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 body is an efficient, highly actionable two-step recipe with concrete model IDs, prompt templates, conditional branching, and a raw-endpoint fallback. Its only weaknesses are minor: a duplicated description line, no explicit output-verification checkpoint between the two generation steps, and command syntax that is implied rather than fully copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: a compact input table, two well-specified steps, and short notes with no explanations of concepts Claude already knows. Minor redundancy (the description restated verbatim as a bold line under the H1) keeps it below the lean anchor 5. | 4 / 5 |
Actionability | Concrete guidance throughout: named models ('ai-dress-change', 'flux-kontext-pro-i2i', 'gpt4o-edit'), full prompt templates with {{placeholder}} substitution, platform-to-aspect-ratio mapping, and a curl fallback with polling. It stops short of anchor 5 only because complete copy-paste command lines with full argument syntax are not shown. | 4 / 5 |
Workflow Clarity | A clearly sequenced two-step workflow with explicit conditional branching (clothing vs. non-clothing) and platform-specific settings, plus post-generation follow-ups. No validation checkpoint exists between Step 1 output and the Step 2 edit that consumes it, which is a minor gap at anchor 4 rather than anchor 5. | 4 / 5 |
Progressive Disclosure | The skill is a short, self-contained recipe with no bundle files (references/, scripts/, assets/ are absent) and no need for external references, yet sections (Inputs, Steps, Notes, Trigger Keywords, agent notes) are well-organized and the one cross-reference to the 'amazon-product-listing' skill is clearly signaled. Per the under-50-lines guideline, well-organized sections alone earn a 5. | 5 / 5 |
Total | 17 / 20 Passed |