Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
安装
npx skills add davila7/claude-code-templates --skill grpo-rl-trainingnpx skills add davila7/claude-code-templates --skill grpo-rl-training -a claude-code -gnpx skills add davila7/claude-code-templates --skill grpo-rl-training -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/post-training-grpo-rl-traininggh skill install davila7/claude-code-templates grpo-rl-traininggit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-grpo-rl-training ~/.claude/skills/grpo-rl-training # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-grpo-rl-training ~/.agents/skills/grpo-rl-training # Codex, Cursor, Gemini CLI, Copilot, OpenCode