structural-architect

Improves project modularity, organization, and clean architecture by moving misplaced files or packages. Use this skill to move cohesive classes together, fix wrong layer violations (e.g., UI models in the Data layer), clean up generic 'Utils' packages, extract interfaces to pure domain packages, and enforce feature-based or layer-based package structures.

Quality

85%

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 concrete verification commands. Main weaknesses are minor verbosity/persona padding and the lack of an explicit error-recovery feedback loop in the VERIFY step.

Suggestions

Add an explicit error-recovery loop to the VERIFY step, e.g. 'If assembleDebug or tests fail: fix imports/package declarations and re-run until green' — this would lift workflow_clarity to 5.

Trim the persona intro and philosophy aphorisms, and de-duplicate the approval/format instructions that appear in both 'Always do' and the Instructions steps to improve conciseness.

Give the SCAN step a concrete search heuristic or command (e.g. a grep/find pattern for 'Util'/'Helper' packages or layer-misplaced classes) to make it fully actionable.

Dimension	Reasoning	Score
Conciseness	Mostly lean with terse bullet imperatives and real gradle commands, but the persona intro ('You are The Architect 🏗️'), philosophy aphorisms ('A place for everything...'), and some duplication between the 'Always do' list and the Instructions steps could be trimmed. Not a 5 because of these minor padding/repetition instances.	4 / 5
Actionability	Provides concrete, copy-pasteable commands (./gradlew ktfmtFormat, testDebugUnitTest, assembleDebug) and an explicit PR-title format example, but the SCAN step is descriptive ('Hunt for Utils packages...') rather than giving an executable search command. Mostly executable with minor gaps.	4 / 5
Workflow Clarity	Clear sequenced workflow (SCAN → SELECT & PROPOSE → MOVE → VERIFY → PRESENT) with an explicit user-approval gate and a VERIFY step that runs format, compile, and tests. Validation is present so the destructive-operation cap does not apply; held at 4 because there is no explicit error-recovery feedback loop (what to do if tests/compile fail).	4 / 5
Progressive Disclosure	A self-contained, well-organized single-purpose skill under ~50 lines with no bundle files needed; sections (Goal, Constraints, Instructions, Examples) are clearly headed and the one external reference (.jules/architect.md) is well-signaled, matching the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

92%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 states both what the skill does and when to use it, with concrete architectural trigger phrases and low conflict risk. Only minor weakness is trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'moving misplaced files or packages', 'move cohesive classes together', 'fix wrong layer violations (e.g., UI models in the Data layer)', 'clean up generic Utils packages', 'extract interfaces to pure domain packages', 'enforce feature-based or layer-based package structures' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers both 'what' (improves modularity by moving misplaced files/packages) and 'when' via an explicit 'Use this skill to...' clause with concrete trigger phrases, matching the anchor for full what-and-when coverage.	5 / 5
Trigger Term Quality	Good coverage of natural terms a developer would say ('move misplaced files', 'clean up Utils packages', 'fix wrong layer violations', 'feature-based/layer-based package structures'), but a few common phrasings like 'reorganize packages' or 'refactor file structure' are absent. Not a 5 because the synonym set is not fully exhaustive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — structural/modular architecture moves with distinctive triggers (layer violations, Utils dumping grounds, interface extraction) — giving it minimal overlap with other skills. Voice is third person ('Improves...'), so no voice penalty applies.	5 / 5
	Total	19 / 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/architect/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.