AI Product Development
SkillAI & modelsThis is a skill that guides an AI agent through building AI features that hold up in production. It covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX, and cost optimization. The agent draws on it to advise on structured outputs with schema validation, streaming responses, and prompt versioning with regression tests.
Use AI Product Development in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add AI Product Development and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the AI Product Development skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have an AI agent that can load skills and a project where you are adding an LLM feature.
What your AI can do with it
- Advise on structured outputs using function calling or JSON mode with schema validation
- Recommend streaming LLM responses to show progress and reduce perceived latency
- Guide prompt versioning in code with a regression test suite
- Flag anti-patterns like context window stuffing and unstructured output parsing
- Warn against trusting unvalidated LLM output and unsanitized user input in prompts
- Point out synchronous LLM calls that break under failure
Getting started
- Have an AI agent that can load skills and a project where you are adding an LLM feature.
- Add the skill to the agent's available skills so it can be loaded when working on AI product code.
- Describe the feature you are building, such as a RAG pipeline or a chat response, and ask the agent to apply the skill.
- Review the patterns and anti-patterns the agent surfaces and adjust your implementation before shipping.
What this skill tells your AI
The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/business-marketing/ai-product/SKILL.md and read by ahel’s review.
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: |
Signals
- GitHub stars
- 32k
- Forks
- 4k
- Last commit
- Oct 2026
Others that do the same job
Questions
- Does it cover RAG architecture?
- Yes. The skill covers RAG architecture along with LLM integration patterns, prompt engineering that scales, AI UX, and cost optimization.
- What does it say about prompt engineering?
- It treats prompts as code: version them in code and test them with a regression suite. It also warns against stuffing the context window, which is expensive, slow, and dilutes relevant context.
Advanced
- Item type
- skill
- Key
ai-product-davila7- Source
- github.com/davila7/claude-code-templates
github.com/davila7/claude-code-templates
More in AI & models
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsai-first-engineering
Skill · affaan-m
More in AI & models