axiom-audit-swiftui-nav

Use when the user mentions SwiftUI navigation issues, deep linking problems, state restoration bugs, or navigation architecture review.

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

92%

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 tight, highly actionable auditor prompt with clear phased sequencing and explicit verification steps. Its only structural weakness is progressive disclosure: it is monolithic with no bundle/reference files, so all detail is front-loaded in one file rather than split behind signaled references.

Suggestions

Consider moving the 10 anti-pattern detection patterns or the output-format template into a reference file (e.g. references/detection-patterns.md) referenced from a concise overview, so the SKILL.md body stays a lean entry point.

Add an explicit "See references/..." pointer once details are split out, keeping references one level deep and clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — each anti-pattern is a tight Pattern/Search/Issue/Fix block with concrete grep patterns and fix snippets, and it avoids explaining SwiftUI/navigation concepts Claude already knows. Not below 3 because there is no padded conceptual exposition; every section adds concrete detection or fix value.	3 / 3
Actionability	Guidance is copy-paste ready: exact grep patterns (e.g. `NavigationStack {`, `.navigationDestination(for:`) and concrete fix code (e.g. "Add `@State private var path = NavigationPath()` and bind with `NavigationStack(path: $path)`"). Not below 3 because instructions are executable and specific rather than abstract.	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," plus a false-positives checklist and output-limit rules. Not below 3 because validation/verification is explicit rather than implicit.	3 / 3
Progressive Disclosure	The skill is a single self-contained file with no bundle files (references/, scripts/, assets/ absent) and no file-level reference structure; the 10 detection patterns and output templates are all inline. Not a 3 because there is no overview-to-reference split or one-level-deep signaled references; not a 1 because the content is well-sectioned by phases rather than an unstructured wall of text.	2 / 3
	Total	11 / 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, distinctive niche, but it leads entirely with the "when" clause and leaves the concrete "what" (detect anti-patterns, map architecture, produce a health score) implicit. Adding an explicit capability statement before the "Use when" clause would raise completeness and specificity.

Suggestions

Lead with a concrete action clause, e.g. "Detects SwiftUI navigation anti-patterns, maps navigation architecture, and produces a navigation health score." before the "Use when..." trigger.

Name the concrete deliverable (e.g. "audit report with severity-ranked issues and fixes") so the "what" is explicit, not just the "when".

Dimension	Reasoning	Score
Specificity	The description names a clear domain ("SwiftUI navigation issues, deep linking problems, state restoration bugs, or navigation architecture review") but states only an implied action ("review") rather than enumerating concrete capabilities like detecting anti-patterns, mapping architecture, or scoring health. Not a 3 because no multiple specific concrete actions are listed; not a 1 because the domain and several problem areas are named rather than vague.	2 / 3
Completeness	The "when" is explicit ("Use when the user mentions..."), but the "what" is only implied via "navigation architecture review" rather than stated as concrete actions. Not a 3 because it does not clearly answer both what AND when; not a 1 because the trigger guidance is strong and the domain makes the purpose discernible.	2 / 3
Trigger Term Quality	"SwiftUI navigation issues, deep linking problems, state restoration bugs, navigation architecture review" are natural phrases a developer would actually say when they need this skill, with good coverage of common variations. Not below 3 because the terms are user-natural rather than obscure jargon.	3 / 3
Distinctiveness Conflict Risk	The niche is narrowly scoped to SwiftUI navigation correctness, with triggers unlikely to fire for unrelated skills (the body even deflects performance to a separate skill). Not below 3 because the triggers are specific and unlikely to conflict with sibling skills.	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-nav/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.