Use when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report.
安装
npx skills add KerberosClaw/kc_ai_skills --skill llm-benchmarknpx skills add KerberosClaw/kc_ai_skills --skill llm-benchmark -a claude-code -gnpx skills add KerberosClaw/kc_ai_skills --skill llm-benchmark -a codex -ggemini skills install https://github.com/KerberosClaw/kc_ai_skills.git --path llm-benchmarkgh skill install KerberosClaw/kc_ai_skills llm-benchmarkgit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills /tmp/KerberosClaw__kc_ai_skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/KerberosClaw__kc_ai_skills/llm-benchmark ~/.claude/skills/llm-benchmark # Claude Code
cp -R /tmp/KerberosClaw__kc_ai_skills/llm-benchmark ~/.agents/skills/llm-benchmark # Codex, Cursor, Gemini CLI, Copilot, OpenCode