Content
78%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 tight, actionable, well-organized single-task skill with a concrete generation command, prompt template, and a spelling-check retry loop. Main improvements would be showing a full copy-paste command line and formalizing the validation checkpoint as a numbered step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and well-structured (inputs table, step, notes), with only minor over-explanation in the generic 'Notes for the Executing Agent' curl-fallback boilerplate that could be trimmed. | 4 / 5 |
Actionability | It gives a concrete `muapi image generate` command with model id, a full prompt template, and conditional aspect-ratio rules; minor gap is that no literal complete command line is shown for copy-paste. | 4 / 5 |
Workflow Clarity | A clear single-step sequence is given with an explicit brand-name spelling check and retry loop; the checkpoint is present but stated informally rather than as a numbered validate-then-proceed step. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, single-purpose, needs no external references, and is organized into clearly labeled sections (Inputs, Steps, Notes, Trigger Keywords), satisfying the simple-skill exception for a top score. | 5 / 5 |
Total | 17 / 20 Passed |