Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/davila7/claude-code-templates/main/cli-tool/components/skills/ai-research/post-training-grpo-rl-training/SKILL.mdRegistry
github (via claudemarketplaces.com)