Battle Test

If you're maintaining a skills directory and need to know where it's falling short of the Skill Creator standard, this runs a systematic audit across your entire collection. It scans frontmatter for structural issues, checks trigger patterns and file globs, then deep-dives a sample of skills against a formal rubric covering trigger accuracy, format quality, verification steps, and token efficiency. You get a scored report with point deductions per finding and a phased remediation plan. The orchestration is thorough but deliberate, walking through discovery, breadth scans, deep evaluation, and interactive follow-up options like generating task files or fixing the worst offenders immediately. Honestly feels like the kind of tooling you build when you've hit critical mass on skills and need to enforce consistency at scale.

Install to Claude Code

npx -y skills add hoangnguyen0403/agent-skills-standard --skill battle-test --agent claude-code