Content
92%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 model of token-efficient skill authoring: concrete one-shot commands, well-labeled sections, an auth fallback, and an explicit safety note to avoid --yolo. The only weakness is placeholder syntax in the Extensions section that keeps it from being fully copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~20-line body is lean and efficient: every line is an executable command or an operational note, with no explanation of concepts Claude already knows, matching 'lean and efficient; every token earns its place'. | 5 / 5 |
Actionability | Mostly executable commands (e.g., 'gemini "Answer this question..."', 'gemini --output-format json "Return JSON"'), but placeholders like 'gemini extensions <command>' and '--model <name>' leave minor gaps, matching 'concrete code or commands with minor gaps' rather than fully copy-paste-ready coverage. | 4 / 5 |
Workflow Clarity | This is a simple single-purpose skill and the single action (one-shot invocation with a positional prompt) is unambiguous, plus a concrete auth fallback note ('run gemini once interactively and follow the login flow'); no destructive or batch operations require validation, so the simple-skill exception applies. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references (no bundle files exist), and its content is organized into clear sections (Quick start, Extensions, Notes), which merits a 5 under the scoring note for simple skills. | 5 / 5 |
Total | 19 / 20 Passed |