Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is concise and well-structured, with good progressive disclosure that defers detail to a real reference file. Its weaknesses are actionability and workflow clarity: the inline guidance is somewhat abstract and lacks explicit verification checkpoints in the body.
Suggestions
Add a concrete detection snippet or tooling cue inline (e.g., a quick axe-core selector or a browser DevTools accessibility-tree check) so the Check section is executable, not just descriptive.
Include an explicit verification step in the body — a validate→fix→recheck loop referencing axe/Lighthouse or the accessibility tree — rather than deferring all verification to the reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean across short sections (Quick Reference, Check, Fix, Explain, Code Review) and assumes Claude's competence without explaining what ARIA or HTML is, matching the score-3 anchor of lean, efficient content where every token earns its place. | 3 / 3 |
Actionability | The "Check" and "Fix" sections describe what to look for in fairly abstract terms ("Identify elements where an ARIA attribute references an id that appears multiple times") without concrete tooling commands in the body, and executable code is deferred to the reference, matching the score-2 anchor of some concrete guidance but incomplete. | 2 / 3 |
Workflow Clarity | The body presents a clear Check → Fix → Explain → Code Review sequence but contains no explicit validation or verification checkpoints in the body itself (verification lives only in the reference), so per the rubric's cap on missing validation steps it lands at the score-2 anchor of steps listed but validation gaps. | 2 / 3 |
Progressive Disclosure | This simple, under-50-line skill is organized into clear sections and appropriately defers detail to a real, one-level-deep reference ("see `references/rule.md`" — confirmed to exist), matching the score-3 anchor for simple skills with well-organized sections and clearly signaled one-level references. | 3 / 3 |
Total | 10 / 12 Passed |