XueHua-s

Expert product design covering UI/UX design, design systems, prototyping, user research, and design thinking. Use when creating user journey maps, building wireframes, defining design tokens and component systems, planning usability tests, or establishing design principles for a product.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Design or review the OUCHN AI exam answer-tool architecture. Use when planning provider tool calling, tool-envelope fallback, DOM answer execution tools, error feedback, or refactoring AIResponse-driven answer filling into browser-safe tool execution.

Anthropic Messages API client patterns for Tampermonkey userscripts (browser-side fetch, vision support, error mapping)

Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task. Also triggered by SDD模式, sdd:plan, or /plan-task.

LobeHub Zustand store conventions: public/internal/dispatch action layers, optimistic update pattern, slice composition via `flattenActions`, and class-based action migration. Use whenever working under `src/store/**`, adding a `createXxxSlice`, writing `internal_*` or `internal_dispatch*` actions, designing `messagesMap`/`topicsMap` reducers, refactoring a `StateCreator` object slice into a `XxxActionImpl` class, or debugging stale store reads. Triggers on `useChatStore`/`useUserStore`/`useGlobalStore`, `createStore`, `flattenActions`, `StoreSetter`, `internal_dispatch`, 'add an action', 'zustand selector', 'store slice', 'class action', 'optimistic update'.

Guard cross-package architecture for RaidenShinBoot. Use when changes affect API contracts, bot/server conversation behavior, Drizzle schema, vector memory, shared persona logic, environment variables, or validation gates.

Navigate the RaidenShinBoot TypeScript monorepo. Use for package ownership, entry points, workspace scripts, dependency placement, environment files, and validation command selection across shared, database, server, bot, and panel.

Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task. Also triggered by SDD模式, sdd:plan, or /plan-task.

Standards for RaidenShinBoot admin panel work. Use for React 19, Refine v4, Tailwind CSS v4, Hono typed client integration, runtime status UX, resource tables, dashboard components, and panel validation.

Skill for building with the Astro web framework. Helps create Astro components and pages, configure SSR adapters, set up content collections, deploy static sites, and manage project structure and CLI commands. Use when the user needs to work with Astro, mentions .astro files, asks about static site generation (SSG), islands architecture, content collections, or deploying an Astro project.

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

Manage software complexity through deep modules, information hiding, and strategic programming. Use when the user mentions "module design", "API too complex", "shallow class", "complexity budget", or "strategic vs tactical". Covers deep vs shallow modules, red flags for complexity, and comments as design documentation. For code quality, see clean-code. For boundaries, see clean-architecture.

面向 Astro + React 项目的稳健开发规范，目标是约束实现过程并产出健壮代码。用于功能开发、缺陷修复、重构落地、边界条件处理、异常恢复、类型与测试补强、以及依赖选择决策；要求先读取 package.json，优先复用现有依赖，避免引入脆弱实现与高风险改动。

Manage software complexity through deep modules, information hiding, and strategic programming. Use when the user mentions "module design", "API too complex", "shallow class", "complexity budget", or "strategic vs tactical". Covers deep vs shallow modules, red flags for complexity, and comments as design documentation. For code quality, see clean-code. For boundaries, see clean-architecture.

fast-md5-web 全局架构与改造规范。用于跨 `src/*`、`wasm/*`、`example/test-fast-md5/*`、`__test/*`、`scripts/*` 的功能迭代、接口重构、性能优化、并发与内存治理，并按《软件设计的哲学》原则直接实施代码改造时。默认全局提示词见 `references/global-prompt.md`。

fast-md5-web 项目结构与模块地图。用于定位代码、理解 TypeScript 库入口与 Worker 协作、Rust WASM 编译链路、example/test-fast-md5 测试应用边界、选择正确 package.json 与脚本目标，或在目录迁移后同步路径映射时。