Professional skill that removes signs of AI-generated writing from text
Run and customize a complete hand-painted 2D action RPG chapter with manual combos, seven automatic skills, gems, equipment, ten rooms, a phased boss, saves and A/B training. Includes full source, local art, a ready-to-play build, reusable Agent Skill instructions and verification helpers.
This Skill is built on practical expertise in AI persona design, brand voice governance, character bible maintenance, dialogue QA, tone drift detection, and role-boundary review. It helps AI agents keep role, vocabulary, emotional range, relationship context, forbidden phrases, and channel fit consistent across support bots, sales assistants, companion bots, fictional characters, and long-running conversations.
Most ecommerce images lose the click before shoppers read the title: product too small, benefit unclear, flat angle, or a thumbnail that doesn't work. In ~1 year I grew to nearly 800K YouTube subscribers and 1.19M+ followers across platforms, so I know how fast people decide what deserves attention. I built that visual judgment into this AI Skill to help sellers make clearer hero images: stronger product focus, better composition, cleaner lighting, and selling-point text where allowed.
I build and run the web-scraping engine behind a production AI assistant. The hardest sites on the web — JavaScript-heavy apps, empty sitemaps, and content behind search forms — hand a normal crawler nothing but cookie banners. Over months I learned to make them give up clean data: render fully, find the hidden pages by search, dedup by stable IDs, and quality-gate every page so junk never reaches your dataset. I've distilled that pipeline into this Skill — self-healing and cost-capped.
Take your UE5 MetaHuman → Blender → Godot in a pipeline that actually works: skin/eye/hair materials, ARKit morph targets, and every gotcha documented so you don't rediscover them. Works great with https://github.com/ibrews/MetaHumanGodot