agents

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterpr

所属插件包：llm-application-dev

Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and p

所属插件包：llm-application-dev

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applicati

所属插件包：llm-application-dev

Build AI assistant application with NLU, dialog management, and integrations

所属插件包：llm-application-dev

Create LangGraph-based agent with modern patterns

所属插件包：llm-application-dev

Optimize prompts for production with CoT, few-shot, and constitutional AI patterns

所属插件包：llm-application-dev

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizi

所属插件包：llm-application-dev

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides su

所属插件包：llm-application-dev

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI ag

所属插件包：llm-application-dev

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance,

所属插件包：llm-application-dev

This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug pr

所属插件包：llm-application-dev

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI,

所属插件包：llm-application-dev

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval p

所属插件包：llm-application-dev

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search

所属插件包：llm-application-dev