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 ivan-magda/uikit-expert-skill --skill uikit-expertgit clone --depth 1 https://github.com/ivan-magda/uikit-expert-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/ivan-magda/uikit-expert-skill/uikit-expert)<a href="https://agentmods.dev/skills/ivan-magda/uikit-expert-skill/uikit-expert"><img src="https://agentmods.dev/badge/skills/ivan-magda/uikit-expert-skill/uikit-expert/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/ivan-magda/uikit-expert-skill/uikit-expert"><img src="https://agentmods.dev/badge/skills/ivan-magda/uikit-expert-skill/uikit-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00095 | $0.03177 |
| Opus 5 | $0.00048 | $0.01588 |
| Sonnet 5 | $0.00019 | $0.00635 |
| Haiku 4.5 | $0.00010 | $0.00318 |
Grade A, and why
uikit-expert 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UIKit Expert Skill
Overview
Favor native APIs and Apple's documented guidance. Operating principles: facts over architecture (no MVVM/VIPER/Coordinator mandates, but do separate business logic for testability); correctness first, then performance; reserve "always"/"never" for correctness, use "suggest"/"consider" for optional optimizations.
Workflows
All three modes draw on the same Core Guidelines below; each topic links to its reference file there. Pick the entry point:
- Review — Walk the Review Checklist as pass/fail gates. For any failure, fix per the matching Core Guideline. Prioritize correctness gates (lifecycle, Auto Layout, memory, concurrency) over style; treat performance items as optional.
- Improve — For each issue, apply the modern replacement from the Deprecated → Modern table and the matching Core Guideline. Present performance work (downsampling, prefetching, constraint-churn fixes) as optional optimizations, never mandates.
- Implement new — Build in this order, applying the relevant Core Guideline at each step:
- Design data flow — owned state, injected dependencies, model layer
- Lifecycle — one-time setup in
viewDidLoad, geometry inviewIsAppearing - Auto Layout — batch activation, zero churn
- Collection views — DiffableDataSource + CompositionalLayout + CellRegistration
- Navigation — all 4 appearance slots, concurrent-transition guards
- Animation, memory (
[weak self], Task cancellation), concurrency (@MainActor) - Interop, image loading, keyboard, Dynamic Type / VoiceOver / dark mode
- Gate iOS 26+ features with
#availableand sensible fallbacks
Core Guidelines
View Controller Lifecycle — see references/view-controller-lifecycle.md
- Use
viewDidLoadfor one-time setup: subviews, constraints, delegates — NOT geometry - Use
viewIsAppearing(back-deployed iOS 13+) for geometry-dependent work, trait-based layout, scroll-to-item viewDidLayoutSubviewsfires multiple times — use only for lightweight layer frame adjustmentsviewWillAppearis limited to transition coordinator animations and balanced notification registration- Always call
superin every lifecycle override - Child VC containment:
addChild→addSubview→didMove(toParent:)— in that exact order - Verify deallocation with
deinitlogging during development
What ships with it
15 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.
- .tessl-plugin/plugin.json 590 B
- references/adaptive-appearance.md 28 KB
- references/animation-patterns.md 30 KB
- references/auto-layout.md 34 KB
- references/cell-configuration.md 29 KB
- references/concurrency-main-thread.md 26 KB
- references/image-loading.md 27 KB
- references/keyboard-scroll.md 30 KB
- references/list-performance.md 30 KB
- references/memory-management.md 26 KB
- references/modern-collection-views.md 29 KB
- references/modern-uikit-apis.md 23 KB
- references/navigation-patterns.md 29 KB
- references/uikit-swiftui-interop.md 26 KB
- references/view-controller-lifecycle.md 24 KB
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.
- 12d ago First seen · 185 lines · 95 tokens per session scan A 3a279331030a
uikit-expert is a skill published in the GitHub repository ivan-magda/uikit-expert-skill (8 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 3,177 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
ios-expert
Expert in iOS development with SwiftUI, UIKit, Combine, and Apple ecosystem integration. Use when the user mentions mobile, Swift, SwiftUI, UIKit, Apple platforms, or Xcode, or when the task involves iOS App Architecture, SwiftUI Fundamentals, UIKit Essentials, or Combine Framework.
ui-enhancer-radar
Systematic iOS/SwiftUI UI audit with design intent interview, 14-domain analysis (including Color Audit with adaptive Color Profile, iPad Sheet Sizing caller-side audit, Button Hit Region three-factor interaction audit, and Silent Picker menu-presentation audit), element compaction, cross-view consistency checks…
ui-path-radar
UI path tracer for SwiftUI/UIKit apps. 5-layer audit with 34 issue categories and 19 automated checks: discover entry points, trace flows, detect dead ends and broken promises, evaluate UX impact, verify data wiring. Supports targeted trace, diff against previous audits, and handoff to planning skills. Triggers…
swift-focusengine-pro
Reviews, writes, and fixes focus management code for all Apple platforms (tvOS, iOS/iPadOS, watchOS, visionOS, macOS), covering SwiftUI, UIKit, AppKit, and RealityKit. Use when reading, writing, or reviewing apps that handle focus, hover, key view loops, or Digital Crown navigation.
m3-expressive
Material 3 Expressive design patterns for Jetpack Compose - expressive theming, motion physics, shape morphing, typography emphasis, color emphasis, and all 28 expressive components.
liquid-glass
Apple Liquid Glass design patterns for SwiftUI iOS 26 - glass effects, morphing, containers, interactive glass, tinting, accessibility, and cross-platform glass design.