Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
安装
npx skills add davila7/claude-code-templates --skill torchforge-rl-trainingnpx skills add davila7/claude-code-templates --skill torchforge-rl-training -a claude-code -gnpx skills add davila7/claude-code-templates --skill torchforge-rl-training -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/post-training-torchforgegh skill install davila7/claude-code-templates torchforge-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-torchforge ~/.claude/skills/torchforge-rl-training # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/post-training-torchforge ~/.agents/skills/torchforge-rl-training # Codex, Cursor, Gemini CLI, Copilot, OpenCode