# ai-dev

> Implement AI features safely, with structured outputs, evaluation hooks, and secure secret handling.

- Author: Berget1411
- Repository: Berget1411/notecards
- Version: 20260124153332
- Stars: 0
- Forks: 0
- Last Updated: 2026-02-07
- Source: https://github.com/Berget1411/notecards
- Web: https://mule.run/skillshub/@@Berget1411/notecards~ai-dev:20260124153332

---

---
name: ai-dev
description: Implement AI features safely, with structured outputs, evaluation hooks, and secure secret handling.
compatibility: opencode
metadata:
  focus: ai-features
  safety: secrets
---

## What I do

- Define prompt templates and structured output contracts
- Keep API keys in `.env` or `.dev.vars`, never in code
- Add safeguards for cost, latency, and user data handling
- Provide minimal eval hooks or smoke tests for AI behaviors

## When to use me

Use this skill when adding AI integrations, prompt logic, or model-driven features.