code-steward

Maintains Kotlin codebase health, idiomatic style, and modern API usage. Use this skill to fix code smells, update deprecated APIs, resolve outdated TODOs, apply Kotlin scope functions, flatten deeply nested logic, and resolve lint or detekt warnings.

Quality

81%

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, actionable instruction skill with a clear sequenced workflow and validation checkpoint. The main improvements would be adding an explicit error-recovery feedback loop and a concrete before/after refactor example.

Suggestions

Add an explicit feedback loop to the VERIFY step, e.g. 'If compile or lint fails, fix the issue and re-run ktfmtFormat/detekt until both pass.'

Include one short before/after code diff in the Examples section (e.g. a verbose null check vs. ?.let) to make the refactor pattern copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean and punchy with aphoristic philosophy bullets and no basic-concept padding; minor redundancy such as 'java.util.Date to java.time.Instant' appearing in both REFINE and Examples.	4 / 5
Actionability	Concrete copy-paste commands (./gradlew ktfmtFormat, detekt, lintDebug), specific idioms (?.let, ?: run, apply, when), and a PR-title example; gaps are minor — no before/after refactor diff is shown.	4 / 5
Workflow Clarity	Clear SCAN→SELECT & PROPOSE→REFINE→VERIFY→PRESENT sequence with an approval gate and a VERIFY validation step, but it stops short of an explicit 'if validation fails, fix and re-run' feedback loop.	4 / 5
Progressive Disclosure	Roughly 50 lines, single file, well-organized into Goal/Constraints/Instructions/Examples with no nested references and no need for external bundle files.	5 / 5
	Total	17 / 20 Passed

Description

83%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 specific, well-triggered, Kotlin-scoped description that clearly conveys both purpose and invocation conditions. The only weakness is that the 'when' guidance reuses the action list rather than naming separate user-facing trigger situations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'fix code smells, update deprecated APIs, resolve outdated TODOs, apply Kotlin scope functions, flatten deeply nested logic, and resolve lint or detekt warnings' — giving comprehensive coverage.	5 / 5
Completeness	Clear 'what' (Kotlin codebase health, idiomatic style, modern API usage) plus a 'Use this skill to...' trigger clause; the 'when' restates actions rather than naming distinct user situations, so it is not maximally explicit.	4 / 5
Trigger Term Quality	Strong natural terms with synonyms (lint/detekt, deprecated APIs, TODOs) but missing file-extension variants like .kt/.kts that a user might mention.	4 / 5
Distinctiveness Conflict Risk	Firmly Kotlin-specific niche (code stewardship, detekt, scope functions) with distinct triggers and minimal overlap risk with other skills.	5 / 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/steward/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.