Design e Frontend

Next.js framework development including App Router, Server Components, Server Actions, SSR, SSG, ISR, caching, data fetching, middleware, layouts, parallel routes, and module architecture for Next.js 13+/15/16. NOT for generic React patterns, hooks, or component logic (use react-development). NOT for UI/CSS design systems or visual styling (use frontend-design).

生成专业分镜图片提示词，适配扩散模型（FLUX/SDXL/Gemini）。校验质量后拆分为独立文件，或直接生成带产品描述的 Gemini 提示词模板。Use when 用户说"生成分镜提示词""校验分镜""拆分镜""分镜""分镜图"或提到视频分镜/镜头提示词/产品分镜模板。

Sequential-audit workflow for running a full UX review pass across an application or product. Walks through five phases — visual audit of design system adherence (frontend-design), navigation and information architecture review (navigation-design), microcopy and error-message audit (ux-writing), end-to-end journey validation (user-journey-design), and cross-product consistency check (consistency-s

Use when the user has a Session-view loop and wants to promote it to a full Arrangement, build sections (intro/verse/drop/break/outro), or extend a 4-bar idea into a 3-minute track. Examples - "turn this loop into a full song", "build me a 2-minute arrangement from this", "promote session to arrangement".

Exasol User Defined Functions (UDFs) and Script Language Containers (SLCs). Covers CREATE SCRIPT, SCALAR and SET functions, ExaIterator API, Python/Java/Lua/R scripts, BucketFS file access, GPU-accelerated UDFs, and building/deploying custom Script Language Containers with exaslct.

Audit and rewrite UI copy to remove AI slop — overlong button labels, hedging error messages, corporate filler, and passive voice in interface text. Use when asked to clean up UI text, deslop interface copy, fix AI-sounding buttons or error messages, audit microcopy for AI patterns, or humanize product UI. Trigger phrases: "deslop", "anti-slop", "remove AI slop from UI", "clean up button labels",

Applies The Agent's official brand colors and typography to any sort of artifact that may benefit from having The Agent's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.

Interactive tutorial that walks the user through designing, writing, testing, and distributing their own Skill for Claude. Use when the user says "teach me how to build a skill", "help me make a skill", "walk me through skill creation", "I want to learn skills", "/build-a-skill", or asks about SKILL.md structure, YAML frontmatter for skills, progressive disclosure, skill distribution, or how to pa

Integrates multiple components inside a single Claude Code plugin — skills, hooks, MCPs, subagents, and commands — using the canonical directory layout and path substitution variables. Use when building a multi-component plugin, combining skills and hooks, laying out the plugin directory structure, working with CLAUDE_PLUGIN_ROOT or CLAUDE_PLUGIN_DATA, choosing where to put shared scripts inside a

This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration. NOT for multi-agent coordination or agent handoffs (use multi-agent-patterns), NOT for agent memory

Writes a complete product spec for an AI-powered feature including user stories, model requirements, fallback behavior, and evaluation criteria.