macos-liquid-glass

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

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%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, lean instruction-only skill with concrete API-level guidance, a clear validated workflow, and a review checklist. Main improvements are trimming the triplicated .app-bundle note and adding a short usage snippet for the core glassEffect/GlassEffectContainer APIs.

Suggestions

Consolidate the ".app bundle vs raw executable" guidance into one place (e.g. keep it in Workflow step 6 and drop the duplicate lines in Review Checklist and Guardrails) to reduce repetition.

Add one compact code snippet showing glassEffect + GlassEffectContainer + glassEffectID usage, since the custom-glass section depends on exact API composition that is currently only described in prose.

Make the step-5 validation more concrete by tying it to the Review Checklist items (e.g. "verify each Review Checklist item in the running app") so the checkpoint has an explicit procedure.

Dimension	Reasoning	Score
Conciseness	The body is dense, non-padded API-level guidance with no explanation of concepts Claude already knows, but the ".app bundle not raw executable" point is repeated three times (Workflow step 6, Review Checklist, and Guardrails) and the checklist partially restates earlier sections — minor trims available.	4 / 5
Actionability	Guidance names exact modifiers ("glassEffect(... .interactive())", "glassEffectID with a local @Namespace", "containerConcentric", "neutralValue"), making it highly actionable for an instruction-only skill; minor gaps are the absence of any usage snippet showing API signatures and the somewhat abstract step-5 validation ("visually coherent and still usable").	4 / 5
Workflow Clarity	The six-step numbered workflow includes an explicit validation step, is reinforced by a dedicated Review Checklist, and points to macos-build-run-debug for actually running and verifying the result — matching the top anchor with clear sequence, explicit validation, and a checklist; no destructive/batch cap applies.	5 / 5
Progressive Disclosure	No bundle files exist, so the body carries everything; sections are well-organized with clear headers and a useful "When To Use Other Skills" routing section, but all detail (App Structure, Toolbars, Search, Controls) lives inline in a single ~165-line layer rather than being split or progressively disclosed.	4 / 5
	Total	17 / 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 that clearly and explicitly states both what the skill does and when to use it, with distinctive domain triggers. Keyword coverage is good but could add common synonyms like the glassEffect API or toolbar/sidebar glass phrasing.

Suggestions

Add one or two natural synonyms users would say, such as the glassEffect API name or "toolbar/sidebar glass", to broaden trigger coverage.

Consider mentioning the audit/review angle (e.g. finding custom chrome that conflicts with the system material) as an explicit trigger, since that is a key use case in the body.

Dimension	Reasoning	Score
Specificity	"Implement and review macOS SwiftUI Liquid Glass UI" names the domain with concrete actions ("adopting system glass, removing conflicting custom chrome, or building glass surfaces") — several specific actions with minor gaps, since the body also covers toolbars, search, and controls that the description does not mention.	4 / 5
Completeness	"Implement and review macOS SwiftUI Liquid Glass UI" explicitly answers what, and "Use when adopting system glass, removing conflicting custom chrome, or building glass surfaces" explicitly answers when with three concrete trigger phrases — fully matching the top anchor.	5 / 5
Trigger Term Quality	Natural terms include "macOS", "SwiftUI", "Liquid Glass", "system glass", "custom chrome", and "glass surfaces", giving good keyword coverage, though common variations users might say (glassEffect, toolbar/sidebar glass, materials) are missing.	4 / 5
Distinctiveness Conflict Risk	"Liquid Glass" is a distinctive niche trigger, but the description is mostly distinct with minor overlap risk against general macOS SwiftUI design/styling skills; sibling skills like macos-swiftui-patterns cover adjacent territory.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: robinebers/openusage
Path: .agents/skills/macos-liquid-glass/SKILL.md
Commit: 256a9f1

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.