Tessl • The management layer for AI agent skills

SkillPublic

architecture-overclock

Resolves deep, structural performance bottlenecks in the Kotlin Android codebase. Use this skill for macro-level improvements like fixing Room N+1 relation queries, optimizing complex multi-measure Compose layouts, implementing Paging 3, refactoring massive UiState classes, or resolving background StateFlow collection battery drains.

Quality

89%

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

85%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, self-contained skill body with a validated, approval-gated workflow and concrete commands throughout. Its residual weaknesses are mild persona/decorative padding and an abstract central implementation step that could use one concrete before/after code sketch.

Suggestions

Trim the persona and philosophy flourishes (the 'rebuild the transmission' line and repeated exclusions already covered by the Never-do list) to tighten token efficiency.

Add one short before/after code sketch under OVERCLOCK (e.g., the N+1 loop query vs. the @Transaction @Relation replacement) to make the core step fully executable.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes domain competence — it never explains concepts Claude already knows — but includes minor trimmable padding: the persona flourish ('You don't just patch the engine; you rebuild the transmission'), philosophy bullets, and partial redundancy between 'Scope & Exclusions' and the 'Never do' list. Not a 5 because decorative persona content does not earn its tokens.	4 / 5
Actionability	Concrete commands are given ('./gradlew ktfmtFormat', './gradlew testDebugUnitTest', './gradlew lintDebug'), techniques are named specifically (@Transaction/@Relation, repeatOnLifecycle, shareIn/stateIn), and the PR prefix convention is explicit. The OVERCLOCK step itself ('Rewrite the inefficient data flow or layout phase') stays abstract with no code snippet, leaving minor gaps.	4 / 5
Workflow Clarity	A clear five-step sequence (PROFILE → SELECT & PROPOSE → OVERCLOCK → VERIFY → PRESENT) with explicit validation checkpoints: prove the bottleneck before changing anything, wait for user approval before modifying code, run tests/lint before the PR, and benchmark to verify impact. Checkpoints are explicit rather than implicit, matching the top anchor.	5 / 5
Progressive Disclosure	No bundle files exist, and none are needed: the ~58-line body is cleanly sectioned (Goal, Constraints, Instructions, Examples) with no content that belongs in a separate reference file. The only external path (.agents/skills/overclock/journal.md) is a runtime journaling target, clearly signaled — navigation is trivial.	5 / 5
	Total	18 / 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: it clearly states what the skill does, when to use it, and names five concrete macro-level optimizations with mostly natural trigger terms. Its only weaknesses are a few missing common synonyms (jank, recomposition, memory leak) and slight overlap risk with more granular Android performance skills.

Suggestions

Add one or two widely-used natural trigger phrases such as 'jank', 'recomposition storms', or 'memory leaks' to broaden the natural-language triggers.

Sharpen the boundary with micro-optimization skills in the description itself (e.g., 'for deep architectural fixes, not simple remember blocks') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'fixing Room N+1 relation queries, optimizing complex multi-measure Compose layouts, implementing Paging 3, refactoring massive UiState classes, or resolving background StateFlow collection battery drains' — giving comprehensive coverage of the skill's domain. This matches the anchor for multiple specific concrete actions, not the score-4 anchor with 'minor gaps in coverage'.	5 / 5
Completeness	It explicitly answers both what ('Resolves deep, structural performance bottlenecks in the Kotlin Android codebase') and when ('Use this skill for macro-level improvements like...') with concrete trigger phrases, mirroring the top anchor's structure.	5 / 5
Trigger Term Quality	Good natural keyword coverage: 'performance bottlenecks', 'Room N+1', 'Paging 3', 'Compose layouts', 'battery drains' are phrases users would actually say. A few common natural terms are missing (e.g., 'jank', 'recomposition', 'slow app', 'memory leak'), so it falls just short of the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	The macro/architecture-level Android performance niche is mostly distinct with specific triggers (Room N+1, Paging 3, StateFlow battery drains), but phrases like 'optimizing Compose layouts' could also trigger a micro-optimization or general Android skill, leaving minor overlap risk with closely related skills.	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/overclock/SKILL.md
Revision: 3c3dce0

Reviewed: 1 month ago

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.

architecture-overclock

Table of Contents

Is this your skill?