Verified:GitHub

@tank/llm-app-patterns

Name: @tank/llm-app-patterns
Availability: InStock
Author: tankpkg

Provides patterns for building LLM-powered apps including RAG, tool-using agents, structured output extraction, streaming responses, and cost optimization.

1|1|Updated Feb 20, 2026

Search Tags:#llm #rag #agents #streaming #cost optimization #structured output #llmops

Ready to run

npx skills add https://github.com/tankpkg/skills --skill tank-llm-app-patterns

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: @tank/llm-app-patterns
Source: https://github.com/tankpkg/skills/tree/main/skills/llm-app-patterns
Command: npx skills add https://github.com/tankpkg/skills --skill tank-llm-app-patterns

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps developers build robust, production-ready applications powered by Large Language Models, addressing common challenges in areas like data retrieval, agentic behavior, and user experience.

Core Features & Use Cases

RAG Systems: Implement effective Retrieval-Augmented Generation for accurate, context-aware responses.
Tool-Using Agents: Design and deploy agents that can leverage external tools and APIs.
Structured Output: Ensure LLMs return data in predictable, machine-readable formats.
Streaming Responses: Improve user experience with real-time output delivery.
Cost Optimization: Strategies to manage and reduce LLM inference costs.
Use Case: Integrate a RAG system into your customer support chatbot to provide accurate answers based on your company's knowledge base, or build an agent that can schedule meetings by calling calendar APIs.

Quick Start

Use the llm-app-patterns skill to implement a RAG system that answers questions from a provided document.

Frequently Asked Questions about @tank/llm-app-patterns

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

FAQPage Schema

How do I implement Retrieval-Augmented Generation (RAG) for a production LLM application?▼

To implement Retrieval-Augmented Generation (RAG) for production LLM applications, apply established patterns for context-aware data retrieval, ensuring accurate responses by grounding the model with external knowledge bases.

What is the best way to ensure LLMs return structured output in a machine-readable format?▼

The best way to ensure LLMs return structured output is by applying extraction patterns that enforce predictable, machine-readable formats, allowing downstream systems to reliably parse the generated data.

How do tool-using agents work in LLM applications?▼

Tool-using agents in LLM applications work by integrating patterns that allow the model to autonomously leverage external tools and APIs, enabling complex actions like scheduling meetings or fetching real-time data.

What strategies help with LLM cost optimization and managing inference expenses?▼

Strategies for LLM cost optimization involve applying specific patterns to manage and reduce inference expenses, balancing computational overhead with response quality to maintain efficient operational costs.

How do I add streaming responses to an LLM application to improve user experience?▼

To add streaming responses to an LLM application, implement real-time output delivery patterns that incrementally send generated text to the client, significantly improving perceived responsiveness and user experience.