axiom-audit-swiftui-architecture

Use when the user mentions SwiftUI architecture review, separation of concerns, testability issues, or "logic in view" problems.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-audit-swiftui-architecture/SKILL.md

Quality

Content

82%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 dense, actionable audit playbook: concrete grep patterns, severity-bumped compound findings, checklists, and a complete output template, all assuming Claude's competence. It loses a point on conciseness to minor redundancy and on workflow clarity to the absence of a fix-retry loop, which is inherent to a read-only audit.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no 'what is SwiftUI' padding) and every section earns its tokens — grep patterns, severity tables, compound-finding rules, and a false-positive list. It is not 5 because at ~220 lines some tables (Phase 3, Phase 4) and the scoring prose carry minor redundancy that could be tightened.	4 / 5
Actionability	Copy-paste-ready Grep/Glob patterns, explicit file-exclusion globs, concrete fix code (e.g., "let item: Item", "@Binding var item: Item", "@Bindable var model: ItemModel"), and a full output-format template cover the common audit cases. Per the instruction-skill scoring note, the absence of full fix code blocks is not penalized because the guidance is concrete and specific.	5 / 5
Workflow Clarity	A clear five-phase sequence (Map → Detect → Reason → Cross-Reference → Score) with explicit verification checkpoints ("use Read to verify the surrounding context before reporting", "Require evidence from the Phase 1 map — don't speculate") and output limits. It is not 5 because, being a read-only audit, there is no validate→fix→retry feedback loop of the kind the anchor-5 example describes.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so this is a single well-organized SKILL.md with clear section headers and a 'Related' pointer to sibling skills. Structure is good and navigation within the file is easy. It is not 5 because some content (the anti-pattern catalog, compound-finding table, output template) is inlined that, in a larger bundle, would live one level deep in reference files.	4 / 5
	Total	17 / 20 Passed

Description

70%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 uses proper third-person voice and includes an explicit 'Use when' trigger clause with natural, specific terms. It is strong on trigger quality and completeness but the 'what' is terse and only one concrete action (review) is named, keeping specificity at the midpoint.

Suggestions

Lead with one or two more concrete actions (e.g., 'Detects logic-in-view and untestable boundaries, maps view/model separation') before the 'Use when' clause to raise specificity.

Add a synonym or variant trigger (e.g., 'MVVM/TCA review', 'view model bloat') to push trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	Quotes "SwiftUI architecture review, separation of concerns, testability issues, or 'logic in view' problems" — it names the domain and several review targets but only one concrete action (review/audit), not a comprehensive list of specific actions. It sits at the 'names domain and 1-2 concrete actions' anchor rather than 4, which requires several distinct specific actions.	3 / 5
Completeness	It has an explicit "Use when the user mentions ..." clause (clear 'when') and a stated 'what' ("SwiftUI architecture review"), so both are present. It is not 5 because the 'what' is terse and the triggers, while concrete, could be more fully enumerated.	4 / 5
Trigger Term Quality	Quotes natural phrases a user would actually say — "SwiftUI architecture review", "separation of concerns", "testability issues", "logic in view" — giving good keyword coverage. It is not 5 because there are no synonyms or variant phrasings beyond this single set.	4 / 5
Distinctiveness Conflict Risk	The SwiftUI architecture-review niche is mostly distinct with specific triggers and low conflict risk. It is not 5 because sibling SwiftUI auditors (performance, navigation) occupy overlapping SwiftUI territory, creating minor overlap risk.	4 / 5
	Total	15 / 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: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-audit-swiftui-architecture/SKILL.md
Commit: 69ffef6

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.