Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A solid, actionable reference with concrete code, exact limits, and a checklist, weakened by verbosity and a lack of validation feedback loops in its workflow. Progressive disclosure is held back by inline detail that a longer skill like this would normally split into reference files.
Suggestions
Trim Claude-already-knows content (the full App Clip surface enumeration, trade-off table, ASO-implication prose) and editorial filler to tighten the body toward the token-efficient score-3 anchor.
Add explicit validation/verification checkpoints to the checklist, e.g. a 'verify size < 15MB in the Xcode size report before proceeding' step with a fix-and-recheck loop, to lift workflow_clarity above 2.
Move the detailed App Clip experience and card-design spec tables into a separate reference file (e.g. references/card-design.md) and link to it from a concise overview, improving progressive_disclosure toward a one-level-deep structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~155-line body is mostly factual spec rather than padded prose, but it retains content Claude largely already knows (an exhaustive enumeration of App Clip surfaces, trade-off tables, ASO-implication prose) and editorial filler ('This forces you to ship only the essential experience'), matching the score-2 anchor of being mostly efficient but could be tightened. It is not a 3 because not every token earns its place, and not a 1 because it avoids tutorial-style concept explanation. | 2 / 3 |
Actionability | It provides executable Swift code (SKOverlay.AppClipConfiguration), a concrete URL scheme, exact character/pixel limits (18 chars, 13 chars, 3000x2000px), named App Store Connect paths, and a copy-ready checklist, matching the score-3 anchor of fully executable, copy-paste-ready guidance. It is not a 2 because the code and specs are concrete and complete, not pseudocode. | 3 / 3 |
Workflow Clarity | The implementation checklist sequences Setup → UX → App Store Connect, but it is a flat checkbox list with no validation/verification checkpoints or fix-retry feedback loops for the risky 15MB size constraint, matching the score-2 anchor of steps present but checkpoints missing. Per the rubric, missing validation in such workflows caps the score at 2, so it cannot reach 3. | 2 / 3 |
Progressive Disclosure | The single ~155-line SKILL.md is well-organized into headed sections with a Related Skills pointer, but there are no bundle files and detailed reference material (experience tables, card-design specs) is inlined rather than split out, matching the score-2 anchor of content that should be separate being inline. It is not a 3 because the simple-skill carve-out applies to under-50-line skills and this body is larger with no one-level-deep references. | 2 / 3 |
Total | 9 / 12 Passed |