# Apple Design Ai

> Design or review generative AI, recommendations, predictions, and machine-learning features in Apple apps, including transparency, correction, feedback, and non-AI fallback behavior.

- **Type:** Skill
- **Install:** `agentstack add skill-carlosziegler-apple-hig-skills-apple-design-ai`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [CarlosZiegler](https://agentstack.voostack.com/s/carlosziegler)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [CarlosZiegler](https://github.com/CarlosZiegler)
- **Source:** https://github.com/CarlosZiegler/apple-hig-skills/tree/main/skills/apple-design-ai

## Install

```sh
agentstack add skill-carlosziegler-apple-hig-skills-apple-design-ai
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Apple AI Experience Design

## Apply the skill

Begin with the user benefit and the consequence of an incorrect result. Decide whether the model is essential or complementary, reactive or proactive, and private or shared. Read the relevant AI reference before designing interaction details.

Specify inputs, uncertainty, generation or prediction states, editing, retry, dismissal, and recovery. Keep model output distinguishable from verified facts or completed actions. Separate suggesting an action from executing it, and preserve the user’s existing authorization boundaries.

Evaluate realistic failures and corrections as well as successful examples. Include a useful path when the feature is unavailable or declined. Present model-quality claims only with supporting evidence; UI wording cannot establish reliability.

## Topic references

Select the topic that matches the design decision; do not load this entire list by default.

- [Generative AI](references/generative-ai.md)
- [Machine learning](references/machine-learning.md)

## Source use

These references are original operational summaries of Apple’s public HIG, checked on 2026-09-08. They are guidance for design decisions, not a reproduced manual or a guarantee of App Store acceptance.

Read only the topic references relevant to the current task. Each links to the full official page. Consult that page for exact specifications, platform exceptions, assets, and version-sensitive behavior; use current official developer documentation for APIs and availability. If live documentation is unavailable, state the snapshot date and identify assumptions instead of inventing current requirements.

The user’s product goals, selected framework, and authorized scope remain controlling. Distinguish a source recommendation from a hard platform requirement and from your own proposed implementation.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [CarlosZiegler](https://github.com/CarlosZiegler)
- **Source:** [CarlosZiegler/apple-hig-skills](https://github.com/CarlosZiegler/apple-hig-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-carlosziegler-apple-hig-skills-apple-design-ai
- Seller: https://agentstack.voostack.com/s/carlosziegler
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.