A solid reference for building LLM-powered features that covers the practical stuff you'll actually need: prompt engineering patterns like few-shot and chain of thought, working with OpenAI and Anthropic APIs, streaming responses, and a complete RAG pipeline with chunking and vector search using Supabase. The error handling section alone is worth it, with retry logic and rate limit backoff that you'd otherwise write yourself. It's not trying to teach LLM fundamentals, just showing you the patterns that work when integrating AI into real applications. Good for anyone moving past tutorial code into production features.

skills.sh installs
314
GitHub stars
1.1K
last updated
Jun 3, 2026

Install

$ npx -y skills add skillcreatorai/ai-agent-skills --skill llm-application-dev --agent claude-code

Installs into .claude/skills of the current project.

Files

LLM Application Development

Prompt Engineering

Structured Prompts

const systemPrompt = `You are a helpful assistant that answers questions about our product.

RULES:
- Only answer questions about our product
- If you don't know, say "I don't know"
- Keep responses concise (under 100 words)
- Never make up information

CONTEXT:
{context}`;

const userPrompt = `Question: {question}`;

Few-Shot Examples

const prompt = `Classify the sentiment of customer feedback.

Examples:
Input: "Love this product!"
Output: positive

Input: "Worst purchase ever"
Output: negative

Input: "It works fine"
Output: neutral

Input: "${customerFeedback}"
Output:`;

Chain of Thought

const prompt = `Solve this step by step:

Question: ${question}

Let's think through this:
1. First, identify the key information
2. Then, determine the approach
3. Finally, calculate the answer

Step-by-step solution:`;

API Integration

OpenAI Pattern

import OpenAI from 'openai';

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

Sponsors

Details

Repository
github.com/skillcreatorai/ai-agent-skills
Category
AI & Agent Building
First seen
Jun 3, 2026

More from skillcreatorai/ai-agent-skills

All 30
1existential-birds avatarpydantic-ai-agent-creationexistential-birds/beagleCreate PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integ219skills.sh installs
2absolutelyskilled avatarai-agent-designabsolutelyskilled/absolutelyskilledai agent design140skills.sh installs
3neondatabase avatarneon-ai-gatewayneondatabase/agent-skillsOne API and one credential for frontier and open-source LLMs and embedding models, built into your Neon branch and powered by Databricks. Use when a user wants 39.8Kskills.sh installs
4github avataragentic-evalgithub/awesome-copilotPatterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluat10.3Kskills.sh installs
5github avataragent-governancegithub/awesome-copilotPatterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tool9.7Kskills.sh installs
6emblemcompany avataremblem-ai-agent-walletemblemcompany/agent-skillsConnect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana, Ethereum, Base, BSC, Poly8.8Kskills.sh installs