Design effective LLM judge .prompt files for evaluators. Use when creating judgeVerdict/judgeScore/judgeLabel prompts, or when existing judges produce unreliable results.
安装
npx skills add growthxai/output --skill output-eval-judge-promptnpx skills add growthxai/output --skill output-eval-judge-prompt -a claude-code -gnpx skills add growthxai/output --skill output-eval-judge-prompt -a codex -ggemini skills install https://github.com/growthxai/output.git --path coding_assistants/claude/plugins/outputai/skills/output-eval-judge-promptgh skill install growthxai/output output-eval-judge-promptgit clone --depth 1 https://github.com/growthxai/output /tmp/growthxai__output
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/growthxai__output/coding_assistants/claude/plugins/outputai/skills/output-eval-judge-prompt ~/.claude/skills/output-eval-judge-prompt # Claude Code
cp -R /tmp/growthxai__output/coding_assistants/claude/plugins/outputai/skills/output-eval-judge-prompt ~/.agents/skills/output-eval-judge-prompt # Codex, Cursor, Gemini CLI, Copilot, OpenCode