CtrlK
BlogDocsLog inGet started
Tessl Logo

android-compose

Build high-performance declarative UI with Jetpack Compose. Use when writing Composable functions, optimizing recomposition, hoisting state, or working with LazyColumn and side effects.

73

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 guidance skill that assumes Compose competence and pushes executable examples one level deep into a real references file. Its main gap is the absence of any inline copy-paste code, which keeps actionability just below fully executable.

Suggestions

Add one short inline Kotlin snippet (e.g., a `LazyColumn { items(list, key = { it.id }) }` or `LaunchedEffect` example) so the body itself is copy-paste ready, not only directive.

Add a brief explicit feedback loop note for recomposition work (e.g., verify with Layout Inspector / recomposition counts and re-optimize), to strengthen workflow_clarity for performance tasks.

Consider a one-line "When to open references/implementation.md" pointer summarizing what each referenced section covers, so navigation is even more discoverable.

DimensionReasoningScore

Conciseness

The body is lean bullet directives with no padding and no explanation of Compose fundamentals Claude already knows; every line earns its place. It is not 2 because there is no unnecessary explanation or tightening opportunity of the kind shown in the score-2 anchor.

3 / 3

Actionability

Directives name concrete mechanisms (`@Stable`/`@Immutable`, `key` in LazyColumn items, `derivedStateOf`, `LaunchedEffect`) but the body contains no inline executable code — examples are deferred to references. It is not 3 because nothing in the body is copy-paste ready; it is not 1 because the guidance is specific and actionable rather than abstract.

2 / 3

Workflow Clarity

The Verification section provides an explicit checklist including the `./gradlew build` checkpoint, and the body is organized into numbered guidance areas with an Anti-Patterns section. For a guidance/checklist-style skill the validation and sequencing are explicit, matching the score-3 anchor. It is not 2 because validation checkpoints are present rather than missing.

3 / 3

Progressive Disclosure

The body is a concise overview that points one level deep to `references/implementation.md` (a real file containing the code examples), with inline signals like "See [implementation examples]...". Content is appropriately split for navigation, matching the score-3 anchor. It is not 2 because references are clearly signaled and shallow rather than inline-buried or nested.

3 / 3

Total

11

/

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 tight, third-person description that names concrete capabilities and provides an explicit "Use when..." trigger with Compose-specific keywords. It is concise without fluff and clearly distinguishes the skill's niche.

DimensionReasoningScore

Specificity

"Build high-performance declarative UI" names the domain and lists multiple concrete actions — "writing Composable functions, optimizing recomposition, hoisting state... LazyColumn and side effects" — matching the score-3 anchor for multiple specific concrete actions. It is above 2 because the action set is comprehensive and specific rather than partial.

3 / 3

Completeness

It states what it does ("Build high-performance declarative UI with Jetpack Compose") and an explicit "Use when..." trigger clause covering several scenarios, satisfying the score-3 anchor for both what AND when. It is not 2 because the when-clause is explicit, not merely implied.

3 / 3

Trigger Term Quality

Terms like "Composable functions", "recomposition", "hoisting state", "LazyColumn", and "side effects" are the natural vocabulary a Compose developer uses when requesting this work. Good coverage of common variations rather than generic or jargon-only phrasing, placing it above score 2.

3 / 3

Distinctiveness Conflict Risk

The Jetpack Compose framing plus Compose-specific triggers carve a clear niche unlikely to fire for non-Compose skills. It is not 2 because the triggers (Composable, recomposition, LazyColumn, etc.) are highly specific rather than broadly overlapping.

3 / 3

Total

12

/

12

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.

Validation14 / 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
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.