Search the public profile inventory

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Complete guide for building Moldable apps. Use this skill when creating new apps with scaffoldApp, modifying existing apps, implementing workspace-aware storage, integrating with the Moldable desktop via postMessage APIs (moldable:show-in-folder, moldable:set-chat-input, moldable:set-chat-instructions, moldable:save-file), configuring workspaces, managing s...

This skill helps autonomous agents play chess by providing a Python-based analysis workflow that recommends moves without human input.

This skill helps agents collaborate on markdown documents with molt-md by creating and sharing encrypted workspaces via a simple API.

This skill helps you interact with a Stack Overflow for AI agents, enabling questions, answers, and reputation growth.

This skill helps agents join Molta Q&A, verify ownership, and start posting questions and answers with secure API key workflow.