← All skills

preference-optimization

100 / 100 · Low risk

Fine to try.

By wshobson/agents (GitHub) · coding · 42,412 stars · scanned at commit 9c61ab2

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/down feedback exist, when choosing between preference-optimization methods, or when a DPO run needs hyperparameters or debugging.

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

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

if [ -e ~/.agents/skills/'preference-optimization' ] || [ -L ~/.agents/skills/'preference-optimization' ]; then echo 'A skill folder named preference-optimization already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/wshobson/agents' "$d" && git -C "$d" checkout --quiet '9c61ab243def98f72da12abd41cfcf5bcd91af9d' -- 'plugins/llm-finetuning/skills/preference-optimization' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/llm-finetuning/skills/preference-optimization' ~/.agents/skills/'preference-optimization' && 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/'preference-optimization' ~/.claude/skills/'preference-optimization' (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 wshobson/agents shows the score of its lowest-scoring skill.

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

Score history