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.
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description with excellent trigger terms and completeness. It clearly identifies when to use the skill with natural developer language. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., analyzing composition traces, identifying state issues, optimizing remember usage).
Suggestions
Expand the capabilities section with more specific actions like 'analyze composition traces, identify unstable parameters, optimize state hoisting, review remember/derivedStateOf usage'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Jetpack Compose) and some actions ('audit and improve', 'code review and architecture'), but doesn't list multiple concrete specific actions like 'identify unnecessary recompositions, optimize state hoisting, analyze composition traces'. | 2 / 3 |
Completeness | Clearly answers both what ('Audit and improve Jetpack Compose runtime performance from code review and architecture') and when ('Use when asked to diagnose slow rendering, janky scrolling, excessive recompositions, or performance issues in Compose UI') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'slow rendering', 'janky scrolling', 'excessive recompositions', 'performance issues', 'Compose UI'. These are terms developers naturally use when experiencing these problems. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Jetpack Compose performance specifically, with distinct triggers like 'recompositions', 'Compose UI', and 'janky scrolling' that wouldn't overlap with general Android or other UI framework skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill document that efficiently covers Compose performance auditing end-to-end. It provides concrete, executable code examples with clear BAD/GOOD patterns, a well-defined workflow with decision points and validation steps, and appropriate progressive disclosure through organized sections. The stability checklist table is particularly useful for quick reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with Android/Compose development. No unnecessary explanations of basic concepts; every section provides actionable, specific guidance without padding. | 3 / 3 |
Actionability | Provides fully executable Kotlin code examples with clear BAD/GOOD patterns, specific tool names (Layout Inspector, Perfetto, Macrobenchmark), and concrete annotations (@Stable, @Immutable). All examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear decision tree at the start, numbered workflow steps (1-5), explicit validation step (Section 5: Verify), and feedback loop asking users to re-run profiling and compare metrics. The workflow handles both code-provided and symptom-only scenarios. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to workflow to code smells to verification. External references are one level deep at the end. Content is appropriately organized with a stability checklist table for quick reference. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
3f68e39
- 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.