Content
86%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 strong, executable skill body: it specifies exact CLI tools, models, prompts, and fallbacks with a clearly phased workflow and user-approval checkpoints. The main improvement opportunities are showing literal command syntax for the image-edit and video calls and adding a retry/validation loop for failed generations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with no explanations of concepts Claude already knows — model IDs, prompts, aspect ratios, the curl fallback, and the auth note are all non-inferable operational detail. The only redundancy is the bolded line duplicating the description, which is trivial; matches anchor 5 ('lean and efficient; assumes Claude's competence'). | 5 / 5 |
Actionability | Concrete guidance throughout — 'muapi image edit (model=gpt-image-2-text-to-image)', full copy-paste prompts, 9:16 aspect ratios, 'curl -X POST https://api.muapi.ai/api/v1/<endpoint>... -H "x-api-key: $MUAPI_API_KEY"', and 'muapi predict wait <request_id>'. Falls short of anchor 5 because the image-edit and video calls are described as parameter lists rather than literal executable commands, and the video model is left as 'e.g. sd-2-omni-reference or veo3.1-image-to-video'. | 4 / 5 |
Workflow Clarity | Two clearly sequenced phases with explicit checkpoints: 'If {{human_image}} or {{product_image}} is not provided, ask the user to upload them', 'Present the combined image to the user for approval', and delivering video plus script at the end. Not 5 because there is no validation/feedback loop for failed or poor-quality generations (retry, re-generate, or check status beyond 'muapi predict wait'), leaving minor validation gaps per anchor 4. | 4 / 5 |
Progressive Disclosure | The skill is self-contained — no references/, scripts/, or assets/ directories exist, and nothing in the ~60-line single-workflow body warrants a separate file. Sections (Inputs, Steps, Trigger Keywords, Notes) are clearly organized and navigable; per the rubric's simple-skill guidance, well-organized sections with no need for external references merit a 5. | 5 / 5 |
Total | 18 / 20 Passed |