterns, singleton imports, lifecycle hooks, and cleanup requirements

WHEN: Performance analysis, bundle size optimization, rendering, Core Web Vitals, code splittingWHAT: Bundle analysis + large dependency detection + re-render issues + useMemo/useCallback suggestions + LCP/FID/CLS improvementsWHEN NOT: Code quality → code-reviewer, Security → security-scanner

View Flask server logs from local or remote server. Shows real-time or recent log entries for debugging. Use when monitoring server activity, debugging issues, or checking server status.

Update the project learning logs (PowerShell/cmd, Git/GitHub/Copilot, AWS, TypeScript, Next.js/React, Playwright) by merging new knowledge into existing categories across one or more files.

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.

Professional report generation system for MyDetailArea dealership management. Creates business intelligence reports with data visualization, multi-format export (HTML/PDF/Excel/CSV), and Notion-style design. Use when generating operational reports, financial analytics, performance dashboards, or custom data exports for the dealership system.

Reference for how I like to write code.

Generate documentation from code, create API references, update README files, and maintain project documentation. Use when user says "document this", "generate docs", "update README", "create API docs", or when documentation is needed.

Periodic task scheduling patterns with Celery Beat (crontab, interval, solar). Use when configuring periodic tasks, setting up task schedules, implementing recurring jobs, configuring django-celery-beat, or creating dynamic schedules.

Use Gemini CLI for large codebase analysis when context limits are exceeded. Use `gemini -p` with @ syntax to include files/directories when analyzing entire codebases, comparing multiple large files, understanding project-wide patterns, or verifying implementation across files exceeding 100KB total.

30 pragmatic rules for production HTML covering semantic markup, accessibility (WCAG 2.1 AA), performance optimization, forms, and security. Use when writing HTML, building page structures, creating forms, implementing accessibility, or optimizing for SEO and Core Web Vitals.

Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best model for a specific task, understand model capabilities, get pricing information, or need help selecting between GPT-4, Claude, Gemini, Llama, or other LLMs. Provides benchmark-based rankings, cost analysis, and use-case-specific recommendations across reasoning, code generation, long context, multimodal, and other capabilities.