Content
85%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 tight, well-structured single-purpose skill: the body gives an executable prompt template, concrete model choices with sensible fallbacks, conditional parameters, and an explicit spelling-check retry loop, all within a compact, well-sectioned document. The only real weaknesses are minor: a redundant restatement of the description and the absence of a fully spelled-out example CLI invocation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence — a compact inputs table, one prompt template, and terse notes with no concept explanations. Minor over-padding: the frontmatter description is repeated verbatim as a bold tagline, and the Trigger Keywords section largely duplicates trigger information. | 4 / 5 |
Actionability | Concrete, near-executable guidance: a full prompt template with placeholder substitution, specific model IDs (ideogram-v3-t2i, flux-2-pro), conditional aspect ratios, and CLI command names. Minor gap: no complete example invocation line for `muapi image generate`, leaving the exact CLI syntax implicit. | 4 / 5 |
Workflow Clarity | As a single-task skill the one-step generation instruction is unambiguous (simple-skill exception applies), and it includes an explicit validation/feedback loop — "Always check: is the brand name spelled correctly? If not, retry with the exact spelling bolded in the prompt" — plus a fallback curl recipe for endpoints without CLI aliases. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references (none exist in the bundle), and the content is well-organized into clearly signaled sections (Inputs, Steps, Notes, Trigger Keywords, agent notes), satisfying the simple-skill criterion for a top score. | 5 / 5 |
Total | 18 / 20 Passed |