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 Use this skill to fix code smells, update deprecated APIs, resolve outdated TODOs, apply Kotlin scope functions, flatten deeply nested logic, and resolve lint or detekt warnings.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 lean, actionable, well-organized stewardship skill with a clear workflow and validation checkpoint. It would benefit from explicit error-recovery feedback loops and concrete before/after refactor examples.

Suggestions

Make the VERIFY feedback loop explicit: 'If compile or lint fails, fix the issue and re-run ktfmtFormat/detekt until clean before presenting the PR.'

Add one short before/after Kotlin code block (e.g. a null-check refactored to ?.let, or a multi-line init flattened with apply) to reach copy-paste-ready actionability.

Trim the Philosophy aphorisms or fold them into the relevant instructions to tighten the token budget further.

Dimension	Reasoning	Score
Conciseness	Efficient and well-structured with concrete commands and patterns; only minor padding remains in the aphoristic Philosophy bullets and the detailed Journaling Rules section.	4 / 5
Actionability	Provides concrete executable guidance (./gradlew ktfmtFormat, detekt, lintDebug), specific Kotlin patterns (?.let, ?: run, apply, java.time.Instant), and commit-prefix examples with a sample PR title, but lacks full before/after code blocks.	4 / 5
Workflow Clarity	A clear five-step SCAN/SELECT/REFINE/VERIFY/PRESENT sequence with a VERIFY checkpoint (format, compile, lint), but the validate->fix->retry feedback loop is implicit rather than explicitly stated.	4 / 5
Progressive Disclosure	Self-contained with well-organized sections (Goal, Constraints, Instructions, Examples) and no nested references; the only external file (.jules/steward.md) is a clearly signaled runtime journal, not a buried reference.	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 strong, specific description that clearly communicates a Kotlin-focused code-health niche with concrete actions and explicit trigger guidance. The main gap is the absence of synonyms and file extensions in the trigger phrasing.

Suggestions

Add natural synonyms and file extensions to the trigger clause, e.g. 'when the user asks to refactor .kt files, mentions detekt/lint warnings, or wants to modernize deprecated Kotlin APIs'.

Reframe part of the 'when' around user-mention contexts (e.g. 'Use when the user mentions code smells, deprecated APIs, or detekt warnings') to reach the explicit trigger-phrasing anchor.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions (fix code smells, update deprecated APIs, resolve outdated TODOs, apply scope functions, flatten nested logic, resolve lint/detekt warnings), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Both 'what' (maintains Kotlin codebase health) and 'when' (Use this skill to...) are present with concrete triggers, but the 'when' enumerates tasks rather than user-mention contexts, keeping it just below the explicit-trigger anchor 5.	4 / 5
Trigger Term Quality	Strong domain keywords a Kotlin developer would naturally say (code smells, deprecated APIs, TODOs, scope functions, lint, detekt), but lacks synonyms and file extensions (.kt) that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped to Kotlin idiomatic style, deprecations, and detekt/lint — a clear niche with distinct triggers and minimal overlap with non-Kotlin or non-stewardship 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: 9f8d94d

Reviewed: 7 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.