Content
87%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.
Concise, highly actionable content with a real supporting script and clean structure, weakened only by the absence of explicit validation/verification guidance for the batch scraping workflow.
Suggestions
Add a verification step after scraping, e.g., checking that returned tweets fall within the requested date range and guidance on what to do when zero results are returned.
Include a brief error-recovery note for common Apify run failures (FAILED/TIMED-OUT) so Claude knows how to retry or adjust the query.
Document expected failure modes (rate limits, token errors) and the corrective action in the Quick Start or a short Troubleshooting section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient body that assumes Claude's competence; no padded explanations of what Twitter or Apify are, and every section earns its place. | 5 / 5 |
Actionability | Copy-paste ready CLI commands in Quick Start, a complete CLI reference table, a direct API input example, and a concrete output schema covering the common cases. | 5 / 5 |
Workflow Clarity | The script's internal 6-step sequence is clear, but the body lacks explicit validation/verification checkpoints for this batch scraping operation (e.g., what to do on zero results, partial failures, or confirming the date filter applied), which caps batch-operation workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | Well-organized sections with a single real bundle file (scripts/search_twitter.py) correctly referenced one level deep and no nested references; appropriate for a simple single-purpose skill. | 5 / 5 |
Total | 18 / 20 Passed |