Content
83%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 and highly actionable single-purpose skill with a real referenced script and good structure. The main weakness is the absence of explicit validation/feedback-loop guidance for a batch operation with cost consequences.
Suggestions
Add an explicit validation step in the workflow, e.g. confirm the cost estimate is acceptable before approving the run, and how to retry/handle FAILED/ABORTED run states.
Note the client-side follower-filter caveat earlier (before the CLI table) so users know --min/--max-followers post-filter rather than constrain the Apify query.
Document the expected output schema example for the `json` format so consumers of the result know the shape without reading the script.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient: copy-paste Quick Start, a tight CLI table, cost note, and an output-field list with no padding explaining what LinkedIn or Apify is; every section earns its place. | 5 / 5 |
Actionability | Four fully executable copy-paste commands, a complete CLI reference with defaults, the real script path, the required env var, and the pip install line — copy-paste ready for the common cases. | 5 / 5 |
Workflow Clarity | This is a batch operation (up to 1000 results with cost implications) but the SKILL.md body provides only rough sequencing and no explicit validate/retry/feedback-loop guidance; the per-guideline cap of 3 applies. | 3 / 5 |
Progressive Disclosure | Well-organized sections (Quick Start, CLI Reference, Cost, Output Fields, Notes) with a single one-level-deep, real script reference and clearly signaled follow-on actors; minor organization gaps keep it just below 5. | 4 / 5 |
Total | 17 / 20 Passed |