CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

performance-memory-catalyst

Ensures the app runs efficiently and safely by handling memory management, state architecture, and Coroutine optimizations. Use this skill to fix memory leaks (OOM), optimize Coroutine dispatchers, enforce immutable StateFlow architectures, add database indexes, or resolve Compose state bottlenecks.

Quality

86%

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

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, actionable skill body: a clearly sequenced workflow with real validation commands, concrete never/always constraint lists, and a useful Examples section. The main improvements are trimming philosophical filler, adding brief code snippets for the prescribed patterns, and stating the failure-recovery loop after verification.

Suggestions

Drop or compress the "Philosophy" bullet list; it restates principles Claude can infer from the constraints and instructions.

Add one-line code snippets for the key prescribed patterns (immutable UiState data class, @Immutable parameter, dispatcher injection) to move guidance from descriptive to copy-paste ready.

Add an explicit recovery step in VERIFY: what to do when `lintDebug`/`testDebugUnitTest` fail (fix, re-run, only then create the PR).

DimensionReasoningScore

Conciseness

The body is lean and list-driven with concrete commands, but a few tokens don't earn their place: the "Philosophy" aphorisms ("State is a snapshot; UI is a pure function of State") and rules restating knowledge Claude already has ("Never use the prefix refactor:", `.use {}` wrapping).

4 / 5

Actionability

Concrete and executable throughout — specific gradle commands (`./gradlew ktfmtFormat`, `lintDebug`, `testDebugUnitTest`) and precise hunt patterns (`GlobalScope.launch`, missing `unregisterReceiver`, unstable Compose parameters). Minor gaps: no code snippets for the `UiState`/`@Immutable` patterns it prescribes, and "Ensure no race conditions were introduced" gives no method for checking.

4 / 5

Workflow Clarity

A clear five-step sequence (PROFILE → SELECT & PROPOSE → OPTIMIZE → VERIFY → PRESENT) with an explicit user-approval checkpoint and concrete validation commands. It falls short of the top anchor only because there is no explicit feedback loop for what to do when lint or tests fail.

4 / 5

Progressive Disclosure

A single, well-sectioned file (Goal, Constraints, Instructions, Examples) with no content that clearly belongs in a separate bundle file; the one external reference (`.agents/skills/catalyst/journal.md`) is clearly signaled and one level deep. There are no references/, scripts/, or assets/ directories, and none are needed.

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 description: third-person, concrete, and complete with an explicit "Use this skill to" trigger clause listing five specific actions. Keyword coverage is good but misses a few natural user phrasings (recomposition, ANR, jank), and the generic efficiency opener slightly blurs distinctiveness.

Suggestions

Add natural user phrasings such as "recomposition", "ANR", "jank", or "app is slow/laggy" to the trigger clause to broaden keyword coverage.

Consider naming the platform (Android/Kotlin) in the first sentence to sharpen distinctiveness against general performance or database skills.

Trim the vague opener "Ensures the app runs efficiently and safely" in favor of leading with the concrete capability list.

DimensionReasoningScore

Specificity

Lists five concrete actions — "fix memory leaks (OOM)", "optimize Coroutine dispatchers", "enforce immutable StateFlow architectures", "add database indexes", "resolve Compose state bottlenecks" — giving comprehensive coverage of the skill's capabilities with no significant gaps.

5 / 5

Completeness

Explicitly answers both "what" ("Ensures the app runs efficiently and safely by handling memory management, state architecture, and Coroutine optimizations") and "when" via a concrete "Use this skill to…" clause with multiple trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("memory leaks (OOM)", "Coroutine dispatchers", "StateFlow", "Compose state", "database indexes") that users would plausibly say, but common variations like "recomposition", "ANR", "jank", or a plain "app is slow" are missing.

4 / 5

Distinctiveness Conflict Risk

The trigger set targets a clear Android/Kotlin performance niche with minimal conflict risk, but the broad opener "Ensures the app runs efficiently and safely" and triggers like "add database indexes" leave minor overlap risk with general database or refactoring skills.

4 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

nekomangaorg/Neko

Path

.agents/skills/catalyst/SKILL.md

Revision

3c3dce0

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill