DPO skills

Orchestra-Research/AI-Research-SKILLs

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

TYH-labs/unsloth-buddy

Skill Claude CodeCodex

This skill should be used when users want to fine-tune language models or perform reinforcement learning (SFT, DPO, GRPO, ORPO, KTO, SimPO) using the highly optimized Unsloth library. Covers environment setup, LoRA patching, VRAM optimization, vision/multimodal fine-tuning, TTS, embedding training, and…

liortesta/ClawdAgent

Skill Claude CodeCodex

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

lamenting-hawthorn/SkillLoop

Skill Claude CodeCodex

Patterns and constraints for tasks running as Hermes scheduled cron jobs. Covers restricted tools, output delivery, and proven workarounds.

lamenting-hawthorn/SkillLoop

Skill Claude CodeCodex

The /goal pattern: cron jobs that run until an objective condition is met, checked by an independent model (maker/checker split). Source: loop engineering framework by 0xCodez / Anthropic evaluator-optimizer pattern.

lamenting-hawthorn/SkillLoop

Skill Claude CodeCodex

Gate before creating any cron job: run the 4-condition test + 30-second checklist to determine if loop engineering is worth the token cost. Source: 0xCodez loop engineering framework (June 2026), Anthropic engineering docs, Addy Osmani.