axiom-audit-swiftui-layout

Use when the user mentions SwiftUI layout review, adaptive layout issues, GeometryReader problems, or multi-device layout checking.

Quality

75%

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-layout/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and workflow-clear, with executable grep/fix guidance and explicit verification checkpoints. Its weaknesses are mild verbosity from concept explanations and a monolithic structure that keeps reference-worthy catalogs inline rather than splitting them into bundle files.

Suggestions

Trim concept explanations Claude already knows (e.g. the 'Why it matters' column and the non-lazy-stack rationale) to the minimum needed to justify each fix.

Move the 10-pattern anti-pattern catalog and/or the output template into a references/ file (e.g. ANTI_PATTERNS.md) and keep SKILL.md as an overview that links to it one level deep, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly directive (exact grep regexes, copy-paste fixes), but at ~250 lines it includes concept explanations Claude largely already knows (e.g. 'Non-lazy stacks instantiate ALL views upfront... high memory') and a verbose 'Why it matters' column, placing it at 'mostly efficient but could be tightened' rather than the lean anchor 3.	2 / 3
Actionability	Guidance is fully executable — concrete regexes like `\.frame\(width:\s\d{3,}`, exact replacement code such as `.containerRelativeFrame(.horizontal) { w, _ in w 0.5 }`, and a precise output template — matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Phases 1–5 are clearly sequenced with explicit verification checkpoints ('use Read to verify the surrounding context before reporting', 'Require evidence from the Phase 1 map — don't speculate'), a cross-reference severity-bumping step, and a defined output format, matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a monolithic ~250-line single file with no bundle files present and no content split out (the 10-pattern catalog, Phase 3/4 tables, and output template could live in references); it matches 'content that should be separate is inline' rather than the one-level-deep split of anchor 3.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 has strong, natural trigger terms and a clear niche, but it is trigger-only: it never explicitly states the skill's action/capability, leaving the 'what' implied. Adding an explicit capability clause would lift specificity and completeness.

Suggestions

Lead with an explicit capability statement before the trigger clause, e.g. 'Audits SwiftUI views for layout anti-patterns and missing adaptive-layout strategies, reporting issues by severity with fixes.'

Spell out concrete actions the skill performs (detect, verify with Read, severity-bump compound findings, output a Layout Health Score) so the 'what' is explicit, not inferred from trigger nouns.

Dimension	Reasoning	Score
Specificity	The description names the domain and a few action-ish phrases ("SwiftUI layout review", "multi-device layout checking") but does not list concrete, comprehensive capabilities like 'detects anti-patterns, reports severity, suggests fixes'; it sits at 'names domain and some actions, but not comprehensive', short of the multi-action anchor 3.	2 / 3
Completeness	An explicit "Use when ..." clause answers the 'when', but the 'what' (what the skill actually does) is only implied by trigger nouns and is never stated as an explicit action verb, so it matches 'has when but what is missing or only implied' rather than anchor 3's clear what-and-when.	2 / 3
Trigger Term Quality	Natural developer-facing terms are well covered — "SwiftUI layout review", "adaptive layout issues", "GeometryReader problems", and "multi-device layout checking" are phrasings a user would plausibly say, matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The triggers are narrowly scoped to SwiftUI layout auditing (GeometryReader, adaptive layout, multi-device), a clear niche unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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-layout/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.