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.
Install
$ agentstack add skill-carlosziegler-apple-hig-skills-apple-design-ai ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-carlosziegler-apple-hig-skills-apple-design-ai) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
- Source: CarlosZiegler/apple-hig-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.