Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked).
Install
npx skills add HeshamFS/materials-simulation-skills --skill skill-evaluatornpx skills add HeshamFS/materials-simulation-skills --skill skill-evaluator -a claude-code -gnpx skills add HeshamFS/materials-simulation-skills --skill skill-evaluator -a codex -ggemini skills install https://github.com/HeshamFS/materials-simulation-skills.git --path skills/meta/skill-evaluatorgh skill install HeshamFS/materials-simulation-skills skill-evaluatorgit clone --depth 1 https://github.com/HeshamFS/materials-simulation-skills /tmp/HeshamFS__materials-simulation-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/HeshamFS__materials-simulation-skills/skills/meta/skill-evaluator ~/.claude/skills/skill-evaluator # Claude Code
cp -R /tmp/HeshamFS__materials-simulation-skills/skills/meta/skill-evaluator ~/.agents/skills/skill-evaluator # Codex, Cursor, Gemini CLI, Copilot, OpenCode