Scores generated CLIs against the Steinberger bar, a 17-dimension rubric covering everything from output modes and auth to spec-derived checks like path validity and type fidelity. You can rescore the current CLI, score by name or path, or compare two side by side. It handles local builds when you're working inside the printing-press repo, falls back gracefully when specs are missing (omitting those dimensions from the denominator), and walks you through menus when multiple matches exist. The JSON output includes per-dimension scores, an overall letter grade, and a gap report. Useful when you want to benchmark a CLI's completeness or see how two generations stack up numerically.
npx -y skills add mvanhorn/cli-printing-press --skill printing-press-score --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sentry/dev
degausai/wonda
github/awesome-copilot
insforge/agent-skills
github/awesome-copilot
breaking-brake/cc-wf-studio