What RAG retrieval strategies are covered?

The skill covers basic semantic search, hybrid search (combining vector and keyword search), multi-query retrieval for better recall, and contextual compression for cost efficiency.

Does this skill include guidance on vector databases?

Yes, it provides a selection matrix for popular vector databases like Pinecone, Weaviate, ChromaDB, and pgvector based on scale, cost, and use case.

What is the primary focus of the llm-app-patterns skill?

It provides architectural blueprints and implementation patterns for production-grade AI applications, specifically covering RAG (Retrieval-Augmented Generation) and agentic workflows.

Can I use this to build multi-agent systems?

Absolutely. It includes patterns for multi-agent collaboration where specialized agents (like researchers and analysts) work together under a coordinator agent.

Does it provide support for prompt management?

Yes, it includes patterns for prompt templates with variable injection, few-shot example management, and prompt versioning for better lifecycle control.

LLM Application Patterns

Name: LLM Application Patterns
Author: claudiodearaujo

byclaudiodearaujo

0•

Data Science & ML

Implements production-ready architectures for LLM applications, including RAG pipelines, autonomous agents, and prompt engineering workflows.

This skill provides a comprehensive architectural framework for developers building sophisticated AI-powered applications. It codifies industry best practices for Retrieval-Augmented Generation (RAG) pipelines, ranging from document ingestion and semantic chunking to advanced retrieval strategies like hybrid search and contextual compression. Additionally, it offers detailed implementation patterns for autonomous agents using ReAct, function calling, and multi-agent collaboration, ensuring your AI applications are robust, scalable, and production-ready.

Key Features

01Prompt IDE patterns for versioning, templating, and A/B testing

020 GitHub stars

03Standardized function calling and tool integration templates

04Advanced retrieval patterns such as Hybrid Search and Multi-query Retrieval

05Autonomous agent blueprints for ReAct, Plan-and-Execute, and Multi-agent teams

06Comprehensive RAG pipeline architectures including chunking and embedding strategies

Use Cases

01Developing complex autonomous agents capable of multi-step reasoning and external tool usage.

02Setting up professional LLMOps workflows for prompt management and response monitoring.

03Designing a scalable RAG system to ground LLM responses in proprietary corporate data.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add claudiodearaujo/sistema-de-narra-o-de-livro-front llm-app-patterns

For use in Claude.ai and ChatGPT

Download Skill