Content
86%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 well-structured, actionable skill body with executable commands for all five endpoints and a clean one-level reference split. Minor duplication of enum/period tables and the absence of an explicit error-recovery loop are the only weaknesses.
Suggestions
De-duplicate the rankType enum and period values: state them once in Rules and reference that from the Use Flow (or vice versa) to trim tokens.
Add a short error-handling step to the Use Flow (e.g., on non-zero CLI exit or error JSON, surface the mapped error and adjust params before retrying).
Note the icon/logo URL prefix and numeric-string conversion gotchas inline near the response handling step rather than only in the Rules section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with tables and real command examples, but the rankType enum and period values are restated in both the 'Use Flow' and 'Rules' sections, a minor redundancy that could be trimmed. | 4 / 5 |
Actionability | Every command ships a copy-paste-ready invocation with a real JSON blob, and the Commands table pairs required args with concrete examples, covering the common cases fully. | 5 / 5 |
Workflow Clarity | The six-step Use Flow is clearly sequenced with an explicit 'MUST read its reference file' checkpoint, but no explicit error-recovery/feedback loop is documented for upstream failures. | 4 / 5 |
Progressive Disclosure | The body is a concise overview that delegates full per-command detail to a single one-level-deep reference (references/cli.md, verified present) via a dedicated 'Full CLI Reference' section and inline read-reference instructions. | 5 / 5 |
Total | 18 / 20 Passed |