Content
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill uses good progressive disclosure with a verified one-level reference and sectioned content, but the body suffers from redundant Check/Code Review sections, prose-only guidance, and a workflow lacking explicit verification checkpoints. Tightening duplication and adding a sequenced audit-with-verify flow would raise the weaker dimensions.
Suggestions
Remove the near-duplicate 'Code Review' section (it repeats 'Check') and trim the conceptual 'Explain' section to cut redundant tokens.
Add a numbered audit workflow (extract → compare → standardize → update all pages → verify) with an explicit verification checkpoint, since updating every page is a batch operation.
Provide concrete executable tooling (e.g., a site-wide grep/search command or a small script) instead of prose instructions so the Check/Code Review steps are copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean and sectioned, but the 'Code Review' section nearly duplicates 'Check' and the 'Explain' section restates local-SEO concepts Claude already knows, so it could be tightened. | 2 / 3 |
Actionability | Concrete fields and locations to check are specified, but guidance stays in prose with no executable command or script, and 'Report any differences' is vague, leaving it short of copy-paste-ready. | 2 / 3 |
Workflow Clarity | An implied Check→Fix sequence exists, but steps are not numbered and there is no explicit validation checkpoint despite 'Fix' being a batch update across all pages, which caps clarity at 2. | 2 / 3 |
Progressive Disclosure | The body is a concise overview that clearly signals a single one-level-deep reference ('see references/rule.md'), which exists and does not nest further, giving clean navigation. | 3 / 3 |
Total | 9 / 12 Passed |