aif-architecture

Generate architecture guidelines for the project. Analyzes tech stack from DESCRIPTION.md, recommends an architecture pattern, and creates .ai-factory/ARCHITECTURE.md. Use when setting up project architecture, asking "which architecture", or after /aif setup.

Quality

82%

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

77%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 content is a well-structured, action-oriented workflow with strong validation checkpoints and clean progressive disclosure to one reference file. Its main weakness is conciseness: the skill-context handling and emphasis phrasing are somewhat repetitive and could be trimmed.

Suggestions

Tighten the Step 0 skill-context block: collapse the repeated 'CRITICAL'/'MUST' bullets into a single concise rule statement (skill-context overrides general rules and must be enforced on every output), since the current phrasing restates the override principle three times.

Consolidate the Step 1 argument-mapping bullets so each mapping (direct, legacy alias, with-suffix, without-suffix) appears once in a compact table rather than across multiple bulleted sub-lists with overlapping prose.

Reduce redundant emphasis words ('CRITICAL', 'MANDATORY', 'MUST') throughout — use them once per section where a checkpoint truly needs enforcement rather than repeating them on adjacent bullets.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the skill-context block and repeated 'CRITICAL'/'MUST' emphasis in Steps 0 and 1.5 could be tightened without losing meaning, fitting 'mostly efficient with some unnecessary padding'.	3 / 5
Actionability	Provides concrete executable guidance — exact AskUserQuestion prompt wording, decision mapping tables, an artifact template, and specific file paths — with only minor gaps (template placeholders are intentional flexibility), matching 'mostly executable guidance with minor gaps'.	4 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced with explicit validation and enforcement checkpoints (read references before generating, codebase alignment check that must stop and ask, post-generation skill-context verification and fix-before-presenting), matching the 'explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	SKILL.md is a workflow overview with a single well-signaled one-level-deep reference (references/architecture.md, which exists and is referenced explicitly multiple times), with content appropriately split, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	17 / 20 Passed

Description

87%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 is strong: it states concrete actions, gives explicit natural-language triggers for both what and when, and occupies a distinct niche with low conflict risk. It sits just below top on specificity and trigger coverage only because the action/keyword lists are not exhaustive.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Analyze tech stack from DESCRIPTION.md', 'recommends an architecture pattern', 'creates .ai-factory/ARCHITECTURE.md') with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what the skill does (analyze, recommend, create the artifact) and when to use it with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('setting up project architecture', 'asking which architecture', 'after /aif setup') with good but not exhaustive keyword coverage, so anchor 4 fits better than 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear architecture-generation niche with distinctive triggers ('which architecture', '/aif setup') and minimal overlap risk, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: lee-to/ai-factory
Path: skills/aif-architecture/SKILL.md
Commit: e144f95

Reviewed: 5 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.