CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expo-ui-swift-ui

`@expo/ui/swift-ui` package lets you use SwiftUI Views and modifiers in your app.

58

Quality

73%

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/expo/skills/expo-ui-swift-ui/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-organized, lean instruction sheet with concrete commands, exact import paths, and a built-in verify-against-docs checkpoint, which is highly effective for a code-usage skill. Its main weaknesses are the fully-fragment code example and time-sensitive SDK-version pinning woven into the main guidance rather than isolated in a versioning section.

Suggestions

Make the Host/RNHostView example a complete, copy-paste-ready React component (wrapped in a function returning the JSX) so it is fully executable as written.

Move the SDK 55 scoping and versioned doc URLs into a dedicated 'SDK versions' or 'old patterns' section so the main guidance is version-stable and the version pin does not penalize conciseness.

Add brief error-recovery guidance (e.g., what to check when a SwiftUI tree does not render or the rebuild fails) to turn the implicit checkpoint into an explicit feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — terse bullets, one compact code example, no conceptual padding (e.g., it never explains what SwiftUI is). It falls short of a 5 because it embeds time-sensitive version pinning ("apply to SDK 55 only" plus v55.0.0 URLs) outside any 'old patterns'/'deprecated' section, which the guidelines penalize; it is above a 3 because there is no unnecessary explanation to trim.

4 / 5

Actionability

Concrete, executable guidance dominates: an exact install command ("npx expo install @expo/ui"), precise import paths, doc-fetch URL patterns per component, and the Host/RNHostView example with complete imports. It is not a 5 because the JSX example is a fragment without a component wrapper, so it is not fully copy-paste runnable as-is; it is above a 3 because nothing is pseudocode or high-level hand-waving.

4 / 5

Workflow Clarity

The install → native rebuild → usage sequence is clear, and the "fetch its docs to confirm the API" instruction acts as an explicit checkpoint before using components. It is not a 5 because there is no error-recovery guidance (what to do when a rebuild fails or a View does not render) — the missing-view/modifier fallback only appears at the end as an aside; it is above a 3 because checkpoints are present and no destructive/batch operations apply.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent), and the content is organized into clear sections (Installation, Instructions) with one-level-deep, clearly signaled external doc references. Per the rubric's simple-skill exception, this earns the top anchor with well-organized sections alone.

5 / 5

Total

17

/

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 clearly states what the skill provides but is held back by the complete absence of any 'when to use' trigger guidance and limited keyword coverage. It identifies a distinct niche but would benefit from explicit trigger phrases users would naturally say.

Suggestions

Add an explicit trigger clause, e.g., "Use when building Expo/React Native apps with SwiftUI components, native iOS UI views, or @expo/ui/swift-ui elements."

Expand capability coverage beyond 'use Views and modifiers' to mention the concrete workflows the skill supports (embedding RN components via RNHostView, extending missing views/modifiers), which would raise specificity and trigger-term quality simultaneously.

Include natural synonym terms users might say, such as "iOS native UI", "SwiftUI in Expo", or "Expo UI", to broaden trigger matching without adding vagueness.

DimensionReasoningScore

Specificity

The description names the domain ("@expo/ui/swift-ui package", "SwiftUI Views and modifiers") and one concrete capability ("lets you use SwiftUI Views and modifiers in your app"), which matches the anchor for 1-2 concrete actions without comprehensive coverage. It is not a 4 because it does not list several specific actions (e.g., embedding, extending, installation), and not a 2 because the named capability is concrete rather than generic.

3 / 5

Completeness

The 'what' is clear ("lets you use SwiftUI Views and modifiers in your app") but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent, and not a 2 because the 'what' is concrete rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords are present ("SwiftUI", "Views", "modifiers", "@expo/ui/swift-ui") but common natural variations users would say are missing (e.g., "iOS UI", "native UI components", "Expo UI"). This fits the anchor for some relevant keywords missing synonyms; it is not a 4 because coverage is thin and not a 2 because the terms are domain-relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

The description occupies a clear niche (SwiftUI interop via a specific package) with minor overlap risk against general React Native / iOS UI skills. It is not a 5 because no explicit trigger phrases reinforce the distinction, and not a 3 because the domain pin ("@expo/ui/swift-ui", SwiftUI) is quite specific.

4 / 5

Total

13

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

openai/plugins

Path

plugins/expo/skills/expo-ui-swift-ui/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.