Content
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill demonstrates strong domain expertise in M3 Expressive for Android 16, covering motion, shapes, color, typography, new components, and accessibility with specific API references and concrete anti-patterns. However, it suffers from zero executable code examples (critical for a Compose UI skill), excessive philosophical framing that inflates token cost, and a monolithic structure with no progressive disclosure. The content reads more like a design manifesto than an actionable implementation guide.
Suggestions
Add executable Jetpack Compose code snippets for key patterns: spring animations with MaterialTheme.motionScheme, shape morphing with Morph, ButtonGroup usage, and edge-to-edge WindowInsets handling.
Split into multiple files: keep SKILL.md as a concise overview with quick-start code, then reference separate files like MOTION.md, SHAPES.md, COLOR.md, COMPONENTS.md for detailed guidance.
Remove or drastically condense the 'Design Thinking' and 'What Separates Professional from Template' sections — these are motivational rather than actionable and repeat points already made in the guidelines.
Add a concrete workflow with validation steps: e.g., 1) Set up theme with motionScheme and colorScheme, 2) Build layout with adaptive size classes, 3) Verify contrast with accessibility scanner, 4) Test animations with reduced motion enabled, 5) Verify edge-to-edge on Android 16 emulator.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains genuinely useful M3 Expressive-specific knowledge that Claude wouldn't have from training, but it's padded with motivational/philosophical framing ('Design Thinking' section, repeated exhortations about 'professional vs template'), analogies ('like pulling a book from a shelf'), and redundant emphasis across sections. The 'NEVER Do These' section partially duplicates guidelines already stated positively. Could be tightened by ~30%. | 2 / 3 |
Actionability | The skill provides specific API names (MaterialTheme.motionScheme, Morph, ButtonGroup, FloatingActionButtonMenu), concrete token names (fastSpatialSpec, surfaceContainerLowest), and specific numeric thresholds (48dp touch targets, 4.5:1 contrast). However, it contains zero executable code examples — no Compose snippets, no actual spring animation code, no shape morphing implementation. For a Jetpack Compose UI skill, the absence of any copy-paste-ready Kotlin/Compose code is a significant gap. | 2 / 3 |
Workflow Clarity | The skill provides a logical adoption order (motion → shape → color → components) and a design thinking sequence, but lacks explicit step-by-step workflows for actually building a screen. There are no validation checkpoints — e.g., how to verify contrast ratios, how to test spring animations, how to confirm edge-to-edge rendering works correctly. The 'Design Thinking' section outlines questions but not a concrete process. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no references to supporting files, no links to detailed guides for subtopics (motion, shapes, color, accessibility could each be separate files), and no clear layering between overview and deep-dive content. Everything is inline at the same level of detail, making it hard to navigate and consuming significant context window for every invocation. | 1 / 3 |
Total | 7 / 12 Passed |