Content
72%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 well-structured, concise, and points cleanly to a real reference file for depth. Its main weakness is the batch audit workflow lacking an explicit validation gate before fixes are applied.
Suggestions
Add an explicit validation checkpoint between Check and Fix, e.g. confirm flagged orphan pages are not intentionally noindex/non-indexable before adding links.
Tighten the opening paragraph to avoid restating what internal links/PageRank are, since Claude already knows this.
Surface one concrete crawl/query snippet (e.g. a grep or log query for inlink counts) in the main body so the core action is executable without opening the reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean bullets and short imperatives that assume Claude's competence, with only minor over-explanation (e.g. the opening 'Internal links are how search engines discover pages...' restates a known concept) that could be trimmed. | 4 / 5 |
Actionability | It gives concrete thresholds ('3–5 internal links', 'inlinks ≤ 1', '5+ good') and a specific check procedure, with executable HTML examples in the reference; minor gaps remain in the main body's Check/Fix steps. | 4 / 5 |
Workflow Clarity | Check → Fix → Explain → Code Review is a clear sequence, but this is a batch/audit operation that proposes link changes with no explicit validation checkpoint before applying fixes, capping workflow clarity at 3 per the destructive/batch guideline. | 3 / 5 |
Progressive Disclosure | The body is a concise overview with well-organized section headers and a single clearly signaled one-level reference to references/rule.md (a real file), matching the anchor for clear overview with one-level-deep navigation. | 5 / 5 |
Total | 16 / 20 Passed |