Marketplace

skill-description-evaluator

Automates multi-model skill description analysis using sequential-thinking. Evaluates invocation likelihood (Sonnet 4.5, Haiku), authority level against competing prompts, semantic clarity, user request matching. Generates 0-100 ratings with actionable recommendations. Use when evaluating skill descriptions or saying 'evaluate skill', 'test skill description', 'analyze skill effectiveness'.

$ Installer

git clone https://github.com/cblecker/claude-skills /tmp/claude-skills && cp -r /tmp/claude-skills/.claude/skills/skill-description-evaluator ~/.claude/skills/claude-skills

// tip: Run this command in your terminal to install the skill