Ai Product

This covers the gap between LLM demos and production systems. You get patterns for structured output validation, prompt versioning, RAG with hybrid search, and circuit breakers for API failures. The principles are practical: treat prompts like code with version control and tests, design for LLM latency with streaming, cache aggressively because costs add up fast. The sharp edges section is worth the price alone. It walks through actual failure modes like prompt injection and malformed JSON responses with specific fixes using Zod schemas and message separation. If you're shipping anything beyond a prototype that calls an LLM API, you'll recognize these problems immediately.

skills.sh installs: 843
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill ai-product --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Product Development

Choose AI only when it improves the target user task against an evaluated baseline.

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.

Detailed Guide

Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.

When to Use

Use this skill when the request clearly matches the capabilities and patterns described above.

Limitations

Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

SKILL.md on GitHub