skills.rest
LuisSambrano
LuisSambranoCOMMUNITY
Explore all skills by this author →
𝕏@luissambrano_uxGitHub

llm-patterns

Provide production-ready patterns and code examples for LLM applications.

7|2|Updated Jan 28, 2026
Search Tags:#prompt engineering#llm#rag#agents#llmops#ai patterns
One-click install
npx skills add https://github.com/LuisSambrano/antigravity-config --skill llm-patterns-luissambrano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-patterns
Source: https://github.com/LuisSambrano/antigravity-config/tree/main/skills/2-ai/llm-patterns
Command: npx skills add https://github.com/LuisSambrano/antigravity-config --skill llm-patterns-luissambrano

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides battle-tested patterns and code examples for building robust, production-ready Large Language Model (LLM) applications, addressing common challenges in RAG, agent design, and LLMOps.

Core Features & Use Cases

  • RAG Pipelines: Implement efficient document ingestion, embedding, retrieval, and generation strategies.
  • Agent Architectures: Explore and implement patterns like ReAct, Function Calling, and Plan-and-Execute.
  • Prompt Engineering: Utilize templates, versioning, and chaining for effective prompt management.
  • LLMOps: Understand key metrics, logging, tracing, and evaluation techniques for monitoring and improving LLM performance.
  • Use Case: You need to build a chatbot that answers questions based on your company's internal documentation. This Skill provides the RAG patterns to ingest your documents, embed them, and retrieve relevant context to ground the LLM's responses.

Quick Start

Use the llm-patterns skill to implement a basic RAG pipeline for document question answering.

Frequently Asked Questions about llm-patterns

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a RAG pipeline for document question answering?▼

To build a RAG pipeline for document question answering, you need to implement document ingestion, generate embeddings, retrieve relevant context, and pass it to the LLM for generation. This pattern grounds responses in your internal documentation.

What are the common agent architectures for LLM applications?▼

Common agent architectures for LLM applications include ReAct, Function Calling, and Plan-and-Execute patterns. These allow LLMs to use tools, plan sequences, and execute multi-step reasoning to solve complex tasks.

How does prompt engineering handle template versioning and chaining?▼

Prompt engineering handles template versioning and chaining by structuring prompts into reusable templates, tracking iterations, and linking multiple prompts together. This ensures consistent prompt management across different LLM application features.

What metrics should I track for LLMOps observability?▼

For LLMOps observability, you should track key performance metrics, implement logging, set up tracing, and conduct evaluations. These techniques monitor LLM behavior and identify performance degradation in production environments.

Do I need LLMOps monitoring to deploy a production-ready LLM application?▼

Yes, you need LLMOps monitoring to deploy a production-ready LLM application. Setting up observability with logging, tracing, and evaluation ensures your RAG pipelines and agents perform reliably and allows for continuous improvement.

Related Skills

Explore More Software Engineering Skills→
patrykkopycinskipatrykkopycinski
6

rag-pipeline

Set up a RAG pipeline with Elasticsearch for vector retrieval.

Community
Intermediate
timequitytimequity
6

devops

Automate containerized deployments using Docker and CI/CD pipelines.

Official
Advanced
OmniNode-aiOmniNode-ai
3

observability

Log agent actions and execution lifecycles to Kafka and PostgreSQL.

Official
Advanced
HemantSudarshanHemantSudarshan

llm-app-patterns

Apply modular patterns for chat interfaces, tool use, and guardrails in LLM applications.

Community
Advanced