AvdLee/SwiftUI-Agent-Skill is a portable set of expert guidance for AI coding tools that work with SwiftUI, Apple’s framework for building app interfaces. It helps teams and developers review, refactor, and write SwiftUI code involving state, view structure, performance, and newer visual APIs. The catalogue entries provide the skill and plugin instructions that agents use to apply this guidance.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AvdLee/SwiftUI-Agent-Skill --skill swiftui-expert-skillgit clone --depth 1 https://github.com/AvdLee/SwiftUI-Agent-SkillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/avdlee/swiftui-agent-skill/swiftui-expert-skill)<a href="https://agentmods.dev/skills/avdlee/swiftui-agent-skill/swiftui-expert-skill"><img src="https://agentmods.dev/badge/skills/avdlee/swiftui-agent-skill/swiftui-expert-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/avdlee/swiftui-agent-skill/swiftui-expert-skill"><img src="https://agentmods.dev/badge/skills/avdlee/swiftui-agent-skill/swiftui-expert-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00197 | $0.02701 |
| Opus 5.5 | $0.00079 | $0.01080 |
| Sonnet 5.5 | $0.00039 | $0.00540 |
| Haiku 4.5 | $0.00020 | $0.00270 |
Grade A, and why
swiftui-expert-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
6 near-identical copies found in the catalogue:
- swiftui-expert-skill — 100% identical, 65 lines differ
- swiftui-expert-skill — 98% identical, 71 lines differ
- swiftui-expert-skill — 97% identical, 72 lines differ
- swiftui-expert-skill — 97% identical, 72 lines differ
- swiftui-expert-skill — 95% identical, 71 lines differ
- swiftui-expert-skill — 94% identical, 63 lines differ
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI Expert Skill
Operating Rules
- Treat each
Viewtype as an invalidation boundary: give it only the data it reads and keep frequently changing dependencies close to the smallest affected subtree - Search
references/latest-apis.mdwhen writing, reviewing, or migrating API usage; look up only the APIs relevant to the task - Replace hard-deprecated APIs with modern equivalents. During feature work, flag soft-deprecated APIs and leave them in place (see
references/soft-deprecation.md) - Prefer native SwiftUI APIs over UIKit/AppKit bridging unless bridging is necessary
- Focus on correctness and performance; do not enforce specific architectures (MVVM, VIPER, etc.)
- Encourage separating business logic from views for testability without mandating how
- Follow Apple's Human Interface Guidelines and API design patterns
- Only adopt Liquid Glass when explicitly requested by the user (see
references/liquid-glass.md) - Present performance optimizations as suggestions, not requirements
- Use
#availablegating with sensible fallbacks for version-specific APIs - For layout and rendering inputs, read the value nearest the SwiftUI view that consumes it; do not substitute process-global screen state
Task Workflow
Review existing SwiftUI code
- Read the code under review and identify which topics apply
- Flag deprecated APIs (compare against
references/latest-apis.md); replace hard-deprecated APIs, and flag soft-deprecated APIs without rewriting them unless the user asked to migrate - Run the Topic Router below for each relevant topic
- Validate
#availablegating and fallback paths for version-specific features - For broad codebase reviews, first identify smaller focus areas and present them one at a time; if the user requests a whole-codebase review, divide it into a TODO list
Improve existing SwiftUI code
- Audit current implementation against the Topic Router topics
- Replace hard-deprecated APIs with modern equivalents from
references/latest-apis.md; flag soft-deprecated APIs and do not rewrite them during feature work - Refactor hot paths to reduce unnecessary state updates
- Extract complex view bodies into separate subviews
- Suggest image downsampling when
UIImage(data:)is encountered (optional optimization, seereferences/image-optimization.md)
What ships with it
50 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 228 B
- assets/logo-small.png 29 KB
- assets/logo.png 389 KB
- assets/logo.svg 2.0 KB
- references/accessibility-patterns.md 5.9 KB
- references/animation-advanced.md 11 KB
- references/animation-basics.md 6.7 KB
- references/animation-transitions.md 7.9 KB
- references/charts-accessibility.md 6.1 KB
- references/charts.md 17 KB
- references/document-apps.md 11 KB
- references/environment-patterns.md 7.1 KB
- references/focus-patterns.md 8.7 KB
- references/image-optimization.md 10 KB
- references/iphone-duo.md 7.4 KB
- references/latest-apis.md 25 KB
- references/layout-best-practices.md 21 KB
- references/liquid-glass.md 12 KB
- references/list-patterns.md 21 KB
- references/localization.md 9.7 KB
- references/macos-scenes.md 9.5 KB
- references/macos-views.md 11 KB
- references/macos-window-styling.md 8.6 KB
- references/modifier-patterns.md 2.5 KB
- references/performance-patterns.md 12 KB
- references/previews.md 8.1 KB
- references/scroll-patterns.md 11 KB
- references/sheet-navigation-patterns.md 15 KB
- references/soft-deprecation.md 2.9 KB
- references/state-management.md 21 KB
- references/styled-text-editing.md 8.7 KB
- references/text-patterns.md 1.6 KB
- references/toolbar-patterns.md 9.9 KB
- references/trace-analysis.md 14 KB
- references/trace-recording.md 5.8 KB
- references/view-structure.md 28 KB
- references/webkit-integration.md 9.5 KB
- scripts/analyze_trace.py 9.9 KB runs code
- scripts/instruments_parser/__init__.py 69 B runs code
- scripts/instruments_parser/causes.py 5.9 KB runs code
- scripts/instruments_parser/correlate.py 6.2 KB runs code
- scripts/instruments_parser/events.py 11 KB runs code
- scripts/instruments_parser/hangs.py 3.4 KB runs code
- scripts/instruments_parser/hitches.py 4.5 KB runs code
- scripts/instruments_parser/summary.py 9.1 KB runs code
- scripts/instruments_parser/swiftui.py 6.6 KB runs code
- scripts/instruments_parser/time_profiler.py 4.3 KB runs code
- scripts/instruments_parser/xctrace.py 3.5 KB runs code
- scripts/instruments_parser/xml_utils.py 7.4 KB runs code
- scripts/record_trace.py 11 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 25d ago Changed · +5 tokens per session 3b794f9cb46e
- 28d ago Changed · +22 tokens per session 7c448e80cc00
- 1mo ago Changed · +4 lines · +32 tokens per session 3bc4c2c7bfa7
- 1mo ago Changed · -21 lines · +46 tokens per session 54ffbaedb010
- 1mo ago First seen · 172 lines · 92 tokens per session scan A 9fe4bb06a2b1
swiftui-expert-skill is a skill published in the GitHub repository AvdLee/SwiftUI-Agent-Skill (3,773 stars, last pushed 21d ago), licensed MIT. It adds 197 tokens to every session and 2,701 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp: publish the Windows head first, then point packaging at the resolved resizetizer manifest. Use for a MAUI MSIX or signed unpackaged build, MAUI packaging in CI, or 'manifest contains unresolved placeholders' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…