Content
53%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.
The body is well-organized and token-efficient as a reference index, but it relies entirely on a rules/ bundle that does not exist, breaking actionability, navigation, and the terminal workflow step. The skill cannot actually deliver its referenced detail.
Suggestions
Add the missing rules/ directory with the referenced rule files (e.g., rules/animations.md, rules/timing.md), or remove the dead links.
Include at least one small inline executable snippet or concrete starting pattern so the skill is actionable before any rule file is loaded.
Fix the typo "Use this skills" to "Use this skill" and verify each listed link resolves to a real file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: a short "When to use," a captions pointer, and a one-line-per-entry index of rule files with concise descriptors, with no over-explanation of concepts Claude already knows. | 5 / 5 |
Actionability | The body provides only high-level hints (one-line descriptors per rule) and directs Claude to "Read individual rule files," but contains no executable code or commands itself, and the referenced rule files do not exist, so the guidance cannot be executed. | 2 / 5 |
Workflow Clarity | A simple reference workflow is present and unambiguous (consult the relevant rule file per topic), but the workflow dead-ends because every referenced rules/*.md file is missing, leaving the sequence incomplete at its terminal step. | 3 / 5 |
Progressive Disclosure | The intended structure is a clean one-level-deep index with clearly signaled references, which is ideal, but the rules/ directory and all referenced files are absent, so navigation is effectively non-functional. | 2 / 5 |
Total | 12 / 20 Passed |