Content
93%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.
A tight, highly actionable single-script skill that respects the context window and gives copy-paste commands plus a complete flag reference. Its only weakness is the absence of an explicit result-verification step for the batch scrape operation.
Suggestions
Add a brief verification note after the commands (e.g., confirm the output is non-empty and that the actor run status was SUCCEEDED; re-run or adjust --timeout if the run FAILED/TIMED-OUT).
Note the error-path behavior surfaced by the script (FAILED/ABORTED/TIMED-OUT raises a RuntimeError) so Claude knows to inspect the run status on failure.
Clarify the script path convention (the body uses skills/product-hunt-scraper/scripts/... while the file ships at ./scripts/...) to avoid path confusion at invocation time.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient with no padding — it skips explaining what Product Hunt or Apify is and gives only the output fields, copy-paste commands, a compact CLI table, and two terse notes. | 5 / 5 |
Actionability | Three copy-paste-ready CLI commands cover the common cases (daily top, weekly with keywords, monthly as JSON) and a full CLI reference table with defaults; the flags match the bundled script. | 5 / 5 |
Workflow Clarity | The single-action workflow is unambiguous and benefits from the simple-skill exception, but the body surfaces no verification step (e.g., check non-empty output, handle FAILED run status) for this batch fetch, capping it below 5. | 4 / 5 |
Progressive Disclosure | Under 50 lines with well-organized Quick Start, CLI Reference, and Notes sections and a single one-level reference to the bundled script at a verified path, satisfying the simple-skill exception. | 5 / 5 |
Total | 19 / 20 Passed |