Agent evaluation framework based on Anthropic's best practices. USE WHEN eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test. Includes three grader types (code-based, model-based, human), transcript capture, pass@k/pass^k metrics, and ALGORITHM integration.
安装
npx skills add danielmiessler/LifeOS --skill evalsnpx skills add danielmiessler/LifeOS --skill evals -a claude-code -gnpx skills add danielmiessler/LifeOS --skill evals -a codex -ggemini skills install https://github.com/danielmiessler/LifeOS.git --path Releases/v2.5/.claude/skills/Evalsgh skill install danielmiessler/LifeOS evalsgit clone --depth 1 https://github.com/danielmiessler/LifeOS /tmp/danielmiessler__LifeOS
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/danielmiessler__LifeOS/Releases/v2.5/.claude/skills/Evals ~/.claude/skills/evals # Claude Code
cp -R /tmp/danielmiessler__LifeOS/Releases/v2.5/.claude/skills/Evals ~/.agents/skills/evals # Codex, Cursor, Gemini CLI, Copilot, OpenCode