This skill helps you accelerate RL-based LLM post-training with slime's Megatron-LM and SGLang for scalable data generation and rollout.
npx playbooks add skill orchestra-research/ai-research-skills --skill slime
The Slime skill is used to accelerate post-training of large language models that rely on reinforcement learning, connecting to Megatron-LM and SGLang for efficient data generation and rollout processes. It enables scalable data generation, which is useful for developers working on large language models that require extensive training data. Developers would use this skill when they need to speed up the post-training process of their RL-based language models.
Its 19-word system prompt specializes your agent in developer workflow with structured methodology and proven output formats. Install with one command to activate immediately.
This skill helps you accelerate RL-based LLM post-training with slime's Megatron-LM and SGLang for scalable data generation and rollout.
Slime is a free developer workflow skill for AI coding agents. This skill helps you accelerate RL-based LLM post-training with slime's Megatron-LM and SGLang for scalable data generation and rollout.. It provides a specialized system prompt that configures your agent with developer workflow expertise.
Run npx playbooks add skill orchestra-research/ai-research-skills --skill slime in your terminal to install Slime into your Claude Code session. It works immediately after installation.
Slime is compatible with Claude Code, Cursor, GitHub Copilot, Windsurf, OpenClaw, Cline, and any AI agent that supports custom system prompts or .cursorrules files.
Yes, Slime is completely free and open source. The full source is available on GitHub at https://github.com/orchestra-research/ai-research-skills/tree/main/06-post-training/slime. You only need a subscription to the AI agent you use it with.
Weekly roundup of top Claude Code skills, MCP servers, and AI coding tips.