Content
72%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 body is a tight, actionable recipe with concrete CLI commands, a sensible parallel fan-out, and clean organization. Its main weaknesses are a missing validation loop for the batch render operation and an unspecified command syntax for the primary `muapi image edit` call.
Suggestions
Add a validation step after the parallel fan-out, e.g. check each returned asset id and confirm its aspect ratio matches the requested format, re-running failed nodes before returning results.
Show the full argument syntax for `muapi image edit` (how source image, prompt, and model flags are passed) or a concrete example invocation, mirroring the completeness of the curl fallback.
Drop the bold sentence duplicating the frontmatter description to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with no explanations of concepts Claude already knows; the only trimmable padding is the bold restatement of the frontmatter description under the title, so it sits at anchor 4 rather than the fully lean anchor 5. | 4 / 5 |
Actionability | Concrete guidance dominates: `muapi image edit` with model=nano-banana-2-edit, a full curl fallback command, and a templated prompt. However the primary command's argument syntax (how the source image and prompt are passed) is never shown, leaving minor gaps that keep it below fully copy-paste-ready anchor 5. | 4 / 5 |
Workflow Clarity | The sequence is clear (one node per format, all parallel, labeled outputs, skip-if-already-matching), but the batch fan-out has no validation or verification step (e.g. confirming each render succeeded or matches the requested ratio), and the guidelines cap batch operations without validation at 3. | 3 / 5 |
Progressive Disclosure | The skill is under 60 lines, single-purpose, needs no external reference files, and is organized into clear well-labeled sections (Inputs, Steps, Notes, Trigger Keywords), which per the simple-skill guideline earns a 5 with well-organized sections alone. | 5 / 5 |
Total | 16 / 20 Passed |