Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, well-structured skill that efficiently teaches one-shot Gemini CLI usage. Its main weakness is incomplete actionability—the model name placeholder and sparse extension command details leave some gaps. The safety note about --yolo and the auth recovery instruction are good additions.
Suggestions
Provide at least one or two concrete model names for the --model flag (e.g., `gemini --model gemini-2.5-pro "Prompt..."`) to make the example fully actionable.
List the most common extension subcommands (e.g., `gemini extensions install`, `gemini extensions remove`) rather than just referencing `<command>`.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Very lean and efficient. Every line provides actionable information without explaining what Gemini is or how CLIs work. No unnecessary padding. | 3 / 3 |
Actionability | Provides concrete commands that are copy-paste ready, but lacks detail on available models (--model <name> is a placeholder), output format options, and what extensions commands are available. The guidance is real but incomplete. | 2 / 3 |
Workflow Clarity | This is a simple, single-purpose skill (one-shot CLI usage). The single action is unambiguous, and the auth note provides a clear recovery path. No multi-step destructive operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with no need for external references, the content is well-organized into logical sections (quick start, extensions, notes). No bundle files are needed for this scope. | 3 / 3 |
Total | 11 / 12 Passed |