Content
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-structured with clean progressive disclosure and a clear review workflow, but the body leans on generic templated phrasing and pushes all executable examples into the reference file.
Suggestions
Inline one minimal good/bad button markup snippet in the Fix section so the body is self-contained for the common case.
Remove the repeated title-echo phrasing in the Explain and Code Review sections to tighten token use.
Collapse the generic "Explain" meta-instruction into the Fix section since it largely restates the rationale already implied by the rule.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean checklist-style content, but it repeats the templated title phrase ("affect Provide accessible names for buttons") and includes generic meta-sections ("Explain", "Code Review") that could be tightened; not below 2 since it avoids explaining basics Claude already knows. | 2 / 3 |
Actionability | Gives concrete, actionable guidance ("Use inner text, aria-label, or aria-labelledby", "replace the button with a link"), but executable examples and copy-paste markup are offloaded to references/rule.md rather than present in the body, leaving key details one step away. | 2 / 3 |
Workflow Clarity | As a simple single-purpose review skill it has an unambiguous Check → Fix → Explain → Code Review sequence, and the Code Review section explicitly names a verification step ("verify the fix with browser accessibility tooling or assistive tech"). | 3 / 3 |
Progressive Disclosure | The body is a concise overview with a clearly signaled one-level-deep pointer ("see references/rule.md"), and that reference file exists and is well-organized into Code Example, Best Practices, Tools & Validation, and Verification sections. | 3 / 3 |
Total | 10 / 12 Passed |