Skill Tester

This is quality control tooling for Claude Code skill packages themselves. It runs three validators that check YAML frontmatter, verify Python scripts use only stdlib imports, and score documentation completeness across four dimensions with letter grades. You'd use it before publishing a skill or in CI to enforce tier requirements like minimum line counts and argparse coverage. The scoring rubric is opinionated but sensible: it penalizes padding, requires help strings on every argument, and won't let good SKILL.md documentation compensate for scripts that lack usability. Completes a full validation pass in under 10 seconds and exits non-zero to block merges when skills fail critical checks.