Overview
verl-rl-training is an open-source devops skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What verl-rl-training does
verl is a flexible, efficient, and production-ready RL training library for large language models from ByteDance's Seed team. It implements the HybridFlow framework (EuroSys 2025) and powers models like Doubao-1.5-pro achieving O1-level performance on math benchmarks.
Best for
What’s inside
The SKILL.md for verl-rl-training is organised into these sections:
- When to Use verl
- Key Features
- Installation
- Quick Start: GRPO Training
- Core Architecture
- Workflow 1: Math Reasoning with GRPO
- Prerequisites Checklist
- Step 1: Prepare Dataset
- Step 2: Define Reward Function
- Step 3: Create Training Config
- Step 4: Launch Training
- Step 5: Monitor and Validate
Installation
Add verl-rl-training to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
License
verl-rl-training is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Works with Claude Code, Codex
Author
Topics
Frequently asked questions
- What does verl-rl-training do?
- Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
- How do I install verl-rl-training?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is verl-rl-training free to use?
- Yes. verl-rl-training is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does verl-rl-training work with?
- verl-rl-training lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does verl-rl-training come from?
- verl-rl-training ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.
