Takes any image and either beautifies it to marketing perfection or shows what it really looks like in daily use, depending on what you feed it. The skill analyzes whether your input is already idealized (renders, ads, promotional shots) or shows real-world wear, then generates the opposite. Works across domains like architecture, food, products, portraits, travel spots. You can also get side-by-side comparisons with that clean split-screen look. It maps five universal dimensions (lighting, materials, color, atmosphere, composition) to domain-specific expressions, so a tired apartment render gets the harsh fluorescent truth while your grainy phone photo gets the developer's promise treatment. Honestly just a systematized way to generate expectation versus reality memes with actual visual intelligence.
npx skills add https://github.com/lionad-morotar/anti-render-skill --skill anti-render