Content
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is concise, highly actionable, and well-structured for a self-contained skill, with concrete commands and prompts throughout. The only gap is the absence of explicit output verification/validation checkpoints in the workflow.
Suggestions
Add an explicit verification step after generation, e.g. confirm both mockups rendered and visually check aspect ratios and section completeness before presenting them.
Add a brief retry/feedback instruction for failed image generations (e.g. re-run with adjusted prompt or fallback model).
Remove the redundant restated description at the top of the body since it duplicates the frontmatter description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and action-oriented, assumes Claude's competence, and avoids explaining known concepts; every section (inputs table, steps, notes) earns its place, matching the lean-and-efficient anchor. | 3 / 3 |
Actionability | Provides fully executable guidance — exact CLI commands ('muapi image generate', 'muapi image edit'), specific model IDs ('gpt4o-text-to-image', 'bytedance-seedream-v4.5'), complete prompts, aspect ratios, and a curl fallback — making it copy-paste ready. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced with conditional logic (screenshot vs. generate) and an unreachable-URL fallback, but there are no explicit validation or verification checkpoints on the generated output, matching the 'sequence present but checkpoints missing' anchor. | 2 / 3 |
Progressive Disclosure | For a short, single-purpose skill with no bundle files, the body is well-organized into clearly headed sections (Inputs, Steps, Notes, Trigger Keywords, Notes for the Executing Agent) with no nested references, satisfying the well-organized-sections anchor. | 3 / 3 |
Total | 11 / 12 Passed |