Llm App Patterns

This is a solid reference for building production LLM applications, covering the practical patterns you'll actually need. It walks through RAG pipelines with real chunking strategies and retrieval methods (semantic, hybrid, multi-query), plus agent architectures like ReAct and function calling with working code examples. The vector database comparison is helpful when you're choosing between Pinecone, Weaviate, ChromaDB, or pgvector. Use this when you're past the hello-world phase and need to understand how to structure a RAG system properly, decide between agent patterns, or set up retrieval that doesn't embarrass you in production. The code samples are Python-focused and look like they came from someone who's actually shipped this stuff.

skills.sh installs: 326
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill llm-app-patterns --agent claude-code

Installs into .claude/skills of the current project.

Files

🤖 LLM Application Patterns

Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.

When to Use This Skill

Use this skill when:

Designing LLM-powered applications
Implementing RAG (Retrieval-Augmented Generation)
Building AI agents with tools
Setting up LLMOps monitoring
Choosing between agent architectures

1. RAG Pipeline Architecture

Overview

RAG (Retrieval-Augmented Generation) grounds LLM responses in your data.

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│   Ingest    │────▶│   Retrieve  │────▶│   Generate  │
│  Documents  │     │   Context   │     │   Response  │
└─────────────┘     └─────────────┘     └─────────────┘
      │                   │                   │
      ▼                   ▼                   ▼
 ┌─────────┐       ┌───────────┐       ┌───────────┐
 │ Chunking│       │  Vector   │       │    LLM    │
 │Embedding│       │  Search   │       │  + Context│
 └─────────┘       └───────────┘       └───────────┘