Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is concise, well-organized, and clearly sequenced for a simple skill, with no external references needed. The main weakness is actionability: the tool is named but no concrete call example or parameter syntax is shown.
Suggestions
Add an executable call example showing the actual parameter syntax, e.g. `paper_search(query="...", year_start=2020, year_end=2025)`.
Resolve the naming inconsistency between frontmatter `allowed-tools: paper-search` and the body's `paper_search`.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and well-sectioned, does not explain what Google Scholar or the Serper API is, and assumes Claude's competence; every section earns its place rather than sitting at the mostly-efficient 2 level. | 3 / 3 |
Actionability | It names the tool (`paper_search`), mentions query and year filters, and shows a concrete output format, but never gives an executable call example with actual parameter names/syntax, leaving guidance incomplete. | 2 / 3 |
Workflow Clarity | For a simple single-purpose read-only search, the four-step "How to Use" sequence is clear and unambiguous with a review step; no destructive/batch validation cap applies. | 3 / 3 |
Progressive Disclosure | At ~43 lines with no bundle files and no need for external references, the well-organized sections satisfy the simple-skill allowance for a top progressive-disclosure score. | 3 / 3 |
Total | 11 / 12 Passed |