Content
67%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 a clean, well-structured guide for a simple three-endpoint API skill: concrete request specs, parameters, response summaries, and error handling are all present. Its main weaknesses are redundant repetition of the full-URL guidance across three sections and the unstated step of constructing a LinkedIn URL from a person's name.
Suggestions
Consolidate the full-URL guidance into one place (the Parameters section) and remove its repetition in How It Works and Tips; drop Tips entries that restate Error Handling.
Add explicit guidance for constructing URLs from user-supplied names (e.g. profile URL is https://linkedin.com/in/<vanity-name>, company URL is https://linkedin.com/company/<company-name>).
Merge the three per-operation Parameter subsections, since all three take the identical single required 'url' parameter, into one line to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient, but "Use full LinkedIn URLs (e.g., https://linkedin.com/in/USERNAME)" is stated in three places (How It Works note, Parameters, Tips) and "Some profiles may have restricted visibility" duplicates the Error Handling section — "mostly efficient but includes some unnecessary explanation or could be tightened". | 3 / 5 |
Actionability | Concrete YAML request specs with real paths and query parameters plus worked example URLs are directly executable through the referenced runtime, but guidance for mapping a user-supplied name to a profile URL (e.g. the "Look up Satya Nadella" example) is left implicit — "mostly executable guidance with minor gaps". | 4 / 5 |
Workflow Clarity | Each of the three single-step operations is unambiguous, with a setup prerequisite (read scrapecreators-api) and error-recovery guidance (retry, rate-limit delays); this is a simple non-destructive skill so the validation cap does not apply, but the name-to-URL step and runtime-selection detail are implicit — "clear sequence with most checkpoints present; minor validation gaps". | 4 / 5 |
Progressive Disclosure | Sections are well organized and all content (three endpoints) is appropriately inline for a skill with no bundle files, but the Tips section largely repeats earlier material, which is a minor organization gap — "good structure; most content is appropriately placed; minor organization gaps". | 4 / 5 |
Total | 15 / 20 Passed |