Content
81%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 concise, highly actionable skill body with clean structure and a verified bundle script. Its main weakness is the absence of validation/error-handling guidance for a batch scraping operation, which caps workflow clarity.
Suggestions
Add an explicit validation checkpoint after the Apify run (e.g. checking the run succeeded and output is non-empty before processing), and a brief error-recovery note for failed or timed-out runs.
Clarify the batch workflow sequence for multiple profiles (scrape -> verify each run -> filter by date -> output) so the multi-profile path has a clear ordered flow.
Note what happens on common failure modes (invalid profile URL, token missing, rate limits) and how to respond.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient at ~45 lines; no padding or explanations of concepts Claude already knows, every section (Quick Start, CLI Reference, Cost, Notes) earns its place. | 5 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands with real profile URLs and flag combinations, plus a complete CLI reference table covering all options. | 5 / 5 |
Workflow Clarity | Although simple and single-purpose, this is a batch operation scraping multiple profiles with no validation/verification checkpoint (e.g. checking the Apify run status, handling failures, or verifying output), which per the rubric caps workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | Well-organized short skill (under 50 lines) with clear section headers and a real referenced script (scripts/scrape_linkedin_posts.py) that exists in the bundle; structure is appropriate with no nested references. | 5 / 5 |
Total | 18 / 20 Passed |