Can I use this for prompt management?

Yes, it features standardized patterns for prompt templates with variables, few-shot examples, and prompt versioning registries.

How does this skill help with RAG implementation?

It provides optimized configurations for document chunking, vector database selection, and advanced retrieval strategies like hybrid search and contextual compression.

Is this skill based on specific industry tools?

The patterns are inspired by industry best practices and frameworks like Dify to ensure production-grade reliability and scalability.

Which AI agent architectures are supported?

The skill includes patterns for ReAct (Reasoning + Acting), Function Calling, Plan-and-Execute, and collaborative Multi-Agent team structures.

LLM Application Patterns

Name: LLM Application Patterns
Author: claudiodearaujo

byclaudiodearaujo

0•

データサイエンスとML

Implements production-ready architectures for LLM-powered applications, including RAG pipelines, agentic workflows, and LLMOps monitoring.

This skill provides a comprehensive library of industry-standard patterns for building sophisticated AI applications. It guides developers through the complexities of Retrieval-Augmented Generation (RAG) by offering optimized strategies for document ingestion, vector storage, and hybrid retrieval. Additionally, it streamlines the creation of AI agents using ReAct, function calling, and multi-agent coordination frameworks, ensuring that LLM implementations are scalable, observable, and grounded in best practices derived from leading industry tools.

主な機能

010 GitHub stars

02Pre-defined agent architectures like ReAct, Plan-and-Execute, and Multi-Agent teams

03Advanced retrieval methods including hybrid search and multi-query expansion

04End-to-end RAG pipeline configuration including chunking and embedding strategies

05Prompt engineering patterns for templating, versioning, and A/B testing

06LLMOps monitoring setup for production-grade observability and tracking

ユースケース

01Architecting scalable RAG systems for enterprise document search and retrieval

02Building autonomous AI agents capable of multi-step reasoning and tool integration

03Standardizing prompt management and AI observability workflows within development teams

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