Content
71%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 a well-structured, lean overview that appropriately defers implementation detail to a one-level reference, but it keeps executable code and concrete verification steps out of the SKILL.md itself, leaving the in-body actionability incomplete.
Suggestions
Inline a minimal copy-paste JSON-LD Person/Organization snippet so the body is actionable without opening the reference.
Make the 'Check' step concrete by specifying what to inspect (e.g. 'Confirm a script[type=application/ld+json] with @type Person is present and linked via the Article author property').
Add an explicit validate-then-retry checkpoint (e.g. 'Re-fetch the rendered URL and confirm the JSON-LD parses') for the verification workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Sections are lean and mostly assume Claude's knowledge; only the one-line 'why it matters' intro is mild over-explanation that could be trimmed. | 4 / 5 |
Actionability | Lists concrete properties and types (Person/Organization, name, url, sameAs, jobTitle) and a clear fix instruction, but the body itself contains no executable code block (the JSON-LD example lives in references/rule.md) and the 'Check' verb ('verify that the page includes…') is somewhat vague. | 3 / 5 |
Workflow Clarity | A clear Check → Fix → Explain → Code Review sequence is implied by the section structure with verification woven through 'Check' and 'Code Review', though explicit validation checkpoints are delegated to the reference rather than stated inline. | 4 / 5 |
Progressive Disclosure | The body is a concise overview with clear sections and a single, well-signaled one-level-deep reference to references/rule.md (verified to exist) that holds the code example and detailed verification steps. | 5 / 5 |
Total | 16 / 20 Passed |