ai-product
Guidelines for building and scaling production AI features with reliability in mind.
Install
mkdir -p .claude/skills/ai-product && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5844" && unzip -o skill.zip -d .claude/skills/ai-product && rm skill.zipInstalls to .claude/skills/ai-product
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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.Key capabilities
- →Implement structured output with schema validation
- →Stream LLM responses for progress indication
- →Version prompts within code
- →Calculate token usage before API calls
How it works
It applies engineering patterns to LLM integration by treating prompts as code and enforcing validation layers to prevent hallucinations and inefficient token usage.
Inputs & outputs
When to use ai-product
- →Designing RAG architecture for applications
- →Implementing input sanitization for prompts
- →Optimizing token costs for LLM features
- →Building regression suites for prompts
About this skill
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
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: |
When not to use it
- →Synchronous request handlers
- →Unstructured output parsing
Limitations
- →Requires manual validation implementation
- →Sensitive to context window limits
How it compares
It prioritizes production-grade validation and safety patterns over simple demo-oriented implementations.
Compared to similar skills
ai-product side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ai-product (this skill) | 1 | 6mo | No flags | Advanced |
| prompt-caching | 14 | 6mo | No flags | Intermediate |
| dspy | 4 | 7mo | Review | Intermediate |
| llm-app-patterns | 3 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by davila7
View all by davila7 →You might also like
prompt-caching
davila7
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.
dspy
davila7
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
llm-app-patterns
davila7
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
tool-design
muratcankoylan
This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.
engineering-advanced-skills
alirezarezvani
25 advanced POWERFUL-tier engineering skills covering agent design, RAG architecture, MCP servers, CI/CD pipelines, database design, observability, security auditing, release management, and platform operations. Works with Claude Code, Codex CLI, and OpenClaw.
exa-reference-architecture
jeremylongshore
Implement Exa reference architecture with best-practice project layout. Use when designing new Exa integrations, reviewing project structure, or establishing architecture standards for Exa applications. Trigger with phrases like "exa architecture", "exa best practices", "exa project structure", "how to organize exa", "exa layout".