Content
88%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 highly actionable and operationally precise: executable examples for every common case, a complete parameter table, explicit timeout/synchronization requirements, and a clear error-recovery policy. It is token-efficient with only minor redundancy, and its structure cleanly separates usage, output, setup, and error handling, with the sole bundle script correctly referenced.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and consistently conveys non-obvious operational facts (backend auto-selection, 600s timeout, synchronous invocation, output location) rather than concepts Claude already knows. Minor over-explanation could be trimmed — the "don't specify a model" guidance is repeated in the intro and Setup section, and the per-provider model lists are somewhat long — keeping it just below the lean anchor 5. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands are given for the common cases: basic generation, size/aspect-ratio generation, single-image editing, and multi-image fusion, plus a parameter table with types and defaults and the exact success/error JSON output shapes. This matches the anchor for complete executable guidance covering common cases. | 5 / 5 |
Workflow Clarity | The single action is unambiguous — invoke scripts/generate.py synchronously with a JSON argument, wait for output (timeout >= 600s), parse the JSON, then display the image — and the Error Handling section provides an explicit feedback loop (on error, do not retry with the same parameters; direct the user to fix env_config, then retry). The simple-skill exception applies and no validation gap exists for this non-destructive, non-batch operation. | 5 / 5 |
Progressive Disclosure | The body is well organized into clear sections (Usage, Parameters, Examples, Output, Setup, Error Handling, Notes) and its single reference, scripts/generate.py, is real and one level deep. Minor gap: the per-provider model lists and setup detail are inlined in a ~105-line body where a small references file could keep SKILL.md leaner, so it sits just below the well-split anchor 5. | 4 / 5 |
Total | 18 / 20 Passed |