android-design-system

Enforce Material Design 3 theming and design token usage in Jetpack Compose. Use when implementing M3 components, color schemes, typography, or design tokens.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-organized enforcement skill that gives concrete API-level do/don't rules without padding. Its main gaps are the absence of an executable Compose code example and an empty, misleading References section.

Suggestions

Add a short before/after Composable code example showing a hardcoded color/typography violation and the corrected MaterialTheme.* version to make guidance fully executable and copy-paste-ready.

Remove the empty "## References" heading, or populate it with actual reference links/files, since no bundle references currently exist.

Consider a one-line verification step (e.g., grep/AST check for Color(0xFF and raw fontSize) to convert the enforcement intent into a checkable workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations or padding ("Map every raw color/type value to lightColorScheme/darkColorScheme slots"), assuming Claude's knowledge of Compose/M3; it is not level 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Guidance references concrete APIs (MaterialTheme.colorScheme.*, Color(0xFF...) to avoid, Color.kt/Theme.kt/Type.kt), but there is no executable before/after Compose code example, leaving it short of copy-paste-ready; it is not level 1 because the direction is concrete and specific rather than vague, and not level 3 because no complete executable example is given.	2 / 3
Workflow Clarity	This is a single-purpose enforcement skill whose action (enforce M3 token usage) is unambiguous, with clear do/don't lists; per the simple-skills note, workflow clarity can score 3 for a clear single action. It is not level 2 because no multi-step sequence or validation checkpoint is required for this lint-style task.	3 / 3
Progressive Disclosure	Sections are well-organized for a sub-50-line skill, but a "## References" heading appears with no content and no bundle files exist, making the signaled reference section misleading; it is not level 1 because organization is otherwise clear, and not level 3 because the dangling empty References section is a structural defect.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 well-crafted description that states a concrete capability in third person and pairs it with an explicit, keyword-rich "Use when" trigger clause. It is concise, specific, and clearly scoped to M3/Compose theming.

Dimension	Reasoning	Score
Specificity	"Enforce Material Design 3 theming and design token usage in Jetpack Compose" plus the explicit list "M3 components, color schemes, typography, or design tokens" names multiple concrete actions, matching the level-3 anchor; it is not level 2 because the actions are specific and plural rather than partial.	3 / 3
Completeness	It explicitly answers what ("Enforce Material Design 3 theming and design token usage") and when ("Use when implementing M3 components, color schemes, typography, or design tokens") with an explicit trigger clause, matching level 3; it is not level 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Natural user-facing terms like "M3 components", "color schemes", "typography", "design tokens", and "Jetpack Compose" are covered well, matching the level-3 anchor; it is not level 2 because common variations are present rather than only a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	The M3/Compose theming niche is distinct with specific triggers unlikely to conflict with other skills, matching level 3; it is not level 2 because the scope is narrow and unambiguous rather than only somewhat specific.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Commit: 611f52a

Reviewed: 4 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.