compose-performance-audit

Audit and improve Jetpack Compose runtime performance from code review and architecture. Use when asked to diagnose slow rendering, janky scrolling, excessive recompositions, or performance issues in Compose UI.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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 highly actionable, well-structured Compose performance guide with strong executable examples and a sensible workflow. The main weakness is duplicated culprit lists across sections that inflate tokens without adding guidance.

Suggestions

Dedupe the overlapping culprit lists in 'Code-First Review' and 'Analyze and Diagnose' into a single shared checklist referenced by both sections.

Strengthen the Verify step into an explicit feedback loop: if recomposition counts or frame timing did not improve, return to Analyze/Remediate with the new evidence.

Reconsider the 'Object allocation in composition' example — remembering a fully static Modifier chain is rarely a meaningful win and may mislead; show a dynamic-keyed modifier case instead.

Dimension	Reasoning	Score
Conciseness	Mostly efficient lists and BAD/GOOD code with little concept over-explaining, but the culprit lists in 'Code-First Review' and 'Analyze and Diagnose' repeat near-identical items (recomposition storms, heavy work, large images) that could be merged.	3 / 5
Actionability	Fully executable Kotlin BAD/GOOD pairs covering the common cases (lambda capture, sorting in composition, missing keys, unstable data classes, deferred state reads), plus a concrete stability checklist with named annotations and APIs.	5 / 5
Workflow Clarity	Clear numbered sequence (Code-First → Profile → Analyze → Remediate → Verify) with a decision tree and a Verify checkpoint comparing recomposition/frame metrics; the verify step is soft ('ask the user to re-run') without an explicit not-improved recovery loop.	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear section headers and external doc links at the end; no nested references, though at ~200 lines some material (code smells, stability table) could arguably be split into a reference file.	4 / 5
	Total	16 / 20 Passed

Description

95%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, third-person description that clearly states both capability and trigger conditions with domain-natural language. Minor specificity gap only in the breadth of named remediation actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Jetpack Compose runtime performance') and several concrete actions ('Audit and improve', 'diagnose slow rendering, janky scrolling, excessive recompositions'); falls short of the 5 anchor's exhaustive multi-action list.	4 / 5
Completeness	Explicitly answers both what ('Audit and improve Jetpack Compose runtime performance from code review and architecture') and when ('Use when asked to diagnose...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms a developer would actually say — 'slow rendering', 'janky scrolling', 'excessive recompositions', 'performance issues in Compose UI' — covering the core synonyms for the domain.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Compose runtime performance) with distinct Compose-specific triggers (recompositions, janky scrolling) that minimally overlap with general Android or generic performance skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: new-silvermoon/awesome-android-agent-skills
Path: .github/skills/performance/compose-performance-audit/SKILL.md
Commit: 82900ea

Reviewed: 1 day 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.