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 content is well-structured and actionable with concrete CLI guidance and a clear phased workflow. The main improvement is adding output-validation and error-recovery feedback loops around the generation steps.
Suggestions
Add explicit validation steps after each generation call (e.g. check the returned image/video is non-empty and matches expected format) with a retry-on-failure loop.
Specify exact muapi CLI argument syntax for the prompt/negative-prompt/aspect-ratio parameters so the commands are copy-paste ready.
Tighten the Notes section by replacing the procedural restatement with a one-line pointer to auth and placeholder substitution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean — an inputs table, phased steps, and agent notes — with the long prompts being essential artifact content rather than concept explanation; only minor phrasing in the Notes could be trimmed, so it sits just below the maximally efficient (5). | 4 / 5 |
Actionability | Provides concrete CLI commands ('muapi image edit', 'muapi video from-image'), model IDs, a curl fallback, and full copy-paste prompts; minor gaps in exact CLI argument syntax keep it just below fully executable (5). | 4 / 5 |
Workflow Clarity | A clear two-phase sequence (cartoonify -> user approval -> motion-control animation) with an explicit approval checkpoint between phases; it lacks output-validation and error-recovery feedback loops, so it does not reach 5. | 4 / 5 |
Progressive Disclosure | No bundle files exist and none are needed; the single SKILL.md is well-organized into clear sections (Inputs, Steps, Trigger Keywords, Notes), which per the rubric's simple-skill guidance merits a 5. | 5 / 5 |
Total | 17 / 20 Passed |