Content
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is well-structured with good progressive disclosure, but loses points for overlapping Check/Code Review sections, an Explain section that re-teaches known concepts, no executable code block in the body, and a missing validate→fix→retry feedback loop.
Suggestions
Remove or trim the 'Explain' section and the redundant 'Code Review' section (it largely restates 'Check'); consolidate the single validation procedure once to improve conciseness.
Add a small executable JSON-LD validation snippet (e.g., a JSON.parse try/catch over script contents) directly in the body so guidance is copy-paste ready, keeping full examples in references/rule.md.
Make the workflow an explicit feedback loop: parse/validate → if errors, fix syntax or required properties → re-validate via Rich Results Test → only proceed when clean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with clear sections, but the 'Explain' section re-explains concepts Claude already knows ('Google uses JSON-LD structured data to generate rich results...') and the 'Check' and 'Code Review' sections substantially overlap, which could be tightened — matching the score-2 'mostly efficient but includes some unnecessary explanation' anchor. | 2 / 3 |
Actionability | Concrete guidance is present (JSON.parse(), the exact "https://schema.org" string, per-type required-property lists, named validation URLs), but the body itself contains no copy-paste executable code block and the Check/Code Review steps are procedural prose rather than runnable snippets, matching score-2 'some concrete guidance but incomplete'. | 2 / 3 |
Workflow Clarity | A clear numbered sequence exists (parse → verify @context → verify @type → required props → validate) with named validation endpoints, but there is no explicit validate→fix→retry feedback loop checkpoint, keeping it at the score-2 'sequence present but checkpoints missing/implicit' anchor rather than score 3. | 2 / 3 |
Progressive Disclosure | The body is well-organized into clear sections and points to a single, clearly-signaled one-level-deep reference (references/rule.md) that exists and contains no nested references, matching the score-3 'clear overview with well-signaled one-level-deep references' anchor. | 3 / 3 |
Total | 9 / 12 Passed |