CtrlK
BlogDocsLog inGet started
Tessl Logo

macos-view-refactor

Refactor macOS SwiftUI views and scenes into stable structure. Use when splitting large views, tightening scene state, or narrowing AppKit escapes.

66

Quality

79%

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 ./.agents/skills/macos-view-refactor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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, lean instructional body that assumes Claude's competence and gives unusually concrete file-layout and attribute-level rules. The main gaps are the absence of any illustrative before/after example and validation appearing as a checklist item rather than an explicit step in the workflow with a fix-retry loop.

Suggestions

Add one short before/after SwiftUI snippet under guideline 3 or 4 to make "stabilize the root layout" and "extract subviews" concrete rather than judgment-based.

Move "Build after each major split" into the numbered Workflow as an explicit step with a feedback loop (e.g., "If the build fails, fix locally before the next split") so checkpoints live inside the sequence, not only in the checklist.

Consider moving the directory-layout rules of guideline 2b into a small references/ file (e.g., FILE-LAYOUT.md) and keeping a one-line summary in the body, tightening SKILL.md further.

DimensionReasoningScore

Conciseness

The body is directive and dense — bullet-style rules with no padding, no explanation of what SwiftUI or AppKit is, and no restating of Claude's existing knowledge. Minor trimming is possible (the Overview repeats the description, and "Common Smells" partially restates the Core Guidelines), which keeps it at 4 rather than the fully lean 5.

4 / 5

Actionability

As an instruction-only skill it gives concrete, executable guidance: an exact member ordering for files, explicit directory targets ("Views/ContentView.swift", "Models/*.swift", "Stores/*.swift", "Services/*.swift", "Support/*.swift"), and specific attribute rules (@SceneStorage vs @AppStorage, @Observable stored as @State). It stays at 4 because there are no before/after snippets illustrating a split, so a few guidelines (e.g., "stabilize the root layout") rely on judgment rather than a shown pattern.

4 / 5

Workflow Clarity

The Workflow section gives a clear 7-step sequence, and the checklist includes the checkpoint "Build after each major split so compile errors stay local", plus step 7 guards behavior preservation. It misses a 5 because the build checkpoint lives in the checklist rather than the workflow sequence, and there is no explicit error-recovery loop (build fails → fix locally before proceeding).

4 / 5

Progressive Disclosure

The single-file body (no references/, scripts/, or assets/ exist) is well organized into Overview, numbered Core Guidelines, Workflow, Checklist, Smells, and Notes, with pointers to sibling skills ("use macos-swiftui-patterns", "use macos-appkit-interop") for adjacent problems. It fits the 4 anchor — good structure with everything appropriately placed in one file — but at ~105 lines some guideline detail (e.g., the file-layout rules in 2b) could be offloaded to a reference file to reach the clearest overview-plus-references shape.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong, tight description in third person that explicitly states both capability and trigger conditions with concrete macOS-specific phrasing. Its only weaknesses are mild: a slightly abstract "stable structure" claim and a few missing natural-language synonyms that would push trigger coverage and specificity to the top anchor.

DimensionReasoningScore

Specificity

The description names the domain ("macOS SwiftUI views and scenes") and lists several concrete actions — "Refactor... into stable structure", "splitting large views", "tightening scene state", "narrowing AppKit escapes". It falls short of a 5 because "stable structure" is somewhat abstract and the action list, while specific, is not comprehensive of everything the skill body covers (file organization, selection stability, command extraction).

4 / 5

Completeness

Both halves are explicit: the "what" is "Refactor macOS SwiftUI views and scenes into stable structure" and the "when" is a concrete "Use when splitting large views, tightening scene state, or narrowing AppKit escapes" clause with specific trigger phrases. This matches the anchor for clearly and explicitly answering both what and when.

5 / 5

Trigger Term Quality

Good keyword coverage with natural user phrases like "splitting large views" and "AppKit", plus technical terms SwiftUI, scenes, and macOS. A few natural variations users might say are missing (e.g., "view too big", "break up a view", "refactor a SwiftUI file"), keeping it below the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche (macOS desktop SwiftUI refactoring, scenes, AppKit boundaries) with distinct triggers, minimizing conflict with generic skills. Minor overlap risk remains with closely related sibling skills the body itself names ("macos-swiftui-patterns", "macos-appkit-interop"), which a user might plausibly mean with the same request.

4 / 5

Total

17

/

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
robinebers/openusage
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.