Content
92%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 compact, well-organized reference skill with terse, actionable decision rules and no wasted tokens. The only meaningful gap is the absence of a brief worked example showing the vocabulary and rules applied to a real storyboard or prompt.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes cinematography competence — every line is a direct mapping ('low angle: power, myth, threat, grandeur') with no padding or explanation of concepts Claude already knows. This matches the 'every token earns its place' anchor. | 5 / 5 |
Actionability | The selection, angle, and coverage rules are concrete, directive mappings a model can apply directly ('Change shot size to change information priority'). It falls short of anchor 5 only because there is no worked example showing the vocabulary and rules applied in an actual storyboard or prompt. | 4 / 5 |
Workflow Clarity | This is a simple, single-purpose reference skill whose single action — choose shot size and angle by dramatic intent — is unambiguous, so the simple-skill exception applies. There are no destructive or batch operations, so the validation cap does not apply. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references, and the content is organized into clear, well-scoped sections (Standard Vocabulary, Selection Rules, Angle Rules, Coverage Rules), matching the simple-skill exception for a top score. No bundle files exist and none are needed. | 5 / 5 |
Total | 19 / 20 Passed |