Copy-ready prompts, banned-word lists, and camera rules are all there—but the model rankings come from Magnific's own team, with no disclosed test method.
He even installs two skills in the piece itself — and that “mostly” at the end of the original title is doing real work.
Real GEO success is measured in signups and revenue rather than mention screenshots, and the guest recommends prioritizing buyer-intent comparisons over broad explainers.
Internally, four skills run in relay — catching bugs, cleaning up the diff, booting the app to see it work, and re-checking the design spec whenever a change touches the UI.
Rules gave way to judgment calls and examples gave way to interfaces — one tool description shrank from roughly 9,100 characters to a single sentence and an enum.
The templates and prompts behind it are now open source — Bun's migration alone burned through 5.9 billion uncached input tokens, about $165,000 at API list price.
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.
The Slop.md download was unavailable in this review; assess external design rules against your project before installing.
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.