skills.rest
ketzal88
ketzal88COMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm-app-patterns

Implement production-grade LLM applications using reusable RAG, agent, prompt IDE, and LLMOps patterns.

Updated Mar 29, 2025
Search Tags:#llm#rag#patterns#agents#observability#prompt-engineering#llmops
One-click install
npx skills add https://github.com/ketzal88/gym-counter --skill llm-app-patterns-ketzal88
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-app-patterns
Source: https://github.com/ketzal88/gym-counter/tree/main/.claude/skills/llm-app-patterns
Command: npx skills add https://github.com/ketzal88/gym-counter --skill llm-app-patterns-ketzal88

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Production-ready patterns help teams design, build, and maintain scalable LLM applications by reusing battle-tested architectures and best practices.

Core Features & Use Cases

  • RAG pipelines with retrieval-augmented generation to ground outputs.
  • Agent architectures (ReAct, Plan-and-Execute, multi-agent collaboration) for complex tasks.
  • Prompt IDE patterns including templates, versioning, and chaining for rapid iteration.
  • LLMOps patterns for observability, monitoring, and reliability in production environments.
  • Guidance on selecting the right pattern for given tasks and project constraints.

Quick Start

Start by selecting a pattern that fits your task and adapt it into your project to accelerate delivery.

Frequently Asked Questions about llm-app-patterns

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

FAQPage Schema
What are the best production-ready patterns for building LLM applications?▼

Production-ready LLM application patterns provide reusable architectures for RAG pipelines, agent collaboration, and LLMOps monitoring to ensure scalable and reliable deployments.

How do I add observability and monitoring to my LLM pipelines?▼

You can add observability to LLM pipelines by applying LLMOps patterns that enforce clear abstractions and monitoring-ready components, ensuring reliable tracking across production environments.

How do I structure retrieval-augmented generation pipelines for production?▼

Structure retrieval-augmented generation pipelines using ready-made patterns that ground outputs through reusable components, accelerating delivery while maintaining clear architectural abstractions.

Which agent architecture should I choose for complex LLM tasks?▼

Choose agent architectures like ReAct, Plan-and-Execute, or multi-agent collaboration based on your specific task constraints, using pattern guidance to match the architecture to project needs.

Can I use prompt IDE patterns for prompt versioning and chaining?▼

Yes, prompt IDE patterns support prompt versioning, templating, and chaining to enable rapid iteration and clear abstraction management within your LLM application workflows.

When should I avoid using multi-agent collaboration patterns?▼

Avoid multi-agent collaboration patterns when your project constraints require simpler solutions; use the provided pattern selection guidance to evaluate whether complex agent architectures are necessary.

Related Skills

Explore More Software Engineering Skills→
havingautismhavingautism
190

using-git-worktrees

Create isolated git worktrees for feature development.

Community
Intermediate
matdev83matdev83

golang-observability

Implement logging, metrics, tracing, and alerting for Go applications.

Community
Advanced
NeoLabHQNeoLabHQ
1.3k

prompt-engineering

Design production LLM agent prompts and templates for RAG workflows.

Official
Basic
tanghuotanghuo

go-abstraction-discipline

Refactor Go code by removing thin wrappers, single-use helpers, and misplaced constants.

Community
Intermediate