前端開發

Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.

Frontend design patterns that avoid AI slop and create polished, professional interfaces.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

2025 UI design trends and patterns including glassmorphism, bento grids, micro-animations, and modern aesthetics. Essential for creating visually stunning, premium web interfaces.

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Next.js 14+ best practices with App Router, Server Components, and modern patterns.

Expert guidance for Plang programming language (plang.is). Use when the user asks about Plang syntax, wants to generate Plang code, needs help debugging Plang goals, wants to understand Plang patterns, or is working on Plang projects. Plang is a natural language pseudo-code language with goal-based architecture using SQLite databases.

Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags.

This skill should be used when the user asks to "configure TypeScript", "fix type errors", "use dayjs", "add type definitions", "set up React with TypeScript", mentions ".ts" or ".tsx" files, or asks about TypeScript best practices or TypeScript-specific tooling.

Configures Neon Serverless Driver for Next.js, Vercel Edge Functions, AWS Lambda, and other serverless environments. Installs @neondatabase/serverless, sets up environment variables, and creates working API route examples with TypeScript types. Use when users need to connect their application to Neon, fetch or query data from a Neon database, integrate Neon with Next.js or serverless frameworks, or set up database access in edge/serverless environments where traditional PostgreSQL clients don't work.

Sets up the full Neon JS SDK with unified auth and PostgREST-style database queries. Configures auth client, data client, and type generation. Use when building apps that need both authentication and database access in one SDK.

Sets up Neon Auth for your application. Configures authentication, creates auth routes, and generates UI components. Use when adding authentication to Next.js, React SPA, or Node.js projects.

分析一段时间内健康数据的趋势和模式。关联药物、症状、生命体征、化验结果和其他健康指标的变化。识别令人担忧的趋势、改善情况，并提供数据驱动的洞察。当用户询问健康趋势、模式、随时间的变化或"我的健康状况有什么变化？"时使用。支持多维度分析（体重/BMI、症状、药物依从性、化验结果、情绪睡眠），相关性分析，变化检测，以及交互式HTML可视化报告（ECharts图表）。

Implements user stories, writes clean tested code, follows best practices. Trigger keywords implement story, dev story, code, implement, build feature, fix bug, write tests, code review, refactor

Z.AI CLI providing:- Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V)- Search: real-time web search with domain/recency filtering- Reader: web page to markdown extraction- Repo: GitHub code search and reading via ZRead- Tools: MCP tool discovery and raw calls- Code: TypeScript tool chainingUse for visual content analysis, web search, page reading, or GitHub exploration. Requires Z_AI_API_KEY.