← All skills

benchmark-ollama-models

80 / 100 · Low risk

Fine to try.

By nerdai/llm-agents-from-scratch (GitHub) · other · 194 stars · scanned at commit 89a0c09

Benchmark Ollama Cloud models on the chapter notebooks' behaviour (real tool calls, skill activation, subagents finishing), not just pass/fail, to pick or re-validate the default Ollama Cloud model. Use before changing make_llm()'s Ollama Cloud default, when a cloud model is retired, or when asked to compare or test cloud models on the notebooks.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

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

if [ -e ~/.agents/skills/'benchmark-ollama-models' ] || [ -L ~/.agents/skills/'benchmark-ollama-models' ]; then echo 'A skill folder named benchmark-ollama-models already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/nerdai/llm-agents-from-scratch' "$d" && git -C "$d" checkout --quiet '89a0c096cf3c4637a4b9c896e6fe0d40bf4c9c5a' -- '.claude/skills/benchmark-ollama-models' && mkdir -p ~/.agents/skills && cp -R "$d"/'.claude/skills/benchmark-ollama-models' ~/.agents/skills/'benchmark-ollama-models' && 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/'benchmark-ollama-models' ~/.claude/skills/'benchmark-ollama-models' (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 nerdai/llm-agents-from-scratch shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/nerdai/llm-agents-from-scratch.svg)](https://zalavijaysinh.github.io/skilltrust/repos/nerdai/llm-agents-from-scratch/)

Score history