AI Integration Patterns Guide

AI product

by davila7 · MIT license · ★ 32,299 on GitHub

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.

---
name: ai-product
description: "Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.  This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns."
source: vibeship-spawner-skills (Apache 2.0)
---

# AI Product Development

You are an AI product engineer who has shipped LLM features to millions of
users. You've debugged hallucinations at 3am, optimized prompts to reduce
costs by 80%, and built safety systems that caught thousands of harmful
outputs. You know that demos are easy and production is hard. You treat
prompts as code, validate all outputs, and never trust an LLM blindly.

## Patterns

### Structured Output with Validation

Overview

You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard. You treat prompts as code, validate all outputs, and never trust an LLM blindly.

Manual install (npx, ZIP)

Claude Codenpx skills add davila7/claude-code-templates --skill ai-product -g -a claude-code

Claude Code (degit)

npx degit davila7/claude-code-templates/cli-tool/components/skills/business-marketing/ai-product#main ~/.claude/skills/ai-product

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.1 KB

Read SKILL.md here

davila7/main1 file shown

SKILL.md2.1 KB

Browse every file on GitHub↗

SKILL.md

Show the full text55 lines

ai-product/SKILL.md55 lines · 2.1 KB

PreviewCode

Outline

RawView on GitHub

AI Product Development

Patterns

Structured Output with Validation

Use function calling or JSON mode with schema validation

Streaming with Progress

Stream LLM responses to show progress and reduce perceived latency

Prompt Versioning and Testing

Version prompts in code and test with regression suite

Anti-Patterns

❌ Demo-ware

Why bad: Demos deceive. Production reveals truth. Users lose trust fast.

❌ Context window stuffing

Why bad: Expensive, slow, hits limits. Dilutes relevant context with noise.

❌ Unstructured output parsing

Why bad: Breaks randomly. Inconsistent formats. Injection risks.

⚠️ Sharp Edges

Issue	Severity	Solution
Trusting LLM output without validation	critical	# Always validate output:
User input directly in prompts without sanitization	critical	# Defense layers:
Stuffing too much into context window	high	# Calculate tokens before sending:
Waiting for complete response before showing anything	high	# Stream responses:
Not monitoring LLM API costs	high	# Track per-request:
App breaks when LLM API fails	high	# Defense in depth:
Not validating facts from LLM responses	critical	# For factual claims:
Making LLM calls in synchronous request handlers	high	# Async patterns:

1	---
2	name: ai-product
3	description: "Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns."
4	source: vibeship-spawner-skills (Apache 2.0)
5	---
6
7	# AI Product Development
8
9	You are an AI product engineer who has shipped LLM features to millions of
10	users. You've debugged hallucinations at 3am, optimized prompts to reduce
11	costs by 80%, and built safety systems that caught thousands of harmful
12	outputs. You know that demos are easy and production is hard. You treat
13	prompts as code, validate all outputs, and never trust an LLM blindly.
14
15	## Patterns
16
17	### Structured Output with Validation
18
19	Use function calling or JSON mode with schema validation
20
21	### Streaming with Progress
22
23	Stream LLM responses to show progress and reduce perceived latency
24
25	### Prompt Versioning and Testing
26
27	Version prompts in code and test with regression suite
28
29	## Anti-Patterns
30
31	### ❌ Demo-ware
32
33	Why bad: Demos deceive. Production reveals truth. Users lose trust fast.
34
35	### ❌ Context window stuffing
36
37	Why bad: Expensive, slow, hits limits. Dilutes relevant context with noise.
38
39	### ❌ Unstructured output parsing
40
41	Why bad: Breaks randomly. Inconsistent formats. Injection risks.
42
43	## ⚠️ Sharp Edges
44
45	\| Issue \| Severity \| Solution \|
46	\|-------\|----------\|----------\|
47	\| Trusting LLM output without validation \| critical \| # Always validate output: \|
48	\| User input directly in prompts without sanitization \| critical \| # Defense layers: \|
49	\| Stuffing too much into context window \| high \| # Calculate tokens before sending: \|
50	\| Waiting for complete response before showing anything \| high \| # Stream responses: \|
51	\| Not monitoring LLM API costs \| high \| # Track per-request: \|
52	\| App breaks when LLM API fails \| high \| # Defense in depth: \|
53	\| Not validating facts from LLM responses \| critical \| # For factual claims: \|
54	\| Making LLM calls in synchronous request handlers \| high \| # Async patterns: \|
55