architecture

Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.

1.69x

Quality

81%

Does it follow best practices?

Impact

83%

1.69x

Average score across 3 eval scenarios

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.

The body is a well-organized overview: a decision tree routes new code to concrete directories, process-boundary and naming tables give executable rules, and detailed material is cleanly offloaded to three real one-level-deep reference files. It is concise and actionable, lacking only an explicit validation feedback loop for structural changes.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes competence: tables, a decision tree, and short rule statements carry the load without explaining what Electron processes or React are. A few table cells add minor justification ('Reason' columns) that could be trimmed, but nothing is padded.	4 / 5
Actionability	Concrete, executable guidance dominates: exact target directories (e.g. `packages/desktop/src/process/bridge/`), real filenames (`CronService.ts`, `useAutoScroll.ts`), and a TypeScript code example showing a forbidden import vs the correct IPC call. Minor gaps: the decision-tree destinations are paths without the actual import/code to wire them.	4 / 5
Workflow Clarity	The decision tree gives an unambiguous routing sequence and the Quick Checklist acts as a verification checkpoint, with the process-boundary rules framed as hard, crash-causing rules. It stops short of a 5 because there is no explicit validate-then-fix feedback loop for batch/destructive structural changes.	4 / 5
Progressive Disclosure	The SKILL.md is a clear overview that delegates the three large detail areas (renderer, process, project layout) to one-level-deep reference files, each linked with a labeled bullet explaining its scope, and all three referenced files exist in ./references/. Navigation is easy and content is appropriately split.	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.

The description clearly answers both what the skill does and when to use it via an explicit five-item 'Use when' clause, with concrete artifact names that aid distinctiveness. It is strong overall, with minor room to sharpen action phrasing and add synonyms.

Suggestions

Reframe the numbered items as concrete capabilities the skill performs (e.g., 'Determines correct file placement', 'Converts single-file components to directories') rather than only trigger situations, to lift specificity toward 5.

Add a couple of natural synonyms a user might say (e.g., 'where to put new code', 'folder structure', 'code organization') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Project architecture and file structure conventions') and several concrete actions (creating files, deciding placement, converting components to directories, reviewing structure, adding bridges/services/agents/workers), though the actions are phrased as trigger situations rather than discrete capabilities, leaving minor coverage gaps.	4 / 5
Completeness	Clearly states 'what' (architecture and file structure conventions) and provides an explicit 'Use when' clause with five numbered concrete trigger scenarios, satisfying both what and when.	5 / 5
Trigger Term Quality	Includes natural task phrases users would say ('Creating new files or modules', 'Deciding where code should go', 'Reviewing code for structure compliance') plus concrete artifact terms ('bridges, services, agents, or workers'), though it lacks synonyms or broader phrasings a user might use.	4 / 5
Distinctiveness Conflict Risk	The Electron multi-process architecture niche and the specific artifact list (bridges, services, agents, workers) make it largely distinct, but the fairly broad 'architecture and file structure conventions' framing could overlap with a general project-layout skill.	4 / 5
	Total	17 / 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: iOfficeAI/AionUi
Path: .claude/skills/architecture/SKILL.md
Commit: 18022a4

Reviewed: ~22 hours 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.