Llm App Patterns

If you're building LLM applications beyond simple prompts, this gives you the architectural patterns you actually need. It covers RAG pipeline design with practical chunking strategies and retrieval methods (semantic, hybrid, multi-query), agent architectures like ReAct and function calling, and the operational patterns for running these systems in production. The code examples are production-oriented, not toy demos. Useful when you're past the prototype phase and need to make decisions about vector databases, embedding models, or which agent pattern fits your use case. It's basically the architecture documentation you'd build internally after shipping a few LLM features, packaged as reusable patterns.

skills.sh installs: 700
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill llm-app-patterns --agent claude-code

Installs into .claude/skills of the current project.

Files

🤖 LLM Application Patterns

Architecture and integration sketches for LLM applications, with explicit retrieval, tool, privacy and verification boundaries.

Detailed Guide

Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.