performance-bolt

Identifies and implements micro-level Kotlin, Jetpack Compose, Coroutine, and Room database performance optimizations. Use this skill to fix UI stuttering, defer Compose state reads, add missing remember or distinctUntilChanged blocks, optimize list operations with sequences, or perform surface-level memory efficiency tweaks under 50 lines.

Quality

83%

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

78%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 well-structured, concrete skill body with an explicit approval-and-verification workflow and no token waste on concepts Claude already knows. Tightening the PROFILE/Examples redundancy and spelling out the test-failure retry loop would lift it to top marks.

Suggestions

Deduplicate between the PROFILE list and the Examples list — both cover asSequence, mapNotNull, distinctUntilChanged, and collectAsStateWithLifecycle; keep one as the scan checklist and the other as concrete fixes.

Make the VERIFY step's feedback loop explicit, e.g. 'If lint or tests fail, fix the reported issues and re-run before proceeding to PRESENT.'

Add one or two full copy-paste code blocks (before/after) for the highest-impact patterns like derivedStateOf scroll reads so examples are executable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is dense and action-oriented with no padded concept explanations, but the long Examples list overlaps the PROFILE section (both cover asSequence, mapNotNull, distinctUntilChanged, collectAsStateWithLifecycle), so some redundancy could be trimmed.	4 / 5
Actionability	Provides concrete gradle commands and specific API calls (derivedStateOf {}, Modifier.offset { ... }, .associateBy { it.id }, .chunked(500), perf: PR prefix), but examples are pattern bullets rather than full copy-paste-ready code blocks.	4 / 5
Workflow Clarity	Clear 5-step sequence (PROFILE → SELECT & PROPOSE → OPTIMIZE → VERIFY → PRESENT) with an explicit user-approval gate and validation commands (ktfmtFormat, lint, tests), though the verify→fix→retry feedback loop is implied rather than spelled out.	4 / 5
Progressive Disclosure	A single self-contained file with no external references and well-organized sections (Goal, Constraints, Instructions, Examples), meeting the simple-skill exception for clean one-level organization.	5 / 5
	Total	17 / 20 Passed

Description

88%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, specific description that covers both capabilities and explicit use-when triggers with natural developer language. Minor keyword-synonym gaps keep trigger_term_quality and distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the Kotlin/Compose/Coroutine/Room domain — 'fix UI stuttering, defer Compose state reads, add missing remember or distinctUntilChanged blocks, optimize list operations with sequences' — giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Explicitly answers both 'what' ('Identifies and implements micro-level ... performance optimizations') and 'when' ('Use this skill to fix UI stuttering, defer Compose state reads ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural developer phrases like 'fix UI stuttering' and 'add missing remember', but omits common synonyms (e.g. 'jank', 'recompositions') and file extensions, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The micro-level perf niche under 50 lines with Compose/Room-specific triggers is mostly distinct, with only minor overlap risk against a general refactoring skill.	4 / 5
	Total	18 / 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: nekomangaorg/Neko
Path: .agents/skills/bolt/SKILL.md
Commit: 9852a3f

Reviewed: 3 days 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.