skills.rest
gonzoblasco
gonzoblascoCOMMUNITY
Explore all skills by this author →
𝕏@gonzoblascoGitHub

llm-app-patterns

Consolidate production-ready patterns for LLM applications with RAG pipelines and agent architectures.

Updated Aug 23, 2026
Search Tags:#llm#rag#patterns#agents#observability#llmops
One-click install
npx skills add https://github.com/gonzoblasco/antigravity-developer-stack --skill llm-app-patterns
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-app-patterns
Source: https://github.com/gonzoblasco/antigravity-developer-stack/tree/main/ai-agents/llm-app-patterns
Command: npx skills add https://github.com/gonzoblasco/antigravity-developer-stack --skill llm-app-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides production-ready patterns to accelerate the design, development, and deployment of LLM-powered applications. It helps teams avoid reinventing core patterns and promotes consistency across projects.

Core Features & Use Cases

  • RAG Pipeline Architecture: guidance on ingestion, embedding, retrieval, and generation with practical examples.
  • Agent Architectures: patterns like ReAct, Function Calling, Plan-and-Execute, and Multi-Agent collaboration.
  • Prompt IDEs & Versioning: templates, variables, versioning, and chaining prompts to streamline development.
  • LLMOps & Observability: metrics, logging, tracing, and evaluation frameworks to monitor production systems.
  • Production Patterns: caching, rate limiting, and fallback strategies to improve reliability.
  • Use Case: architect end-to-end AI assistants, enterprise knowledge bases, and automated data-processing pipelines.

Quick Start

Start by selecting a RAG pattern for your data, implement a compatible agent pattern for the task, wire up a prompt template, and enable LLM observability to begin iterative improvement.

Frequently Asked Questions about llm-app-patterns

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

FAQPage Schema
What are the standard production patterns for building LLM applications?▼

Standard production patterns for LLM applications include RAG pipeline architectures, agent collaboration frameworks, prompt versioning, and LLMOps observability to ensure reliable deployment and monitoring.

How do I architect a RAG pipeline for ingestion and retrieval?▼

To architect a RAG pipeline, implement data ingestion, generate embeddings, execute retrieval, and perform generation. These RAG pipeline patterns provide structure for building enterprise knowledge bases and AI assistants.

When should I use agent architectures like ReAct or Plan-and-Execute?▼

Use agent architectures like ReAct, Function Calling, or Plan-and-Execute when your LLM application requires multi-step reasoning, tool utilization, or multi-agent collaboration to automate complex data processing tasks.

What's the best way to monitor LLM applications in production?▼

The best way to monitor LLM applications in production is implementing LLMOps observability patterns, which utilize metrics, logging, tracing, and evaluation frameworks to track system performance and enable iterative improvement.

How do I improve LLM application reliability with caching and fallback strategies?▼

Improve LLM application reliability by implementing production patterns like caching to reduce latency, rate limiting to manage API usage, and fallback strategies to maintain service availability during high load.

Do I need a prompt IDE to manage prompt templates and versioning?▼

A prompt IDE is needed to manage prompt templates, variables, and versioning effectively. It streamlines development by allowing you to chain prompts and iterate on prompt design within your LLM application workflow.

Related Skills

Explore More Software Engineering Skills→
patornpatorn

langchain-rag

Build end-to-end RAG pipelines with LangChain document loaders, embeddings, and vector stores.

Community
Advanced
sorodriguezzsorodriguezz

Emit Telemetry Data to an OpenTelemetry-Compatible Monitoring Tool

Export metrics, logs, and traces from InterSystems IRIS via OTLP/HTTP.

Community
Advanced
yusufcmgyusufcmg
1

rag-implementation

Implement Retrieval-Augmented Generation systems with vector databases and semantic search.

Community
Advanced
frankxaifrankxai

AI Architecture Patterns

Select and implement enterprise AI architecture patterns across AWS, GCP, Azure, and OCI.

Community
Advanced