數據與 AI

This skill should be used when implementing rich, interactive React components in LangGraph applications, including weather dashboards, image galleries, flashcards, charts, forms, and custom visualizations. Use when building new agents with custom UI, retrofitting existing agents with generative UI, or implementing specific component types like galleries or interactive forms.

Comprehensive SEO optimization for web applications. Use when asked to improve search rankings, add meta tags, create structured data, generate sitemaps, optimize for Core Web Vitals, or analyze SEO issues. Works with Next.js, Astro, React, and static HTML sites.

Use when implementing any feature or bugfix. Write the test first, watch it fail, write minimal code to pass. Red-Green-Refactor cycle.

Build accessible user interfaces following WCAG guidelines with semantic HTML, keyboard navigation, screen reader support, and proper color contrast. Use this skill when creating or modifying UI components, implementing form inputs, adding interactive elements, working with navigation menus, creating modals or dialogs, or handling focus management. Apply when working on React component files (*.tsx, *.jsx), Shadcn/ui components, or any frontend code that users interact with. This skill ensures semantic HTML elements (nav, main, button, etc.) that convey meaning to assistive technologies, keyboard navigation with visible focus indicators (focus:ring-2 focus:ring-offset-2 in Tailwind), sufficient color contrast ratios (4.5:1 for normal text), descriptive alt text for images and meaningful labels for form inputs, screen reader testing and verification, ARIA attributes for complex components when semantic HTML isn't sufficient, logical heading structure (h1-h6 in proper order), and proper focus management in dyna

Kyverno image validation: registry allowlists, digests, signatures, and CVE scanning gates for K8s supply chain security.

Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge

Systematic framework for selecting the optimal specialized agent for any task. Use when delegating to subagents via the Task tool to ensure the most appropriate specialist is chosen based on framework, domain, task type, and complexity. Applies decision tree logic to match tasks with agent expertise.

Expert on Decibel on-chain perpetual futures trading platform on Aptos. Covers trading engine, orderbook, TypeScript SDK, REST APIs, WebSocket streams, market data, position management, TWAP orders, and vault operations. Triggers on keywords decibel, perpetual futures, aptos trading, on-chain trading, decibel sdk, perps, orderbook, twap, market data, trading api.

End-of-session ritual. Reflect while context is rich, then seal. Triggers on /close, 'wrap up', 'let's finish', or context nearly full. Pairs with /open and /close. (user)

Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.

Expert knowledge of Padel tournament formats (Americano & Mexicano). Use this skill when users ask about organizing padel tournaments, pairing algorithms, scoring systems, calculating rankings, or implementing tournament management software for Americano or Mexicano formats.

Enforce Viet K-Connect non-negotiables (no Server Actions, API Routes only, Drizzle/Supabase patterns, TanStack Query repo layer, i18n ko/en/vi key parity). Use before/after code changes and for PR review checklists.

Provides comprehensive Render.com deployment standards covering environment configuration, database migrations, cron jobs, health checks, log management, and production best practices for web services

Guidance for building, refactoring, and debugging Expo + React Native apps (including Expo Router). Use when wiring screens/layouts, navigation (tab/stack) scaffolding with `_layout.tsx` per group, avoiding unwanted redirects in `app/index.tsx`, theming, data fetching with React Query/fetch, Expo module usage, offline handling, and running local Expo tooling (install/start/lint).

Enriches Jira tasks with comprehensive context, requirements analysis, and technical details through intelligent extraction, dependency mapping, and historical analysis

SagebaseでのBAML (Boundary ML) 統合に関する知識とベストプラクティス。BAML定義ファイルの作成、クライアント再生成、Factory Pattern実装、ハイブリッドアプローチの設計を支援します。

Author high-quality assessment items (questions, prompts, tasks) aligned to learning objectives with answer keys and rubrics. Use when creating test questions, writing assessment items, or building item banks. Activates on "write assessment items", "create test questions", "develop quiz", or "author performance tasks".

여러 LLM(OpenAI, Gemini, Ollama 등)을 통합하여 멀티 에이전트 협업을 수행합니다. 역할 분담, 토론/합의, 체인 파이프라인, 병렬 처리 등 다양한 협업 패턴을 지원하며, 사용 시점에 시나리오를 동적으로 구성할 수 있습니다. 복잡한 작업을 여러 LLM에게 분산하여 더 나은 결과를 얻고 싶을 때 사용하세요.

Patterns for ingesting knowledge into vector databases and RAG systems

Structured incremental development workflow that enforces explicit scoping before implementation. Use when: (1) User says 'build', 'implement', 'develop', 'create feature', or 'add functionality', (2) Task involves multiple files or could have ripple effects, (3) User wants to avoid scope creep or premature implementation, (4) Breaking down complex tasks into verifiable steps. This skill prevents AI agents from jumping into code without a validated plan.