android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/android-clean-architecture/SKILL.md

Quality

Content

80%

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

The content is highly actionable and token-efficient, with complete executable examples for every layer. Its weak spots are structure rather than guidance: a single monolithic file and no validation checkpoints for a non-trivial reference.

Suggestions

Move the larger reference blocks (full Koin/Hilt DI setup, SQLDelight schema, Gradle convention plugins) into bundled reference files linked one level deep from SKILL.md to improve progressive disclosure.

For the data-layer repository flow, add an explicit validate→fix→retry note (e.g. verify mappers compile against the domain interface before wiring DI) to give the workflow a feedback checkpoint.

Confirm the "References" section points to bundled files within this skill rather than only to external skills, so navigation stays one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean executable Kotlin/SQL with tight one-line rationales and no padding about concepts Claude already knows; each token-earning line (e.g. the "Critical: domain must NEVER depend on data" rule) carries real guidance.	3 / 3
Actionability	It provides complete, copy-paste-ready examples across the stack — ItemRepositoryImpl, @Dao with @Query/@Upsert, SQLDelight .sq, Ktor HttpClient setup, Koin and Hilt modules — matching the fully-executable anchor.	3 / 3
Workflow Clarity	As a pattern reference rather than a multi-step task it has clear sections and explicit dependency rules, but it is well over 50 lines and contains no validation/feedback checkpoints, so it does not reach the level-3 sequence-with-validation bar.	2 / 3
Progressive Disclosure	Everything lives inline in one ~340-line SKILL.md with no bundle files; the References section points to other skills rather than one-level-deep bundle files, so content that could be split (full Koin/Hilt/SQLDelight guides) stays inline.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and clearly niched, but it lacks an explicit "Use when..." trigger clause and misses common user phrasings like "KMP" or "clean architecture." Adding trigger guidance and broader natural keywords would raise the two lowest dimensions.

Suggestions

Append an explicit activation clause, e.g. "Use when structuring Android or KMP projects into layered modules, or when designing UseCases, Repositories, and data sources."

Add natural trigger terms users actually say — "clean architecture", "KMP", "layered architecture", "dependency inversion" — alongside the existing keywords.

Keep the third-person voice and concise action list; only the missing "when" guidance and keyword breadth are holding back the score.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete capabilities — "module structure, dependency rules, UseCases, Repositories, and data layer patterns" — matching the anchor for listing several specific actions rather than vague language.	3 / 3
Completeness	It clearly answers "what" but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces natural terms like "Android" and "Kotlin Multiplatform" but omits common variations a user would actually say ("clean architecture", "KMP", "layered architecture"), so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The combination of "Android and Kotlin Multiplatform projects" with UseCase/Repository/data-layer patterns carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

Reviewed: 3 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.