Content
78%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 reference skill: the body stays a lean overview of principles, selection tables, and checklists, while detail is correctly pushed to 12 real, one-level-deep reference files. Main improvement opportunities are removing the boilerplate 'When to Use' section and adding one worked example of the specified output format.
Suggestions
Delete or replace the generic 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview') with a concrete condition, or remove it entirely — it adds tokens without information.
Add one short worked example under Output Format (e.g., a sample recommendation for a 4-section iPad/iPhone app showing the pattern, hierarchy, and size-class behavior) to close the actionability gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient: terse principle statements ('Sidebars for top-level sections, lists for browsable items, detail views for individual content'), dense selection tables, and checklists assume Claude's platform knowledge rather than explaining basics. Minor trimming targets remain — the trailing 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview') is content-free boilerplate, and the attribution footer adds tokens without guidance value. Not score 5 because of that filler; not score 3 because nothing is noticeably verbose or over-explained. | 4 / 5 |
Actionability | For an instruction-only skill the guidance is concrete: the pattern-selection table maps app structures to named components with per-platform adaptation ('iPhone: bottom tab bar. iPad: sidebar (`.sidebarAdaptable`, iPadOS 18+). Mac: sidebar or toolbar tabs'), and specific APIs are named (NavigationSplitView, UISplitViewController, TabView). Not score 5 because there are no worked examples (e.g., a sample output or a concrete layout hierarchy walkthrough); not score 3 because the table plus checklist give specific, followable direction rather than vague hints. | 4 / 5 |
Workflow Clarity | A clear implicit sequence exists: check the design-context file → ask the listed questions → select a pattern via the table → verify against the Layout Adaptation Checklist → produce output in the specified four-part format. The checklist functions as a validation checkpoint. Not score 5 because the sequence is distributed across sections rather than presented as an explicit ordered workflow, and there are no feedback/recovery steps; not score 3 because checkpoints (the checklist) are present and the process is easy to follow. This is a non-destructive advisory skill, so the validation cap does not apply. | 4 / 5 |
Progressive Disclosure | The body is a genuine overview with a Reference Index table pointing to all 12 reference files, each labeled with topic and key content ('Source lists, selection state, collapsible sections, iPad/Mac patterns'). All 12 referenced files exist in ./references/, are flat (one level deep), and contain no nested .md references — verified against the actual bundle. This matches the 'clear overview with well-signaled one-level-deep references' anchor exactly. | 5 / 5 |
Total | 17 / 20 Passed |