CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swiftui-view-refactor

Refactor SwiftUI views into smaller components with stable, explicit data flow.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/swiftui-view-refactor/SKILL.md

The canonical home for this skill is swiftui-view-refactor in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

68%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 body is a tight, highly actionable rulebook: concrete code patterns, explicit ordering conventions, and quantitative thresholds, with supporting rationale properly moved to a one-level-deep reference file. The main weaknesses are the absence of a validation/verification step in the workflow (no build-or-test checkpoint for a behavior-preserving refactor) and minor redundancy between the guidelines, workflow, and notes sections.

Suggestions

Add an explicit verification step to the workflow, e.g. '8. Verify: build the project and run existing tests to confirm behavior and layout are unchanged.'

Trim the 'Notes' section, which restates guidelines already covered, and drop the duplicated header snippet from the 'Avoid' example in section 3.

Promote the 'references/mv-patterns.md' pointer into its own clearly labeled section with a markdown link describing what the reader will find there.

DimensionReasoningScore

Conciseness

Prescriptive bullets and Prefer/Avoid code pairs with no padding about concepts Claude already knows — every section is actionable guidance. Minor trims are possible (the 'Avoid' example in section 3 repeats the header VStack snippet from the 'Prefer' example, and 'Notes' largely restates earlier guidelines), which keeps it below anchor 5.

4 / 5

Actionability

Concrete, syntactically valid Swift throughout: the '_viewModel = State(initialValue: SomeViewModel(dependency:))' init pattern, the '.task(id: searchText)' reload example, an explicit property-ordering list, and hard thresholds ('~300 lines', 'iOS 17+'). Minor gaps — helpers like 'FilterChip' and 'documentsListContent' are referenced but not defined, so examples are not fully copy-paste ready.

4 / 5

Workflow Clarity

The 7-step Workflow is clearly sequenced but has no validation checkpoint: there is no 'build/test to confirm behavior is unchanged' step, and step 7 ('Keep behavior intact') is a constraint rather than a check. Sequence present, checkpoints missing matches anchor 3; not 4 because the only checkpoint is implicit.

3 / 5

Progressive Disclosure

Well-sectioned body with rationale correctly offloaded to 'references/mv-patterns.md', which exists in the bundle and is one level deep. The reference is a single bare path on the last line of 'Notes' rather than a clearly signaled dedicated section — a minor organization gap that keeps it below anchor 5.

4 / 5

Total

15

/

20

Passed

Description

61%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 states a clear, appropriately niche capability in third person with natural trigger keywords, but it omits any 'Use when...' trigger guidance, which caps completeness at 3 and weakens discoverability. A when-clause naming the concrete triggers (large views, long body implementations, splitting into subviews) would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when cleaning up a large SwiftUI view, splitting a long body implementation, or when asked to break a view into smaller subviews.'

Broaden trigger-term coverage with natural synonyms users say: 'split', 'break up', 'extract subviews', 'view is too big/long'.

Mention 1-2 more concrete capabilities the skill actually delivers (e.g., explicit dependency injection via environment, Observation/iOS 17 migration) to lift specificity beyond two actions.

DimensionReasoningScore

Specificity

Names the domain and 1-2 concrete actions ('Refactor SwiftUI views into smaller components', 'stable, explicit data flow') but coverage is not comprehensive — no mention of dependency injection, view model handling, or Observation usage that the body actually covers. Not 4 because it lists only a couple of actions rather than several specific ones.

3 / 5

Completeness

Has a clear 'what' ('Refactor SwiftUI views into smaller components with stable, explicit data flow') but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guideline. Not 4 because 'when' is entirely absent, not merely imprecise.

3 / 5

Trigger Term Quality

Contains natural phrases users would say: 'SwiftUI views', 'refactor', 'components', 'data flow' ('refactor this SwiftUI view' is a natural request). A few natural variations are missing ('split', 'break up', 'extract subviews'), matching anchor 4 rather than 3 because it goes beyond bare domain-naming.

4 / 5

Distinctiveness Conflict Risk

'SwiftUI views' pins a clear niche with minimal conflict risk — it would rarely trigger for non-SwiftUI skills. Minor overlap remains with a general Swift refactoring or SwiftUI performance skill, so anchor 4 fits better than 5.

4 / 5

Total

14

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/swiftui-view-refactor/SKILL.md

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.