CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jetpack-compose-performance

Diagnose and optimize Android Jetpack Compose UI code. Use this skill when analyzing performance bottlenecks of existing code to minimize recomposition overhead and prevent dropped frames and UI lag.

Quality

85%

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 high-quality, expert-level audit skill: every category pairs concrete, version-aware rules with a mandatory, verified reference file, and the Modifier.Node example is fully executable. Main weaknesses are moderate redundancy (repeated MANDATORY declarations, a trailing IMPORTANT restatement) and inlining of detailed scope-guard rules that belong in the references.

Suggestions

Consolidate the per-category 'MANDATORY: read references/... before flagging' blocks into the single global 'Mandatory Reference Read' workflow step, since each category heading already links its reference file.

Add an explicit final workflow step for verifying fixes (e.g., 'confirm improvements with Macrobenchmark or JankStats before reporting') to close the validation gap in the audit workflow.

Move the long @Stable/@Immutable scope-guard sub-bullets into references/state-and-stability.md, keeping only the decision rule inline, to slim the body toward a true overview.

DimensionReasoningScore

Conciseness

The body is densely packed with expert, version-specific guidance (Compose 1.13 computedStateOf, Strong Skipping trade-offs, snapshot read overhead) and wastes no tokens on basics Claude already knows, fitting the 'efficient; minor instances that could be trimmed' anchor. The 6x repeated 'MANDATORY ... MUST read' blocks (redundant with the workflow's global mandate) and the trailing '<br />' / 'IMPORTANT' restatement keep it below 5.

4 / 5

Actionability

Guidance is fully concrete and executable: exact APIs (Modifier.graphicsLayer, drawWithCache, Path.rewind(), MutableLongSet, packInts), version gates (Compose 1.13+, < 1.12), specific replacement patterns ('contentType = { _, item -> item.type }', 'mutableStateOf(list, neverEqualPolicy())'), and a complete copy-paste-ready Kotlin Modifier.Node migration example covering the common cases.

5 / 5

Workflow Clarity

A clear sequence is present (foundational prerequisites -> exhaustive scan of all 7 categories 'rather than stopping after the first issue found' -> mandatory reference read before flagging or editing), with the read-before-flag gate acting as an explicit checkpoint. Not 5 because verification (benchmarking) is only mentioned inside individual rules rather than as an explicit final validation step with a feedback loop.

4 / 5

Progressive Disclosure

Seven well-organized categories each link to a real bundle file (all referenced paths verified to exist in references/), one level deep with strong 'read before flagging' signaling. Not 5 because the body itself inlines substantial rule detail (e.g., multi-line @Stable/@Immutable scope-guard bullets) that a purer overview-plus-references split would move into the reference files.

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 names a specific domain, states concrete capabilities and outcomes, provides an explicit third-person 'Use this skill when...' trigger clause with concrete trigger phrases, and occupies a distinct niche. The only minor gap is absent common synonyms like 'jank' or 'slow scrolling'.

DimensionReasoningScore

Specificity

Names the domain ('Android Jetpack Compose UI code') with concrete actions and outcomes ('Diagnose and optimize', 'minimize recomposition overhead', 'prevent dropped frames and UI lag'), matching the 'several specific actions; minor gaps' anchor. Not 5 because the two lead verbs are broader than the comprehensive multi-action anchor example.

4 / 5

Completeness

Explicitly answers both what ('Diagnose and optimize Android Jetpack Compose UI code... to minimize recomposition overhead and prevent dropped frames and UI lag') and when ('Use this skill when analyzing performance bottlenecks of existing code') with concrete trigger phrases, matching the 5 anchor. It does not fall to 4 since the when-clause is already explicit and specific, and voice is third person.

5 / 5

Trigger Term Quality

Contains natural phrases users would say ('performance bottlenecks', 'recomposition overhead', 'dropped frames', 'UI lag'), giving good keyword coverage. Not 5 because common synonyms such as 'jank', 'stutter', or 'slow scrolling' are missing; not 3 because coverage is genuinely good rather than partial.

4 / 5

Distinctiveness Conflict Risk

'Android Jetpack Compose' performance optimization is a clear niche with distinct trigger terms (recomposition overhead, dropped frames, UI lag), so conflict risk with generic Compose, Android, or general performance skills is minimal.

5 / 5

Total

18

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 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

relative_links

Relative link issues: 5 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 5 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

android/skills

Path

jetpack-compose/jetpack-compose-performance/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.