# ml-training-recipes > Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discove… Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput. - Type: Skill - Made by: Orchestra-Research - Category: AI & agents - Formats: Skills - Version: 7c0517a - Source: https://github.com/orchestra-research/ai-research-skills/tree/HEAD/10-optimization/ml-training-recipes - Page: https://pluginboard.ai/skills/ml-training-recipes ## Works with - ChatGPT - Claude - Gemini - GitHub Copilot - Cursor - Claude Code - Codex - Antigravity - Gemini CLI - Replit - OpenClaw - OpenCode - Hermes Agent ## Install ### ChatGPT In ChatGPT: Download the ml-training-recipes folder and zip it, then Plugins → Skills → Create → Upload from your computer. Business and Enterprise plans. View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Claude In Claude (web or desktop): Download the ml-training-recipes folder and zip the folder itself, then upload it in Customize → Skills. View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Gemini In Gemini: Download the ml-training-recipes folder, then at gemini.google.com click Customize → Skills → Create → Upload and pick the folder (or a .zip of it). View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### GitHub Copilot Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.copilot/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Cursor Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.cursor/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Claude Code Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.claude/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes Or all of AI Research Skills (Orchestra), in Claude Code: ```text /plugin marketplace add Orchestra-Research/AI-Research-SKILLs /plugin install rag@ai-research-skills ``` ### Codex Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.agents/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Antigravity In Antigravity: Copy the ml-training-recipes folder into ~/.gemini/config/skills (Antigravity app and IDE) or ~/.gemini/antigravity-cli/skills (Antigravity CLI). View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Gemini CLI Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.gemini/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Replit Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes .agents/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### OpenClaw Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.openclaw/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### OpenCode Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.config/opencode/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes ### Hermes Agent Run in your terminal: ```shell npx -y degit Orchestra-Research/AI-Research-SKILLs/10-optimization/ml-training-recipes ~/.hermes/skills/ml-training-recipes ``` View the folder on GitHub: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/HEAD/10-optimization/ml-training-recipes --- From Pluginboard (https://pluginboard.ai).