← All skills

grpo-rl-training

100 / 100 · Low risk

Fine to try.

By KalarisLabs/research-agent-skills (GitHub) · research · 126 stars · scanned at commit 802bbea

Guides GRPO (Group Relative Policy Optimization) fine-tuning of language models with the TRL library, including GRPOTrainer configuration, composing multiple reward functions (correctness, format, length, style), dataset prep in chat format, Unsloth setup, LoRA merging, and monitoring reward, reward_std and KL. Use when training a model to follow a strict output format such as XML or JSON. Use when teaching verifiable tasks like math or code with objective correctness rewards. Use when improvin…

Works with any agent that supports SKILL.md skills.

Partially scanned — some files couldn't be read; we'll retry on the next scan

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/'grpo-rl-training' ] || [ -L ~/.agents/skills/'grpo-rl-training' ]; then echo 'A skill folder named grpo-rl-training already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/KalarisLabs/research-agent-skills' "$d" && git -C "$d" checkout --quiet '802bbea44e551abac24d6856f83fc55149bbdba3' -- 'skills/grpo-rl-training' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/grpo-rl-training' ~/.agents/skills/'grpo-rl-training' && 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/'grpo-rl-training' ~/.claude/skills/'grpo-rl-training' (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 KalarisLabs/research-agent-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/KalarisLabs/research-agent-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/KalarisLabs/research-agent-skills/)

Score history