axiom-audit-swiftdata

Use when the user mentions SwiftData review, @Model issues, SwiftData migration safety, or SwiftData performance checking.

Quality

72%

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-swiftdata/SKILL.md

Quality

Content

88%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 high-quality, actionable auditor skill with concrete grep patterns, verification checkpoints, and a well-sequenced five-phase workflow. Its main weakness is the absence of progressive disclosure — all detail lives inline in one long file with no bundle references to offload the pattern catalog.

Suggestions

Move the 10-pattern detection catalog and/or the Phase 4 compound-severity table into a references file (e.g. references/patterns.md), keeping SKILL.md as an overview that points to it.

Trim the per-pattern 'Issue' explanations to the non-obvious SwiftData-specific mechanics, since Claude can infer general reference-semantics rationale.

Add a brief 'Quick start' summary at the top so the five-phase workflow is skimmable before the detailed phase sections.

Dimension	Reasoning	Score
Conciseness	The body is information-dense with concrete grep patterns, severity tables, and fix snippets rather than padded prose; the per-pattern 'Issue' lines include some mechanics Claude could infer, but overall it assumes competence and earns its length through coverage of 10 patterns plus 5 phases.	4 / 5
Actionability	Provides fully executable guidance: exact Grep regexes, Read-verification steps, copy-paste fixes (e.g. '@Model final class', '@Relationship var tags: [Tag] = []'), and concrete thresholds (5+ indexes, batches of 100-500) covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced five-phase workflow with explicit validation checkpoints ('use Read to verify the surrounding context before reporting', 'Require evidence from the Phase 1 map — don't speculate') and feedback loops for an audit/batch process.	5 / 5
Progressive Disclosure	Well-organized into labeled phases and sections with clear navigation, but it is a long monolithic single file (no bundle files in references/scripts/assets) and some pattern/compound detail could arguably live in reference files; structure is good with minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

56%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 has strong trigger guidance and a distinct SwiftData niche, but it omits any statement of what the skill actually does, leaving the "what" only implied. Adding an explicit capability clause (e.g. "Detects SwiftData anti-patterns and migration/data-loss risks") would raise completeness and specificity.

Suggestions

Add an explicit 'what' clause before the 'Use when' trigger, e.g. 'Detects SwiftData anti-patterns, missing-model registration, and migration/data-loss risks. Use when...'.

Name concrete actions (audits @Model declarations, verifies VersionedSchema coverage, checks background-context isolation) instead of only listing trigger topics.

Consider adding synonyms a user might say ('CoreData-to-SwiftData', 'ModelContainer crashes') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the SwiftData domain and several concrete sub-areas ("@Model issues", "SwiftData migration safety", "SwiftData performance checking"), but describes trigger topics rather than the concrete actions the skill performs (e.g. detecting violations, auditing), leaving capability specificity incomplete.	3 / 5
Completeness	Provides an explicit "Use when..." trigger (the "when") but never states what the skill does (the "what" is only weakly implied via trigger topics), matching the anchor for only-when-present-without-what.	2 / 5
Trigger Term Quality	Includes natural terms a Swift developer would say ("SwiftData review", "@Model issues", "migration safety", "performance checking") with good coverage; only minor synonyms or variations are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (SwiftData, @Model, migration safety) with distinctive triggers and minimal overlap risk with other skills.	5 / 5
	Total	14 / 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-swiftdata/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.