Refactor and review SwiftUI view files with strong defaults for small dedicated subviews, MV-over-MVVM data flow, stable view trees, explicit dependency injection, and correct Observation usage. Use when cleaning up a SwiftUI view, splitting long bodies, removing inline actions or side effects, reducing computed `some View` helpers, or standardizing `@Observable` and view model initialization patterns.
86
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a narrow, opinionated domain (SwiftUI view refactoring) with specific architectural patterns and concrete trigger scenarios. It uses third-person voice, includes natural developer terminology, and provides an explicit 'Use when...' clause with multiple actionable triggers. The description is concise yet comprehensive, making it easy for Claude to distinguish this skill from general Swift or iOS development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and patterns: refactoring SwiftUI views, splitting long bodies, removing inline actions/side effects, reducing computed `some View` helpers, standardizing `@Observable` and view model initialization patterns, MV-over-MVVM data flow, stable view trees, explicit dependency injection. | 3 / 3 |
Completeness | Clearly answers both 'what' (refactor and review SwiftUI view files with specific architectural defaults) and 'when' (explicit 'Use when...' clause listing five concrete trigger scenarios like cleaning up views, splitting long bodies, removing inline actions, etc.). | 3 / 3 |
Trigger Term Quality | Includes highly natural keywords a SwiftUI developer would use: 'SwiftUI view', 'subviews', 'MVVM', '@Observable', 'view model', 'dependency injection', 'refactor', 'review', 'splitting long bodies', 'side effects', 'some View'. These cover a strong range of terms users would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — narrowly scoped to SwiftUI view refactoring with specific architectural opinions (MV-over-MVVM, stable view trees, Observation usage). Unlikely to conflict with general Swift skills, general code review skills, or other iOS development skills due to the precise domain and opinionated patterns mentioned. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable SwiftUI refactoring skill with excellent concrete code examples and clear 'prefer/avoid' patterns. Its main weaknesses are moderate verbosity from repeated themes across sections and the lack of explicit validation/verification steps in the workflow. The content would benefit from tightening prose, adding verification checkpoints, and potentially splitting detailed examples into a reference file.
Suggestions
Add explicit validation checkpoints to the workflow, such as 'Verify the project compiles after each extraction step' and 'Run previews to confirm visual parity before and after refactoring'.
Consolidate repeated guidance about preferring small subview types—it appears in sections 3, the Notes, and Large-view handling—into a single authoritative statement to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining basic SwiftUI concepts, but some sections are somewhat verbose—e.g., the 'Avoid' examples could be shorter, and a few guidelines repeat similar points across sections (e.g., 'prefer small subview types' appears in multiple places). The code examples earn their place but the prose surrounding them could be tightened. | 2 / 3 |
Actionability | The skill provides fully executable Swift code examples for each guideline, concrete 'Prefer' vs 'Avoid' patterns, and specific rules (e.g., store @Observable as @State, init pattern for view models). The workflow section gives a clear step-by-step refactoring process. Everything is copy-paste ready and directly applicable. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced and covers the refactoring process well. However, there are no explicit validation checkpoints or feedback loops—step 7 says 'keep behavior intact' but doesn't specify how to verify this (e.g., run previews, check for compilation, compare before/after). For a refactoring skill that could introduce regressions, this is a notable gap. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, and there's one reference to an external file (references/mv-patterns.md). However, at ~150+ lines with extensive inline code examples, some content (like the full Prefer/Avoid examples for each guideline) could be split into a reference file. The skill is borderline monolithic for its length. | 2 / 3 |
Total | 9 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
05ba982
Table of Contents
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.