What problem does it solve? Evaluating the quality of generated CLI tools requires a consistent rubric; this Skill runs the cli-printing-press scorecard against generated CLIs, producing graded dimension scores, gap reports, and side-by-side comparisons. ## Core Features & Use Cases - Single CLI Scoring: Score a generated CLI by name or path across Tier 1 infrastructure and Tier 2 domain-correctness dimensions, producing a total score and letter grade. - Rescore Current: Automatically discover the CLI from current-run state or the published library and rescore it without arguments. - Side-by-Side Comparison: Run two scorecards in parallel and render a delta table showing per-dimension differences between two CLIs. - Use Case: After regenerating a CLI for the Notion API, run the skill to compare notion-pp-cli-4 against notion-pp-cli-2 and see exactly which dimensions improved. ## Quick Start Ask the assistant to score the generated CLI named notion-pp-cli-4, or to compare notion-pp-cli-4 against notion-pp-cli-2.