← All skills

trl

80 / 100 · Low risk

Fine to try.

By mkurman/zorai (GitHub) · other · 327 stars · scanned at commit 8ea1fc3

Transformer Reinforcement Learning library (TRL). Supervised fine-tuning (SFT), reward modeling, PPO, DPO, KTO, GRPO for RLHF. Process reward models and language model alignment.

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/'trl' ] || [ -L ~/.agents/skills/'trl' ]; then echo 'A skill folder named trl already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/mkurman/zorai' "$d" && git -C "$d" checkout --quiet '8ea1fc3ae126b6e103b8508bacd8f5aa60b6f4ad' -- 'skills/scientific-skills/trl' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/scientific-skills/trl' ~/.agents/skills/'trl' && 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/'trl' ~/.claude/skills/'trl' (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 mkurman/zorai shows the score of its lowest-scoring skill.

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

Score history