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.

skills.sh installs: 135
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add borghei/claude-skills --skill skill-tester --agent claude-code

Installs into .claude/skills of the current project.

Files

Skill Tester

Validate skill packages for structure compliance, test Python scripts for syntax and stdlib-only imports, and score quality across four dimensions (documentation, code quality, completeness, usability) with letter grades and improvement recommendations. Supports BASIC, STANDARD, and POWERFUL tier classification.

Core Capabilities

Structure validation — check required files, directory layout, YAML frontmatter, and required SKILL.md sections against tier thresholds.
Script testing — AST syntax checks, stdlib-only import analysis, argparse and __main__-guard detection, runtime --help and sample-data execution.
Quality scoring — four equally weighted dimensions producing an overall score, letter grade (A+ through F), and a prioritized improvement roadmap.
Tier classification — BASIC / STANDARD / POWERFUL requirements for SKILL.md depth, script count/LOC, argparse, output formats, and error handling.
Dual output — human-readable reports and --json for CI/CD gating with meaningful exit codes.