Content
72%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, lean refactor guide with concrete directory and API guidance and clean sectioning. Its main gap is the absence of an explicit validate/retry feedback loop in the workflow for a batch refactor operation.
Suggestions
Add an explicit validate->fix->retry checkpoint in the Workflow, e.g. 'Build after each split; if errors occur, fix locally and rebuild before proceeding to the next split.'
Show one minimal before/after code snippet illustrating a section extraction into a dedicated subview, to make the 'Prefer dedicated subview types' guideline copy-paste concrete.
Tighten overlap between Core Guidelines, Refactor Checklist, and Common Smells by cross-referencing instead of restating items.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and free of basic-concept padding; assumes Claude knows SwiftUI/AppKit and every section earns its place, with only minor restatement between the Core Guidelines, Checklist, and Smells. | 4 / 5 |
Actionability | Provides concrete file-shape ordering, an explicit directory layout (App/, Views/, Models/, Stores/, Services/, Support/), and specific API guidance (@SceneStorage vs @AppStorage, @Observable as @State); no literal code but the guidance is specific and executable for an instruction skill. | 4 / 5 |
Workflow Clarity | A clear 7-step numbered Workflow with a 'Build after each major split' checkpoint exists, but there is no explicit validate->fix->retry feedback loop for what is effectively a batch/destructive refactor, which caps the score. | 3 / 5 |
Progressive Disclosure | No bundle files are needed; the body is well-organized into clear sections and appropriately defers to two sibling skills for adjacent problems rather than inlining them, satisfying the simple-skill exception. | 5 / 5 |
Total | 16 / 20 Passed |