CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

view-refactor

Refactor macOS SwiftUI views and scenes with strong defaults for small dedicated subviews, stable sidebar and selection structure, explicit command and toolbar ownership, scene-aware state, and narrow AppKit escape hatches. Use when cleaning up a macOS view file, splitting oversized scene roots, removing iOS-centric patterns, or tightening mixed SwiftUI/AppKit architecture.

69

Quality

87%

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

The canonical home for this skill is view-refactor in openai/plugins

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.

The body is a well-organized, instruction-only skill: concrete directory conventions, named API annotations, a sequenced workflow, and a build-validated checklist, all reasonably concise. It falls short of top marks mainly on missing explicit error-recovery loops in the workflow, no worked before/after example, and no reference files for detail that is currently inlined.

Suggestions

Add an explicit feedback loop to the workflow (e.g., 'After each split, build; if it fails, fix in the newly created file before moving on') to raise workflow clarity.

Include a short before/after refactor example (a monolithic root view and its extracted subviews/files) to make the guidance copy-paste concrete.

Consider moving the file-splitting conventions (section 2b directory layout and the checklist) into a reference file to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is lean and imperative — bullets like 'Break the app into meaningful scene roots' and a concrete file-ordering list add real guidance without explaining SwiftUI basics Claude already knows. A few bullets restate principles Claude could infer ('Keep files small and named after the primary type they contain') and some sections overlap (checklist vs. workflow), which keeps it just below the every-token-earns-its-place level of 5.

4 / 5

Actionability

As an instruction-only skill, it gives concrete, specific guidance: exact directory conventions ('App/<AppName>App.swift', 'Views/SidebarView.swift', 'Models/*.swift', 'Services/*.swift'), named property wrappers (@SceneStorage, @AppStorage, @StateObject), and a clear file-shape ordering. It stops short of fully copy-paste-ready material (e.g., a before/after refactor example), so it sits at 4 rather than 5.

4 / 5

Workflow Clarity

The Workflow section gives a clear 7-step sequence, and the checklist includes a validation checkpoint ('Build after each major split so compile errors stay local'). What is missing is an explicit feedback loop — what to do when the build fails and when to re-verify — which keeps it at 4 rather than the explicit validate-fix-retry pattern of 5.

4 / 5

Progressive Disclosure

With no bundle files, the single SKILL.md is well-organized into Overview, Guidelines, Workflow, Checklist, Smells, and Notes, with one-level pointers to related skills ('use swiftui-patterns', 'use appkit-interop') rather than nested references. At ~105 lines with several distinct guideline areas, some detail (e.g., file-splitting conventions or a worked example) could live in reference files, so structure is good but not fully split — a 4.

4 / 5

Total

16

/

20

Passed

Description

92%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 description: it pairs a comprehensive, concrete statement of what the skill does with an explicit 'Use when' clause full of natural trigger phrases, and it is tightly scoped to macOS SwiftUI/AppKit refactoring. The only gap is minor — a few common synonyms (e.g., 'Swift file', '.swift') are absent from the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'small dedicated subviews', 'stable sidebar and selection structure', 'explicit command and toolbar ownership', 'scene-aware state', 'narrow AppKit escape hatches' — comprehensively covering the macOS view-refactoring domain. It clearly matches the 5 anchor (multiple specific concrete actions, comprehensive) rather than 4, which implies minor coverage gaps that are not evident here.

5 / 5

Completeness

It explicitly answers 'what' (the first sentence enumerating the refactoring behaviors) and 'when' ('Use when cleaning up a macOS view file, splitting oversized scene roots, removing iOS-centric patterns, or tightening mixed SwiftUI/AppKit architecture') with concrete trigger phrases, matching the 5 anchor closely.

5 / 5

Trigger Term Quality

The 'Use when' clause offers natural phrases users would say — 'cleaning up a macOS view file', 'splitting oversized scene roots', 'removing iOS-centric patterns', 'tightening mixed SwiftUI/AppKit architecture' — plus domain terms SwiftUI/AppKit/macOS. A few natural variations are missing (e.g., 'Swift file', '.swift', 'refactor my view'), so it sits at 4 rather than the comprehensive synonym/extension coverage of 5.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (macOS SwiftUI/AppKit view refactoring) with distinct triggers; phrases like 'removing iOS-centric patterns' and 'narrow AppKit escape hatches' further distinguish it from generic SwiftUI or iOS skills, giving minimal conflict risk.

5 / 5

Total

19

/

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

Path

.agents/skills/view-refactor/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.