Content
80%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 content is well-structured, executable, and appropriate for a single-purpose image-generation skill: concrete CLI invocation, a complete prompt, and clean sectioning with no unnecessary nesting. The main gap is the absence of an explicit generate/verify/retry feedback loop.
Suggestions
Add a brief validation/retry checkpoint after image generation (e.g. check the returned image for obvious failures and re-run with adjusted prompt params if needed) to push workflow clarity toward 5.
Tighten or hoist the large inline prompt into a collapsible-style block so the overview stays scannable, improving token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is well-organized and assumes Claude's competence (direct CLI params, minimal preamble); the long inline image-generation prompt is necessary content rather than padding, though a few framing sentences could still be trimmed. | 4 / 5 |
Actionability | Provides the concrete `muapi image edit` invocation with specific parameters (model id, size, format, quality, moderation) and a full copy-paste prompt, with only minor gaps around exact CLI argument syntax. | 4 / 5 |
Workflow Clarity | Sequences the single phase with input-gathering, auth setup, placeholder substitution, and post-generation suggestions; validation is present but light (no explicit verify/retry loop on a failed generation), keeping it just below 5. | 4 / 5 |
Progressive Disclosure | For a short, single-purpose skill with no bundle files, the body is cleanly sectioned (Inputs, Steps, Trigger Keywords, Notes) with no nested references, which earns the top score under the simple-skill exception. | 5 / 5 |
Total | 17 / 20 Passed |