swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
Install with Tessl CLI
npx tessl i github:avdlee/swiftui-agent-skill --skill swiftui-expert-skill94
Does it follow best practices?
Validation for skill structure
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 a strong skill description that clearly articulates specific capabilities (writing, reviewing, improving SwiftUI code), covers relevant technical domains, and provides explicit trigger conditions. The inclusion of cutting-edge features like 'iOS 26+ Liquid Glass adoption' adds distinctiveness while the 'Use when...' clause provides clear guidance for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions ('Write, review, or improve SwiftUI code') and specific technical domains ('state management, view composition, performance, macOS-specific APIs, iOS 26+ Liquid Glass adoption'). | 3 / 3 |
Completeness | Clearly answers both what ('Write, review, or improve SwiftUI code following best practices...') and when ('Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'SwiftUI', 'views', 'refactoring', 'code quality', 'macOS', 'iOS 26', 'Liquid Glass', 'state management'. Good coverage of both general and specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to SwiftUI with distinct triggers like 'Liquid Glass', 'iOS 26+', 'macOS-specific APIs'. Unlikely to conflict with generic coding skills or other platform-specific skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable SwiftUI skill with excellent progressive disclosure through its reference file system. The main weakness is moderate redundancy between the Core Guidelines, Workflow sections, and Review Checklist, which inflates token usage without adding proportional value. The concrete code examples and decision tables make this immediately useful for Claude.
Suggestions
Consolidate the Review Checklist into the Core Guidelines or reference files to eliminate redundancy—the checklist largely repeats information already stated elsewhere
Consider removing the Philosophy section as it explains intent rather than providing actionable guidance Claude needs
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy—the Review Checklist largely duplicates the Core Guidelines and Workflow sections. The Quick Reference table is efficient, but overall the document could be tightened by consolidating repeated information. | 2 / 3 |
Actionability | Provides concrete, executable code examples (Liquid Glass patterns with fallbacks), specific property wrapper selection tables, and clear decision criteria. The guidance is copy-paste ready and immediately applicable. | 3 / 3 |
Workflow Clarity | The Workflow Decision Tree clearly sequences three distinct workflows (review, improve, implement) with explicit steps and cross-references to detailed documentation. Each workflow has clear entry points and validation checkpoints via the Review Checklist. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, quick reference tables for immediate use, and well-signaled one-level-deep references to 15+ specialized reference files. Navigation is intuitive with inline links throughout. | 3 / 3 |
Total | 11 / 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.
- 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.