Does it recommend specific tools for LLM applications?

The skill provides comparative data and use cases for popular vector databases like Pinecone, Weaviate, and PGVector, along with various embedding model options.

Can this skill help with building multi-agent systems?

Yes, it includes architectural patterns for agent teams, including coordinator, researcher, and critic roles for solving complex, collaborative tasks.

What types of RAG strategies does this skill cover?

It provides patterns for fixed-size, semantic, and recursive chunking, as well as hybrid search, multi-query retrieval, and contextual compression strategies.

What agent architectures are included?

It covers the ReAct pattern (Reasoning + Acting), Function Calling patterns, Plan-and-Execute workflows, and Multi-Agent collaboration frameworks.

LLM Application Patterns

Name: LLM Application Patterns
Author: claudiodearaujo

byclaudiodearaujo

0•

データサイエンスとML

Provides production-ready architectural patterns and implementation guides for building robust LLM applications, RAG pipelines, and AI agents.

This skill serves as a comprehensive reference for developers designing sophisticated AI systems, offering modular patterns for RAG orchestration, autonomous agent behaviors, and prompt management. It bridges the gap between basic LLM calls and production-grade applications by detailing specific strategies for document chunking, vector search, multi-agent collaboration, and observability, making it an essential companion for building scalable and reliable AI-driven software based on industry best practices.

主な機能

01Detailed autonomous agent patterns such as ReAct, Plan-and-Execute, and Function Calling

02Implementation guides for multi-agent collaboration and task coordination

03Prompt engineering patterns for templating, versioning, and A/B testing

04Comparative analysis of vector databases and embedding models for production use

050 GitHub stars

06Comprehensive RAG pipeline architectures including chunking and retrieval strategies

ユースケース

01Building complex AI agents capable of using tools and reasoning through multi-step tasks

02Implementing professional LLMOps workflows for prompt management and system monitoring

03Designing a scalable Retrieval-Augmented Generation (RAG) system for internal documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add claudiodearaujo/izacenter llm-app-patterns

For use in Claude.ai and ChatGPT

Download Skill