CtrlK
BlogDocsLog inGet started
Tessl Logo

liquid-glass

Implement and review macOS SwiftUI Liquid Glass UI. Use when adopting system glass, removing conflicting custom chrome, or building glass surfaces.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

The body is a tight, API-specific guide organized into clean sections with a workflow, checklist, and guardrails. Its main gaps are the absence of copy-paste code examples and an explicit error-recovery loop, plus no progressive disclosure via reference files.

Suggestions

Add one or two short copy-paste SwiftUI snippets (e.g., a GlassEffectContainer with glassEffectID + @Namespace morph) to lift actionability toward fully executable guidance.

Make the validation step an explicit feedback loop: 'If grouping/transitions are incoherent, adjust the GlassEffectContainer/glassEffectID and re-validate.'

Move detailed glassEffect/glassEffectID API reference into a references/GLASS_API.md and link to it one level deep to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: imperative bullets naming exact APIs (glassEffect, glassEffectID, ToolbarSpacer, searchable, containerConcentric) with no tutorial padding or explanation of concepts Claude already knows. It is not below 5 because there is no over-explanation to trim.

5 / 5

Actionability

Highly actionable guidance citing specific SwiftUI modifiers and initializers with clear usage rules, but it provides no copy-paste code examples, which the anchor-5 example requires; as an instruction-only skill this is acceptable but leaves a minor gap.

4 / 5

Workflow Clarity

A clear 6-step sequence includes an explicit validation step (step 5) plus a Review Checklist and Guardrails, but it lacks an explicit error-recovery feedback loop ('if invalid, fix and re-validate'), keeping it below 5.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with easy in-file navigation and no nested references, but all content lives in a single file with no bundle references; for a skill this broad, a one-level-deep reference (e.g., glassEffect usage details) could improve discoverability.

4 / 5

Total

17

/

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.

The description is well-constructed: it states the capability, gives an explicit 'Use when…' trigger clause with concrete scenarios, and carves out a distinctive Liquid Glass niche. It is concise and in third person, with only minor gaps in action enumeration and API-name synonyms.

DimensionReasoningScore

Specificity

Names the domain ('macOS SwiftUI Liquid Glass UI') and several concrete actions — implement, review, adopting system glass, removing conflicting custom chrome, building glass surfaces — but stops short of enumerating the component areas (toolbars, search, sheets) covered by the body, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' ('Implement and review macOS SwiftUI Liquid Glass UI') and 'when' ('Use when adopting system glass, removing conflicting custom chrome, or building glass surfaces') with concrete trigger phrases, paralleling the anchor-5 example structure.

5 / 5

Trigger Term Quality

Uses natural terms a macOS developer would say — 'Liquid Glass', 'system glass', 'custom chrome', 'glass surfaces' — but omits common synonyms and the actual API names (glassEffect, glassEffectID) users may mention.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (macOS SwiftUI Liquid Glass) with distinctive triggers ('adopting system glass', 'removing conflicting custom chrome') unlikely to fire for unrelated skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.