CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

android-architecture

Apply Clean Architecture layering, modularization, and Unidirectional Data Flow in Android projects. Use when setting up project structure, placing code in layers, configuring feature/core modules, or implementing UDF patterns; defer Compose state and ViewModel/StateFlow implementation to their specific skills.

68

Quality

86%

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.

A tight, well-structured standards skill: lean bullets, exact naming conventions, a genuine verification checklist, and real one-level-deep references. Main gaps are the absence of inline code for module/DI setup (deferring everything to implementation.md), no error-recovery guidance in verification, and Compose guidance duplicated between the body and compose-standards.md.

Suggestions

Consolidate Compose guidance: trim section 4 to a one-line pointer to references/compose-standards.md, since collectAsStateWithLifecycle and @Stable/@Immutable rules are already duplicated there.

Add a small inline snippet (e.g., a settings.gradle.kts module include block or a build.gradle.kts dependency excerpt) so module setup is executable directly from SKILL.md without opening implementation.md.

Add error-recovery guidance to the Verification section (e.g., 'if a feature module fails to compile independently, check for cross-feature dependencies and move shared code to :core:common').

DimensionReasoningScore

Conciseness

The body is lean bullet-point guidance with zero concept explanations (no "what is Clean Architecture" padding), exact module paths, and exact API names — it fully assumes Claude's competence and every line earns its place, matching anchor 5.

5 / 5

Actionability

Guidance is concrete and executable in intent — exact module names (":feature:home", ":core:network"), exact APIs ("StateFlow<UiState>", "collectAsStateWithLifecycle"), and the "./gradlew build" verification command — but there is no inline code for module build configuration or DI wiring; those details are deferred to references/implementation.md. That places it at anchor 4 (minor gaps) rather than anchor 5's copy-paste-ready coverage, though well above anchor 3's pseudocode level.

4 / 5

Workflow Clarity

Sections 1-4 give a clear sequence (layer -> modularize -> UDF -> Compose) and the Verification section provides an explicit checklist with a runnable command ("./gradlew build succeeds", "Domain layer has zero Android framework imports"). It misses anchor 5 because there are no error-recovery feedback loops (e.g., what to do when a feature module fails to compile independently).

4 / 5

Progressive Disclosure

The body is a concise overview with clearly signaled, one-level-deep references (references/implementation.md and references/compose-standards.md, both real files). It falls short of anchor 5 because sections 1 and 2 repeat the same implementation.md pointer, and section 4 inlines four Compose bullets (collectAsStateWithLifecycle, @Stable/@Immutable) that substantially duplicate references/compose-standards.md — content that should live in the separate file.

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.

A strong description: it states concrete capabilities, an explicit "Use when" trigger list, and explicit deferral boundaries to sibling skills. The only room for improvement is adding a few more natural trigger synonyms (e.g., repository pattern, MVVM) and slightly more concrete action verbs.

DimensionReasoningScore

Specificity

"Apply Clean Architecture layering, modularization, and Unidirectional Data Flow" names the Android domain plus several concrete actions, going beyond the 1-2 actions of the anchor-3 example. It falls short of anchor 5 because "layering" and "modularization" are more abstract than fully concrete operations like "extract text, fill forms, merge documents".

4 / 5

Completeness

It explicitly answers both questions: what ("Apply Clean Architecture layering, modularization, and Unidirectional Data Flow in Android projects") and when ("Use when setting up project structure, placing code in layers, configuring feature/core modules, or implementing UDF patterns"), matching the anchor-5 example structure with concrete trigger phrases.

5 / 5

Trigger Term Quality

The "Use when" clause supplies natural phrases users would say: "setting up project structure", "placing code in layers", "feature/core modules", "UDF patterns". A few common variations are missing (e.g., "repository pattern", "MVVM", "module structure"), which keeps it at anchor 4 rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (Android architecture) and actively reduces conflict risk with "defer Compose state and ViewModel/StateFlow implementation to their specific skills", which is explicit boundary guidance beyond what anchor 5 requires.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Path

skills/android/android-architecture/SKILL.md

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.