Content
61%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 well-structured, mostly actionable skill body with a real executable script and clear intent-to-shot mapping tables. It loses points for re-explaining cinematography basics Claude already knows and for leaving the async polling workflow without concrete validation steps.
Suggestions
Remove or condense definitions of basic cinematography terms (Dolly, Truck, Crane, Anamorphic) that Claude already knows; keep only the skill's controlled-vocabulary intent labels.
Show the actual polling command for Step 3 (e.g. the core/platform/check-result.sh invocation with a loop and a success/failure branch) to add validation checkpoints.
Trim the 'Core Competencies' section and decorative emoji/separator lines to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with compact tables and lists, but it defines camera fundamentals Claude already knows (Dolly, Truck, Crane, Anamorphic, Rack Focus) and the 'Core Competencies' section is padded with generic descriptions that could be trimmed. | 3 / 5 |
Actionability | Provides a concrete, executable bash invocation with flags referencing a real bundle script (scripts/generate-film.sh); minor gaps in that the async polling command is named but not shown. | 4 / 5 |
Workflow Clarity | Three steps are clearly sequenced (define brief, invoke script, handle async response), but there are no validation checkpoints and the polling/error-handling loop in Step 3 is only described, not specified. | 3 / 5 |
Progressive Disclosure | Well-organized into clearly labeled sections with a real one-level-deep script reference; minor organization noise from emoji headers and multiple horizontal rules rather than fully lean navigation. | 4 / 5 |
Total | 14 / 20 Passed |