CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swiftui-expert-skill

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

88

1.20x
Quality

82%

Does it follow best practices?

Impact

95%

1.20x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized expert skill with a clear decision tree, concrete API-level rules, and exemplary progressive disclosure to 14 real one-level-deep reference files. The main weakness is token cost: Core Guidelines and the Review Checklist restate many of the same rules, roughly doubling sections that could be merged or delegated to the references.

Suggestions

Merge the Review Checklist into the Core Guidelines (or vice versa) — items like '@State is private', 'ForEach stable identity', and 'Button over onTapGesture' appear in both; a single checklist section with per-topic reference pointers would cut significant tokens.

Delegate the per-topic bullet rules that duplicate reference content (e.g., the full Animations and Liquid Glass guideline lists) to their reference files, keeping only the top 2-3 non-negotiable rules inline.

Add one short executable snippet for the most common non-Liquid-Glass cases (e.g., a correct @Observable + @Bindable data-flow example or a stable-identity ForEach), so the most frequent workflows have copy-paste patterns too.

DimensionReasoningScore

Conciseness

The body is dense and never explains concepts Claude already knows, but the Core Guidelines and Review Checklist sections substantially duplicate each other — e.g., '@State must be private', 'ForEach uses stable identity (not .indices)', '.animation(_:value:) with value parameter', and 'Button over onTapGesture' each appear two to three times across sections. This matches 'mostly efficient... could be tightened' rather than the minor-trim profile of anchor 4.

3 / 5

Actionability

Guidance is highly concrete with exact API names ('@Bindable', '.phaseAnimator', 'glassEffectID', 'Self._printChanges()'), a property-wrapper selection table, and a copy-paste-ready Swift code block for Liquid Glass. It falls short of anchor 5 only because the single code example covers just one topic — the other workflows (state management, ForEach identity) are told as rules without a short executable example.

4 / 5

Workflow Clarity

The Workflow Decision Tree clearly sequences three workflows, each gated by an explicit first step ('First, consult references/latest-apis.md'), and the Review Checklist provides per-topic checkpoints. It sits at anchor 4 rather than 5 because there are no feedback-loop steps (e.g., re-check after fixes); acceptable here since the skill is advisory, not destructive/batch.

4 / 5

Progressive Disclosure

The body is a true overview: every checklist and workflow section points to its reference file by path, all 14 referenced files exist in references/, references are exactly one level deep, and the one required-reading file (latest-apis.md) is explicitly flagged. This matches 'clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation'.

5 / 5

Total

16

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit 'Use when...' clause and natural trigger phrases covering build, refactor, review, and modernization workflows. The only weaknesses are slight genericity in the action verbs and minor overlap risk with general code-review skills.

DimensionReasoningScore

Specificity

"Write, review, or improve SwiftUI code" names three concrete actions, and the domains are enumerated ("state management, view composition, performance, and iOS 26+ Liquid Glass adoption"). This matches the anchor 'lists several specific actions; minor gaps in coverage' — the verbs are concrete but somewhat generic (write/review/improve) and don't enumerate outputs like the anchor-5 example does.

4 / 5

Completeness

The description explicitly answers both questions: what ("Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, and iOS 26+ Liquid Glass adoption") and when ("Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns") with concrete trigger phrases, exactly matching the anchor-5 exemplar.

5 / 5

Trigger Term Quality

Natural user phrases are present — "building new SwiftUI features", "refactoring existing views", "reviewing code quality", "adopting modern SwiftUI patterns" — which users would genuinely say. A few natural terms are missing (e.g., 'Swift', '.swift', 'iOS app UI'), matching the anchor 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym/extension coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The SwiftUI niche is clear and most triggers are SwiftUI-specific (Liquid Glass, refactoring views), but phrases like "reviewing code quality" and general best-practice framing create minor overlap risk with generic code-review or Swift/iOS skills — matching 'mostly distinct; minor overlap risk with closely related skills' rather than the fully distinct anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

SnowingFox/macos-island

Path

.codex/skills/swiftui-expert-skill/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.