Run SLM-Lab deep RL benchmarks, monitor dstack jobs, extract results, and update BENCHMARKS.md. Use when asked to run benchmarks, check run status, extract scores, update benchmark tables, or generate plots.
安装
npx skills add kengz/SLM-Lab --skill slm-lab-benchmarknpx skills add kengz/SLM-Lab --skill slm-lab-benchmark -a claude-code -gnpx skills add kengz/SLM-Lab --skill slm-lab-benchmark -a codex -ggemini skills install https://github.com/kengz/SLM-Lab.git --path .claude/skills/benchmarkgh skill install kengz/SLM-Lab slm-lab-benchmarkgit clone --depth 1 https://github.com/kengz/SLM-Lab /tmp/kengz__SLM-Lab
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/kengz__SLM-Lab/.claude/skills/benchmark ~/.claude/skills/slm-lab-benchmark # Claude Code
cp -R /tmp/kengz__SLM-Lab/.claude/skills/benchmark ~/.agents/skills/slm-lab-benchmark # Codex, Cursor, Gemini CLI, Copilot, OpenCode