swiftui-liquid-glass
Implement, review, or improve SwiftUI features using the iOS 26+ Liquid Glass API. Use when asked to adopt Liquid Glass in new SwiftUI UI, refactor an existing feature to Liquid Glass, or review Liquid Glass usage for correctness, performance, and design alignment.
89
88%
Does it follow best practices?
Impact
89%
1.97xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with clear 'what' and 'when' clauses, excellent distinctiveness due to the niche Liquid Glass API focus, and good trigger term coverage. The main weakness is that the capability actions (implement, review, improve) are somewhat generic verbs rather than listing specific concrete operations the skill can perform with the Liquid Glass API.
Suggestions
Add more specific concrete actions beyond 'implement, review, improve' — e.g., 'apply glass material modifiers, configure translucency effects, migrate existing views to glass backgrounds' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (SwiftUI Liquid Glass API) and some actions (implement, review, improve), but doesn't list specific concrete actions like 'apply glass material effects', 'configure blur radius', or 'set up glass background modifiers'. | 2 / 3 |
Completeness | Clearly answers both 'what' (implement, review, or improve SwiftUI features using the Liquid Glass API) and 'when' (explicit 'Use when' clause covering adoption, refactoring, and review scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'SwiftUI', 'Liquid Glass', 'iOS 26+', 'Liquid Glass API', 'refactor', 'review', 'adopt Liquid Glass'. These are terms a developer would naturally use when requesting this kind of work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Liquid Glass API' and 'iOS 26+' are very specific triggers that are unlikely to conflict with general SwiftUI skills or other UI framework skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill that is concise, actionable, and well-organized for its domain. The executable Swift snippets cover the key patterns, and the checklists provide concrete review criteria. The main weakness is the lack of explicit validation/feedback loops in the workflow—there's no guidance on verifying that glass effects render correctly or recovering from common mistakes.
Suggestions
Add a brief validation step to the workflow paths, such as 'Build and run on iOS 26 simulator to verify glass rendering and fallback behavior on iOS 25' to close the feedback loop.
Consider adding a 'Common Pitfalls' section noting what happens when modifier order is wrong or GlassEffectContainer is missing, so Claude can diagnose issues during review.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what SwiftUI or glass effects are conceptually, assumes Claude's competence with Swift/SwiftUI, and every section serves a clear purpose. No unnecessary padding or concept explanations. | 3 / 3 |
Actionability | Provides fully executable Swift code snippets covering the main patterns (basic glass effect with fallback, GlassEffectContainer grouping, glass button style). The checklists give specific, concrete guidance with exact API names and modifier ordering rules. | 3 / 3 |
Workflow Clarity | The decision tree provides three clear paths (review, improve, implement) with sequenced steps, and the checklists serve as validation checkpoints. However, there are no explicit validation/verification steps or feedback loops—e.g., no 'build and verify glass rendering' step or error recovery guidance for common pitfalls like incorrect modifier ordering. | 2 / 3 |
Progressive Disclosure | Well-structured with a clear overview, decision tree, guidelines, checklists, quick snippets, and a reference to a separate detailed guide (`references/liquid-glass.md`). Content is appropriately split with one-level-deep references and easy navigation through clearly labeled sections. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Dimillian/Skills
- Commit
05ba982
- 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.