Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with executable CLI examples and a clear single-tool workflow, but it carries redundant match-level wording and a heavy inline JSON schema that inflate the token budget without progressive disclosure to absorb them.
Suggestions
Move the full input JSON schema into a references/ file and link to it, keeping only the input table inline in SKILL.md.
De-duplicate the match-level descriptions: present them once in the table and remove the prose restatement.
Add a short 'Quick start' section near the top so the example command surfaces before the schema reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with executable commands and a tabular input spec, but it duplicates the match-level descriptions (prose and table) and embeds a large ~60-line input JSON schema inline, so it is not fully lean. | 2 / 3 |
Actionability | It provides concrete, copy-paste-ready CLI commands including input-file and stdin variants plus a troubleshooting install command, matching the fully-executable anchor. | 3 / 3 |
Workflow Clarity | As a single-tool skill the find-then-call sequence is stated up front and the output format is explicit; with no destructive or batch operation requiring validation, the simple-skill rule lets workflow clarity reach 3. | 3 / 3 |
Progressive Disclosure | Sections are organized, but the large embedded JSON schema is inline content with no bundle files or one-level-deep references to offload it to, fitting the some-structure-but-inline-content anchor rather than the well-signaled-references anchor. | 2 / 3 |
Total | 10 / 12 Passed |