CtrlK
BlogDocsLog inGet started
Tessl Logo

swiftui-expert-skill

Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management and `@Observable` data flow, view composition and invalidation/performance, lists and `ForEach` identity, environment usage, localization, animations, Liquid Glass adoption, migrating soft-deprecated APIs, or Instruments `.trace` capture/analysis for hangs, hitches, CPU hotspots, or excessive view updates.

87

1.16x
Quality

92%

Does it follow best practices?

Impact

92%

1.16x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 high-quality, well-structured skill that excels at progressive disclosure and workflow clarity. It provides actionable, concrete guidance with executable commands and a comprehensive correctness checklist. The main weakness is moderate redundancy between the Topic Router table and the References section at the bottom, plus some inline verbosity in the trace recording workflow that could be further delegated to its reference file.

Suggestions

Remove or consolidate the References section at the bottom since it largely duplicates the Topic Router table — or differentiate their purposes more clearly (e.g., Topic Router for task-time lookup, References as a quick-scan index with one-line descriptions only).

DimensionReasoningScore

Conciseness

The skill is generally efficient and avoids explaining basic SwiftUI concepts Claude already knows. However, there is some redundancy: the References section at the bottom duplicates the Topic Router table almost entirely, and the trace recording workflow is quite verbose with inline explanations that could be offloaded to the referenced file.

2 / 3

Actionability

The skill provides concrete, executable commands (e.g., `python3 scripts/record_trace.py` with specific flags), a detailed correctness checklist with hard rules, specific workflow steps for each task type, and clear decision criteria (e.g., simulator → Time Profiler, real device → SwiftUI template). The guidance is specific and copy-paste ready.

3 / 3

Workflow Clarity

Multi-step workflows are clearly sequenced with numbered steps, explicit validation checkpoints (e.g., 'Only when valid', 'Validate #available gating'), feedback loops (e.g., 'If errors: fix and re-validate' in trace analysis step 2's iterative window resolution), and clear trigger conditions for each workflow. The trace recording workflow includes a clean stop mechanism and finalization wait.

3 / 3

Progressive Disclosure

The skill is an excellent overview document that delegates detailed content to 25+ well-organized reference files via a clear Topic Router table. References are one level deep, clearly signaled with consistent paths, and the main document stays focused on workflows and routing rather than inlining all reference material.

3 / 3

Total

11

/

12

Passed

Description

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 communicates both what the skill does and when to use it. It leads with an explicit 'Use when...' clause and enumerates a comprehensive list of specific SwiftUI-related capabilities using natural developer terminology. The only minor note is that it's a single long sentence, but the content is excellent and highly actionable for skill selection.

DimensionReasoningScore

Specificity

Lists many specific concrete actions and domains: state management with @Observable, view composition and invalidation/performance, lists and ForEach identity, environment usage, localization, animations, Liquid Glass adoption, migrating soft-deprecated APIs, and Instruments .trace capture/analysis for hangs, hitches, CPU hotspots, and excessive view updates.

3 / 3

Completeness

Opens with an explicit 'Use when...' clause that clearly answers both what (writing, reviewing, refactoring SwiftUI code with detailed sub-capabilities) and when (when working on SwiftUI code for iOS/macOS involving any of the listed concerns). The trigger guidance is explicit and upfront.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a developer would use: 'SwiftUI', 'iOS', 'macOS', '@Observable', 'ForEach', 'state management', 'animations', 'Liquid Glass', 'Instruments', '.trace', 'hangs', 'hitches', 'CPU hotspots', 'localization'. These are highly specific and natural keywords developers would mention.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: SwiftUI-specific development including very specific topics like Liquid Glass adoption, @Observable data flow, and Instruments .trace analysis. Unlikely to conflict with generic coding skills or even other Apple platform skills due to the SwiftUI-specific focus and detailed sub-domains.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
avdlee/swiftui-agent-skill
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.