CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

85%

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

82%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 tight, well-structured refactor skill with concrete layout and ordering rules plus a validation checkpoint. Could push higher with a small worked Swift example and the build-verify loop repeated per step.

Suggestions

Add one short before/after Swift snippet illustrating a computed view fragment extracted into a dedicated subview, to lift actionability toward fully copy-paste-ready.

Repeat the 'build after each major split' validation cue at the relevant workflow steps rather than only in the checklist, to make the feedback loop explicit per phase.

Consider a one-level reference file for extended directory-layout examples so the SKILL.md stays a lean overview while still pointing to concrete patterns.

DimensionReasoningScore

Conciseness

Lean, bullet-driven body that assumes Claude's SwiftUI/AppKit competence and never pads with concepts Claude already knows; every guideline earns its place.

5 / 5

Actionability

Highly specific actionable guidance (property ordering, directory layout like App/<AppName>App.swift, Views/SidebarView.swift, Services/), but no executable Swift snippets; justified for an instruction-only refactor skill yet stops just short of fully copy-paste-ready examples.

4 / 5

Workflow Clarity

Seven clearly sequenced steps with an explicit validation checkpoint ('Build after each major split so compile errors stay local') and a behavior-preservation guard, but the build-verify loop is stated once rather than woven through each step.

4 / 5

Progressive Disclosure

Well-organized self-contained sections with no nested references and clear sibling-skill handoffs in Notes; no bundle files exist so references are unnecessary, but it could optionally point to concrete before/after examples.

4 / 5

Total

17

/

20

Passed

Description

87%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, specific description that clearly states both capability and explicit 'Use when' triggers with concrete synonyms. Minor room to sharpen the action verbs from abstract to fully concrete operations.

DimensionReasoningScore

Specificity

Lists several specific actions ('splitting oversized scene roots', 'removing iOS-centric patterns', 'tightening mixed SwiftUI/AppKit architecture') but the verbs ('refactor', 'tightening') stay somewhat abstract rather than fully concrete operations, so it sits just below comprehensive.

4 / 5

Completeness

Explicitly answers both what ('Refactor macOS SwiftUI views and scenes with strong defaults...') 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.

5 / 5

Trigger Term Quality

Good natural-term coverage with synonyms a user would say ('cleaning up a macOS view file', 'splitting oversized scene roots', 'iOS-centric patterns'), though a few common phrasings are missing.

4 / 5

Distinctiveness Conflict Risk

Clear macOS SwiftUI/AppKit refactor niche with distinct triggers and minimal overlap risk; the body's Notes even hand off adjacent problems to sibling skills, reinforcing distinctiveness.

5 / 5

Total

18

/

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.

Validation16 / 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.