← All skills

llm-benchmark

75 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.

By KerberosClaw/kc_ai_skills (GitHub) · coding · 79 stars · scanned at commit dbd37fb

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. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.

Works with any agent that supports SKILL.md skills.

What this skill can do

Safer alternatives

Low-risk skills in the same category (coding) that look related. Check that one does what you need.

• 82 Low riskbenchmarkserejaris/personal-corp-os · 244 stars
• 100 Low risklocal-llm-expertsickn33/agentic-awesome-skills · 49,524 stars
• 100 Low riskllm-benchmarkUitbreidenOS/UitKit · 14 stars

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'llm-benchmark' ] || [ -L ~/.agents/skills/'llm-benchmark' ]; then echo 'A skill folder named llm-benchmark already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/KerberosClaw/kc_ai_skills' "$d" && git -C "$d" checkout --quiet 'dbd37fbe2121356fe25b69c70cbe5fc8b8870415' -- 'llm-benchmark' && mkdir -p ~/.agents/skills && cp -R "$d"/'llm-benchmark' ~/.agents/skills/'llm-benchmark' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'llm-benchmark' ~/.claude/skills/'llm-benchmark' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for KerberosClaw/kc_ai_skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/KerberosClaw/kc_ai_skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/KerberosClaw/kc_ai_skills/)

Score history