Content
82%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 well-structured, highly actionable prompting template with a clear locked workflow and concrete field-level guidance. Its only real gaps are the absence of explicit validation checkpoints in the workflow and a monolithic single-file structure that could split some reference material out.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean directive bullets that assume Claude's competence and avoid explaining known concepts, but supplementary framing sections ('What This Skill Solves', 'Best Fit Cases') add a little beyond the essential, fitting the 4 anchor with minor trimmable instances. | 4 / 5 |
Actionability | For an instruction-only skill the guidance is fully actionable: explicit ordered field lists (silhouette, age cues, facial system, costume logic, material response), concrete section orders for still and video modes, a worked fusion example, and a copy-paste 'Compact Output Pattern' template covering the common cases. | 5 / 5 |
Workflow Clarity | A clear locked sequence is given (identity lock, world/genre, medium/realism, sound, per-shot execution, continuity carryover) with an explicit 'Do not invert this order' guardrail, but there are no explicit validation checkpoints verifying one layer is locked before proceeding, so it stops at the 4 anchor. | 4 / 5 |
Progressive Disclosure | The single self-contained file is well-organized with clear hierarchical headers enabling easy navigation, but at ~130 lines with no external reference files it is monolithic rather than split, matching the 4 anchor (the under-50-line simple-skill exception to reach 5 does not apply). | 4 / 5 |
Total | 17 / 20 Passed |