CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-modernize

Use when the user wants to modernize iOS code to iOS 17/18 patterns, migrate from ObservableObject to @Observable, update @StateObject to @State, or adopt modern SwiftUI APIs.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A highly actionable, well-structured migration skill whose dense code examples and decision guidance are its strengths. The main weakness is redundancy between the per-pattern Detection blocks and the 'Audit Process' section, plus a verbose inline output template.

Suggestions

Remove the duplicate Grep detection lists in 'Audit Process > Step 2' since each Pattern already specifies its own Detection greps; cross-reference them instead.

Move the large Output Format markdown template into a references file (e.g. references/output-template.md) and link to it, keeping only a brief shape description inline.

Add an explicit mid-migration validation checkpoint (e.g. 'after migrating models, build and confirm no @Published references remain before touching view wrappers') to strengthen the feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient with dense, useful code examples, but the 'Audit Process' section restates the per-pattern Grep detections already listed under each pattern, and the long inline Output Format template adds padding that could be trimmed.

3 / 5

Actionability

Copy-paste-ready Grep patterns, side-by-side legacy/modern Swift examples for all eight patterns, explicit migration steps, and a decision flowchart give fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Clear scan→categorize→report sequence with a Migration Order and a post-migration Verification section, but validation is end-of-process rather than interleaved as explicit validate→fix→retry checkpoints.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with one appropriately signaled external reference (axiom-swift/swift-modern.md for Pattern 8); no bundle files exist, and the long inline Output Format template is a minor organization gap.

4 / 5

Total

16

/

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.

A strong, third-person description that pairs explicit 'Use when' triggers with concrete named API migrations, giving clear what/when guidance and low conflict risk. Minor specificity leakage from the generic 'adopt modern SwiftUI APIs' clause keeps it just short of perfect.

DimensionReasoningScore

Specificity

Lists several concrete migrations (ObservableObject→@Observable, @StateObject→@State) plus a generic trailing clause ('adopt modern SwiftUI APIs'), leaving minor coverage gaps rather than comprehensive enumeration.

4 / 5

Completeness

Explicitly answers both what (modernize/migrate/update/adopt) and when ('Use when the user wants to modernize iOS code to iOS 17/18 patterns...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural developer phrasings like 'modernize iOS code' and the specific API names users would name, but misses a few synonyms (e.g. 'Observation framework', 'SwiftUI observation').

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (iOS 17/18 SwiftUI modernization) with distinct, specific triggers that are unlikely to fire for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (569 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
CharlesWiltgen/Axiom
Reviewed

Table of Contents

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.