Content
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured instruction-only skill with a clean audit-to-fix-to-verify workflow and an appropriately delegated single reference. The main weaknesses are duplicated Check/Code Review sections and the absence of any inline executable code example in the body.
Suggestions
Merge the near-duplicate 'Check' and 'Code Review' sections to remove redundancy and recover token budget.
Add one minimal inline JSON-LD snippet so the core action is copy-paste ready without forcing a reference hop.
Trim the 'Explain' section's Knowledge Panel definition, which restates a concept Claude already knows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean, but the 'Check' and 'Code Review' sections duplicate the same homepage-JSON-LD verification instructions, and 'Explain' restates the Knowledge Panel concept, so it could be tightened. | 2 / 3 |
Actionability | The Fix section gives specific property lists (name, url, logo ImageObject with width/height, contactPoint, sameAs), but the body carries no inline executable code example, delegating that to the reference, leaving guidance concrete but incomplete. | 2 / 3 |
Workflow Clarity | A clear Check → Fix → Code Review sequence is present with explicit validation checkpoints ('Validate with Google's Rich Results Test', 'Confirm Organization schema is NOT duplicated on interior pages'). | 3 / 3 |
Progressive Disclosure | The SKILL.md is a concise overview that signals a single one-level-deep reference ('see references/rule.md') which exists as a real file, matching the clear-overview-with-well-signaled-reference anchor. | 3 / 3 |
Total | 10 / 12 Passed |