Content
68%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, executable, and appropriately concise, with a real bundled script and clear CLI reference. Its main weakness is the absence of explicit validation/error-handling guidance for a batch scraping operation.
Suggestions
Add an explicit verification checkpoint to the workflow (e.g., check the Apify run status, confirm returned ad count matches --max-ads, and surface actor errors before reporting results).
Document error/timeout handling behavior (what happens on Apify run failure, company-name resolution failure) so Claude knows how to recover rather than retry blindly.
Collapse the JSON output example and the output-fields table into one section to reduce redundancy and tighten token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and well-sectioned without explaining concepts Claude already knows, though the JSON example plus a full output-fields table is mildly redundant and could be trimmed. | 4 / 5 |
Actionability | Provides copy-paste-ready CLI commands, a complete flag reference table, and a concrete output schema; only minor gaps (e.g., token provisioning detail) keep it from the top anchor. | 4 / 5 |
Workflow Clarity | "How It Works" gives a clear 4-step sequence, but this batch/paid-API operation has no explicit validation or verification checkpoint in the body, capping it at 3 per the batch-operation guideline. | 3 / 5 |
Progressive Disclosure | Single bundled script (scripts/search_google_ads.py, confirmed present) with no nested references and well-organized sections; the inline output-fields table is slightly dense but appropriate, leaving minor organization gaps. | 4 / 5 |
Total | 15 / 20 Passed |