Skip to content
appsgit

Verl Rl Training

Verl Rl Training is an agent skill (a SKILL.md file) from Orchestra-Research/AI-Research-SKILLs. It provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). It works with Claude Code, Codex, Cursor, Gemini CLI and OpenCode and has 13,315 GitHub stars across a repository of 5 listed skills.

github.com/Orchestra-Research/AI-Research-SKILLs/06-post-training/verl (opens in a new tab)

View on GitHub (opens in a new tab)

Add this skill

Claude

This repository is a Claude Code plugin marketplace. In Claude Code:

/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
/plugin   # browse ai-research-skills and install the plugin that contains verl-rl-training

In the Claude apps, zip the verl-rl-training folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git
cp -r AI-Research-SKILLs/06-post-training/verl .agents/skills/verl-rl-training   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git
cp -r AI-Research-SKILLs/06-post-training/verl .cursor/skills/verl-rl-training   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

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. 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.

When it triggers

  • Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

More skills in Orchestra-Research/AI-Research-SKILLs

5 skills are listed from this repository.

Similar skills

More devops & cloud skills

All DevOps & cloud

FAQ

Verl Rl Training FAQ

Still curious? Email info@appsgit.com.

What is the Verl Rl Training skill?

Verl Rl Training is an agent skill (a SKILL.md file) from Orchestra-Research/AI-Research-SKILLs. It provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). It works with Claude Code, Codex, Cursor, Gemini CLI and OpenCode and has 13,315 GitHub stars across a repository of 5 listed skills. Its SKILL.md lives at github.com/Orchestra-Research/AI-Research-SKILLs/06-post-training/verl.

How do I install the Verl Rl Training skill?

In Claude Code, run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs, then install its plugin from /plugin. For Codex or Cursor, copy the verl-rl-training folder into .agents/skills/ or .cursor/skills/.

Is the Verl Rl Training skill free?

Yes. The repository is open source under the MIT license.

Is Verl Rl Training maintained?

The repository's most recent commit was on Jun 16, 2026. Its latest release is v1.7.2. appsgit only lists skills from repositories with a commit in the last six months.