lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
安装
npx skills add NousResearch/hermes-agent --skill evaluating-llms-harnessnpx skills add NousResearch/hermes-agent --skill evaluating-llms-harness -a claude-code -gnpx skills add NousResearch/hermes-agent --skill evaluating-llms-harness -a codex -ggemini skills install https://github.com/NousResearch/hermes-agent.git --path optional-skills/mlops/evaluation/evaluating-llms-harnessgh skill install NousResearch/hermes-agent evaluating-llms-harnessgit clone --depth 1 https://github.com/NousResearch/hermes-agent /tmp/NousResearch__hermes-agent
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/evaluation/evaluating-llms-harness ~/.claude/skills/evaluating-llms-harness # Claude Code
cp -R /tmp/NousResearch__hermes-agent/optional-skills/mlops/evaluation/evaluating-llms-harness ~/.agents/skills/evaluating-llms-harness # Codex, Cursor, Gemini CLI, Copilot, OpenCode