Frontend

Decision guide for when to query Bluera Knowledge stores vs using Grep/Read on current project. Query BK for library/dependency questions and reference material. Use Grep/Read for current project code, debugging, and implementation details. Includes setup instructions and mental model.

Build Midnight dApps with TypeScript integration, wallet connectivity, and contract deployment. Use when connecting wallets, deploying contracts, or building dApp frontends. Triggers on wallet, provider, Next.js, deployment, or TypeScript integration questions.

Apply consistent CSS styling methodologies using project conventions such as Tailwind CSS utility classes, BEM naming, CSS Modules, or styled-components while maintaining design system consistency. Use this skill when writing or modifying styles in component files, CSS files, Tailwind classes, styled-components, CSS-in-JS solutions, or design token configurations. Use this skill when working with CSS frameworks, establishing design tokens for colors and spacing, optimizing CSS for production builds, or ensuring consistent styling patterns across the application. Use this skill when working with .css, .scss, .module.css files, or when adding className attributes to components with utility classes.

Use when editing Observable notebooks (docs/index.html), creating charts with Plot, adding SQL cells, loading data with FileAttachment, or working with DuckDB. Triggers on notebook editing, visualization, data loading.

Track complex, multi-session work with dependency graphs using bd (beads) issue tracker. Git-backed JSONL files are the source of truth, with SQLite as local cache. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Guides UI styling and design using Tailwind CSS 4, shadcn/ui components, and the global theme system. Use when styling components, designing UIs, or making visual changes. Emphasizes CSS variable-based theming for consistent, maintainable styles.

Use this skill whenever the user wants to design, refactor, or extend Next.js App Router routes, layouts, and navigation patterns (including route groups, dynamic routes, and server/client component boundaries) in a TypeScript + Tailwind + shadcn/ui project.

React Native 脚手架 comet CLI 命令规范与项目配置。当用户提到"comet"、"脚手架"、"scaffold"、"初始化项目"、"创建应用"、"项目结构"、"comet.yaml"时使用此 skill。

Build Roblox games with Flamework, a TypeScript framework. Use when creating services, controllers, components, networking (RemoteEvents/RemoteFunctions), dependency injection, lifecycle events, or working with Flamework decorators, macros, and configuration.

This skill should be used when importing Foundry classes, registering sheets, loading templates, enriching HTML, or using any Foundry API that has moved to namespaces. Covers compat wrappers, deferred sheet registration, and the modern-first fallback pattern.

Generate comprehensive tests for Zustand stores with nested immutable updates, async actions, and persistence. Use when creating or modifying stores, writing tests, or debugging state issues. Keywords: zustand, store, testing, state, vitest, mock.

Refine requirements from discoveries during TDD/BDD implementation. Captures edge cases, race conditions, and business rules discovered by developers. Enables requirements refinement loop. Use when developers discover missing requirements during coding.

claude-plugin 프로젝트 개발 가이드라인, 레퍼런스 패턴, 프로젝트 구조 조회. Use when Claude needs to (1) Look up development principles (P1-P4, DRY, KISS, YAGNI, SOLID), (2) Find reference patterns for Hooks/Agents/Commands creation, (3) Understand project structure and file locations, (4) Learn how to create Skills/Hooks/Agents/Commands, or (5) Delegate to claude-code-guide for official Claude Code documentation

Create, organize, and prioritize tasks from briefs or brain dumps. Sync with Taskmaster MCP. Use to plan work, track status, and pick next steps.

Search the web using Tavily API for high-quality, AI-optimized results. Use when the agent needs to find current information, verify facts, research topics, or answer questions requiring web data. Keywords: search, web, internet, lookup, find, research, current events, facts.

Interpretive guidance for Python code quality using ruff (modern) or pylint+isort+black (traditional). Use when linting Python files, configuring Python tools, troubleshooting lint errors, or understanding tool selection.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Build RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M context), MiniMax-M2. Use for document Q&A, knowledge bases, and agentic RAG. Covers LangChain, LlamaIndex, ChromaDB, and embedding models.

Builds accessible UI components with Headless UI primitives for React and Vue. Use when creating custom-styled dropdowns, modals, tabs, or other interactive components with full accessibility support.

Runs Google Lighthouse audits using Playwright for SEO, Performance, Accessibility, and Best Practices scoring. Supports both URLs and local HTML files. Use when user mentions "Lighthouse", "page speed", "performance audit", "Core Web Vitals", "CWV", or needs comprehensive web performance analysis.