CtrlK
BlogDocsLog inGet started
Tessl Logo

swiftui-view-refactor

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

54

Quality

61%

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-claude/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 well-structured, executable, and lean, with strong prefer/avoid Swift examples and a real one-level reference. The main gap is the Workflow, which lacks an explicit build/test verification checkpoint for a behavior-preserving refactor.

Suggestions

Add a verification checkpoint to the Workflow, e.g. step 8: 'Build the target and run its tests to confirm the refactor preserves behavior; fix regressions before finishing.'

Signal references/mv-patterns.md earlier — link it from the 'Default to MV, not MVVM' section, not just the closing Notes, so the deeper material is discoverable where it is relevant.

De-duplicate the 'Large-view handling' and 'Notes' sections against Core Guidelines 3 to remove the subview-extraction restatement.

DimensionReasoningScore

Conciseness

The body uses direct imperatives and prefer/avoid code pairs without explaining SwiftUI basics, and every section earns its place. Minor trim opportunities exist (the 'Large-view handling' and 'Notes' sections restate subview-extraction guidance already in Core Guidelines 3). Not a 5 due to that slight redundancy, and not a 3 because there is no real over-explanation of concepts Claude already knows.

4 / 5

Actionability

Concrete, copy-paste-ready Swift examples cover the common cases (HeaderSection/FilterSection extraction, save/reload with .task(id:), @State view-model init, ordering rules). Not a 5 because some examples rely on undefined placeholders (FilterChip, SomeViewModel, Dependency) introducing minor gaps, and not a 3 because the guidance is genuinely executable rather than pseudocode.

4 / 5

Workflow Clarity

The 7-step Workflow is clearly sequenced, but there is no explicit validation/verification checkpoint (e.g. 'build and run tests to confirm behavior is intact'), even though refactoring modifies behavior-sensitive code. This fits the 'steps listed but validation gaps' anchor. Not a 4 because a checkpoint is absent rather than merely minor, and not a 2 because the sequence itself is coherent and well-defined.

3 / 5

Progressive Disclosure

Clear section headers organize the body and the single reference to references/mv-patterns.md is one level deep and resolves to a real file. Not a 5 because the reference is signaled only once near the end in 'Notes' rather than surfaced where MV guidance is discussed, and not a 3 because structure and the reference are clearly present rather than buried.

4 / 5

Total

15

/

20

Passed

Description

53%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 what and a distinct niche, but omits any explicit 'when to use' trigger guidance, capping completeness at 3. Trigger-term coverage has the core domain keywords but misses common synonyms.

Suggestions

Add a 'Use when ...' clause naming concrete triggers, e.g. 'Use when cleaning up a large SwiftUI view, splitting a long body, or reorganizing view properties for clearer data flow.'

Broaden trigger terms with synonyms users actually say — 'split', 'break up', 'subviews', 'long body' — alongside 'SwiftUI views' and 'smaller components'.

Optionally enumerate a few specific actions (extract subviews, reorder properties, set up Observation) to lift specificity from one action to a small list.

DimensionReasoningScore

Specificity

It names the domain ('SwiftUI views') and one concrete action ('Refactor ... into smaller components') plus the goal 'stable, explicit data flow', but does not enumerate the multiple refactor actions the skill covers, so coverage is not comprehensive. Not a 2 because it goes beyond merely naming the domain, and not a 4 because no list of several specific actions is given.

3 / 5

Completeness

The 'what' is clear ('Refactor SwiftUI views into smaller components with stable, explicit data flow'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric. Not a 4 because 'when' is entirely absent rather than present-but-vague.

3 / 5

Trigger Term Quality

Natural terms like 'SwiftUI views' and 'smaller components' are present, but common variations a user might say ('split', 'break up', 'subviews', 'long body') are missing. Not a 4 because keyword coverage is incomplete rather than just a few terms short, and not a 2 because it has relevant domain keywords rather than only generic language.

3 / 5

Distinctiveness Conflict Risk

'Refactor SwiftUI views into smaller components' targets a clear, distinct niche with low overlap risk against unrelated skills. Not a 5 because the absence of an explicit trigger clause leaves minor overlap risk with a general 'SwiftUI' or 'refactor' skill, and not a 3 because it is far more specific than a broad 'works with views' description.

4 / 5

Total

13

/

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

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
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.