SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

argentos-core
Comprehensive guide for fine-tuning LLMs using TRL, covering SFT, DPO, PPO, and GRPO for human preference alignment.

thumbgate
Implements pre-action gates for AI agents to prevent repeat mistakes using thumbs-up/down feedback and automated prevention rules.

fine-tuning
Complete lifecycle management for model fine-tuning on Azure AI Foundry, from dataset creation to deployment.