This open-source training playbook locks down all three fine-tuning paths — supervised fine-tuning, preference alignment, and reward scoring — plus the LoRA parameters, pairs with Unsloth, and runs on a consumer GPU with just 8GB of VRAM.
pols.dev ships a ~87KB Markdown rulebook naming AI UI tells and positive recipes. Install by agent path, or download the file—not a website generator.
One core skill, 23 design commands, an anti-pattern list, plus CI-ready slop detection. The main site shows the workflow; /slop lays out the "looks AI-made" UI tells.