CtrlK
BlogDocsLog inGet started
Tessl Logo

swiftui-view-refactor

Refactor SwiftUI view files into stable, testable structure. Use when splitting large views, tightening data flow, or cleaning Observation ownership.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 well-structured, actionable refactor guide with strong executable code examples and sensible progressive disclosure to a real reference file. Its main gap is the absence of explicit validation/verification checkpoints in the workflow, which is notable for a code-modifying skill.

Suggestions

Add an explicit verification step to the Workflow, e.g. 'Build, run existing tests, and confirm UI/behavior is unchanged before finishing' with a fix-and-retry loop on failure.

Tighten the Notes section by removing guidance already stated in Core Guidelines to reduce redundancy.

Consider moving the detailed Prefer/Avoid code blocks for sections 3-4 into references/ to keep SKILL.md as a leaner overview.

DimensionReasoningScore

Conciseness

The body assumes SwiftUI competence and avoids explaining basic concepts, but the Notes section restates several Core Guidelines points and the Prefer/Avoid blocks add length that could be trimmed slightly.

4 / 5

Actionability

Concrete, copy-paste-ready Swift examples (dedicated subview structs, @State/@Binding, .task(id:), init-based view model construction) cover the common refactor cases with executable Prefer/Avoid contrast.

5 / 5

Workflow Clarity

The seven-step Workflow is clearly sequenced, but step 7 ("Keep behavior intact") is a constraint rather than an explicit validation checkpoint, and there is no build/test/behavior-verification feedback loop for this code-modifying skill, which caps the score at 3 per the destructive-operation guidance.

3 / 5

Progressive Disclosure

Content is well organized into Core Guidelines, Workflow, Notes, and Large-view handling, with a clearly signaled one-level-deep reference to the real file references/mv-patterns.md; most content is appropriately placed, though a fair amount of inline guidance could arguably be split further.

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 explicitly covers both what the skill does and when to use it with concrete trigger phrases. It is distinctive and domain-specific, with only minor room to add synonyms and tighten the headline action.

DimensionReasoningScore

Specificity

"Refactor SwiftUI view files into stable, testable structure" names the domain and pairs it with concrete actions in the Use-when clause ("splitting large views", "tightening data flow", "cleaning Observation ownership"), but the headline verb is somewhat abstract, leaving minor coverage gaps versus a fully enumerated action list.

4 / 5

Completeness

"Refactor SwiftUI view files into stable, testable structure" explicitly states what it does and "Use when splitting large views, tightening data flow, or cleaning Observation ownership" gives concrete when-triggers, clearly answering both what and when.

5 / 5

Trigger Term Quality

Phrases like "splitting large views", "tightening data flow", "cleaning Observation ownership", and "SwiftUI view files" are natural terms a developer would say, giving good keyword coverage, though common synonyms like MVVM, subviews, or @State are absent.

4 / 5

Distinctiveness Conflict Risk

The SwiftUI-specific niche and distinct triggers ("Observation ownership", "splitting large views") make this unlikely to fire for unrelated skills, with minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.