CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

swiftui

API reference: SwiftUI. Query for views, layouts, navigation, @State/@Binding/@Observable, view modifiers, NavigationStack, iOS 26+ features.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/swiftui/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 reference skill with concrete, executable lookup commands and an exemplary one-level-deep file index. Its main weaknesses are a duplicated workflow section and an inline path table that inflate token cost, plus a broken example referencing a non-listed text.md file.

Suggestions

Merge "Usage Instructions" into "Fetching More Docs" — they repeat the same three-step workflow almost verbatim, wasting tokens.

Fix the example that greps text.md, a file not listed in the downloaded-files table; either add text.md to the table or change the example to use a listed file (e.g. list.md or view-protocol.md).

Trim or move the "Common SwiftUI Doc Paths" table into swiftui-overview.md (already described as the full framework index), keeping only the URL-mapping rule and a few examples inline.

DimensionReasoningScore

Conciseness

The body is mostly lean (file table, grep examples, URL mapping), but the "Usage Instructions" section restates the "Fetching More Docs" workflow almost verbatim, and the 22-row "Common SwiftUI Doc Paths" table duplicates the role the 907KB overview file already fills as the full framework index. This matches anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened"), not 4 — the whole-section duplication is more than a minor instance.

3 / 5

Actionability

Guidance is mostly executable: concrete grep commands ("grep -i \"padding\" view-protocol.md") and an explicit URL mapping ("/documentation/swiftui/button maps to https://sosumi.ai/documentation/swiftui/button"). Minor gap: the example "grep -i \"font\" text.md" references a text.md that is not in the downloaded-files table, so that command would fail — anchor 4, not 5.

4 / 5

Workflow Clarity

"Fetching More Docs" gives a clear, correctly-ordered 1-2-3 sequence (local grep → other installed skills → sosumi.ai fetch), which is unambiguous for this non-destructive lookup skill. It sits at anchor 4 rather than 5 because the same workflow is presented twice ("Usage Instructions" repeats it), slightly blurring the canonical sequence.

4 / 5

Progressive Disclosure

Textbook one-level-deep structure: SKILL.md acts as an index with a table describing all 12 reference files plus a fallback fetch path. Minor organization gaps keep it at anchor 4 rather than 5: the inline 22-row path table overlaps the overview file's index function, and text.md is referenced in the example workflow but is absent from the file table.

4 / 5

Total

15

/

20

Passed

Description

66%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 is specific and uses natural, distinctive SwiftUI terminology, but it completely lacks a "Use when..." trigger clause, capping completeness at 3. Adding explicit usage triggers (e.g. "Use when writing or debugging SwiftUI code...") would make it a strong description.

Suggestions

Add an explicit trigger clause, e.g. "Use when writing, debugging, or answering questions about SwiftUI code, views, or property wrappers."

Replace the vague "iOS 26+ features" with the concrete feature names users would actually mention (e.g. Liquid Glass, new controls).

Include a few common synonyms/variations such as "Swift UI", "iOS UI", or "SwiftUI views" to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Query for views, layouts, navigation, @State/@Binding/@Observable, view modifiers, NavigationStack" lists several concrete query targets, matching anchor 4. It is not 3 (more than 1-2 actions named) nor 5 (coverage has gaps, e.g. "iOS 26+ features" is vague and common topics like lists, forms, and animation are absent).

4 / 5

Completeness

The "what" is clear (an API reference for SwiftUI with listed query topics), but there is no "Use when..." clause or equivalent explicit trigger guidance — "Query for" only weakly implies when, which caps this dimension at 3 per the rubric guideline. It is not 2 because the "what" is specific, and not 4 because no explicit "when" exists at all.

3 / 5

Trigger Term Quality

Terms like "views", "navigation", "@State/@Binding/@Observable", "view modifiers", and "NavigationStack" are exactly what a SwiftUI developer would say, giving good keyword coverage. It falls short of anchor 5 because natural variations and synonyms (e.g. "Swift UI", "iOS UI", gestures, animation) are missing.

4 / 5

Distinctiveness Conflict Risk

SwiftUI-specific symbols (@State, @Binding, NavigationStack) establish a clear niche with distinct triggers, but the generic "API reference:" framing risks minor overlap with sibling Apple-documentation skills. This fits anchor 4 ("mostly distinct; minor overlap risk with closely related skills"), not 5.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 12 missing

Warning

Total

14

/

16

Passed

Repository

Prisma-Labs-Dev/apple-skills

Path

skills/swiftui/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.