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.

89

1.20x
Quality

83%

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-structured skill with excellent reference architecture and actionable, expert-level SwiftUI rules. Its main weakness is redundancy: the decision tree, core guidelines, and checklists restate overlapping material, inflating token cost without adding information.

Suggestions

Consolidate the triplicated guidance (Workflow Decision Tree, Core Guidelines, Review Checklist) — e.g., keep the checklists but trim the Core Guidelines bullets they duplicate, or drop the per-item reference links from the workflow steps since the References section already maps them.

Add one or two short executable Swift snippets for the most error-prone rules (e.g., `@Observable` + `@Bindable` usage, or a correct `.animation(_:value:)` vs. the deprecated form) to match the copy-paste quality of the Liquid Glass example.

Tie the Review Checklist into the workflows as an explicit validation loop ("fix failing items, then re-run the checklist") to earn full workflow-clarity credit.

DimensionReasoningScore

Conciseness

The guidance itself is dense, factual, and assumes SwiftUI competence (e.g., "Nested `ObservableObject` doesn't propagate changes", "`Self._printChanges()`"), but the same rules are stated three times across the Workflow Decision Tree, Core Guidelines, and Review Checklist (ForEach stable identity, animation value parameters, Liquid Glass rules, and state-wrapper rules all repeat). This noticeable redundancy could be consolidated, placing it at "mostly efficient but includes some unnecessary... could be tightened" rather than anchor 4.

3 / 5

Actionability

Rules are concrete and executable: exact property-wrapper selection rules, a lookup table, an executable Liquid Glass Swift code block with an `#available` fallback, and a named debugging call. It misses anchor 5 because most guidance is rule statements rather than copy-paste-ready examples covering common cases — only one area (Liquid Glass) has runnable code.

4 / 5

Workflow Clarity

Three clearly sequenced workflows (review/implement/improve) each with an explicit first step ("First, consult `references/latest-apis.md`"), per-step reference pointers, and a Review Checklist section that functions as a validation checkpoint. It stops short of anchor 5 because there are no explicit feedback loops (e.g., re-verify after fixing a failing checklist item) tying the checklists into the workflows.

4 / 5

Progressive Disclosure

All 14 referenced files exist in `references/`, are referenced one level deep, and are signposted inline with per-section pointers plus a References list with one-line descriptions. The body appropriately serves as the distilled overview with detail delegated to the reference files, matching "clear overview with well-signaled one-level-deep references; easy navigation".

5 / 5

Total

16

/

20

Passed

Description

87%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: third-person, concrete about capabilities, and with an explicit and specific 'Use when...' clause covering the three main workflows. Only minor improvements possible in synonym/trigger coverage and slightly more concrete action verbs.

DimensionReasoningScore

Specificity

"Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, and iOS 26+ Liquid Glass adoption" lists several specific actions and names four concrete sub-domains. It falls short of a 5 because the verbs (write/review/improve) are less concrete than example-rich anchors like "extract text, fill forms, merge documents", and it's not noticeably below the top anchor either.

4 / 5

Completeness

It explicitly answers both questions: what ("Write, review, or improve SwiftUI code following best practices for state management, view composition, performance...") and when ("Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns") with concrete trigger phrases and third-person voice, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural trigger phrases are present: "building new SwiftUI features", "refactoring existing views", "reviewing code quality", "adopting modern SwiftUI patterns", plus technology keywords (SwiftUI, iOS 26+, Liquid Glass). A few natural variations users might say (e.g., "Swift", "iOS app", "Swift UI") are missing, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

SwiftUI is a clear, narrowly-scoped technology niche with distinct triggers; the description would not fire for unrelated skills and only trivially overlaps with a hypothetical general Swift skill. This matches "clear niche with distinct triggers; minimal conflict risk".

5 / 5

Total

18

/

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

.windsurf/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.