Your AI built it. We make it look designed.
Paste your URL at launch and get a Slop Score, plus a FIX.md your own AI tool uses to repair exactly what's wrong. Join the waitlist and your site gets scored first.
From URL to FIX.md
Scan.
We render your page and run it against a catalog of concrete AI-slop tells, from purple gradient heroes to fake stat rows.
Score.
You get a 0-100 score across six categories: color, typography, layout, components, copy voice, authenticity. Deterministic checks, not vibes: same URL, same score.
Fix.
The full audit ships a FIX.md tailored to your site. Drop it into Cursor, Claude Code, Lovable or Bolt. Your own tool fixes your page.
What a report looks like
Three sites, three different looks. The fixes remove machine defaults, not style: what you chose on purpose stays.
- ColorHigh
Indigo-to-violet gradient on every surface
Why: The scan found nine gradient declarations: hero, logo, buttons and stat numbers all wear the same stock indigo-to-violet ramp every AI scaffold ships with. It signals 'template', not 'product'.
Fix: One solid accent, chosen on purpose. Flatten the hero to a single surface and let type carry it.
- AuthenticityHigh
Fabricated stat row
Why: Happy-user counts, uptime nines and round-the-clock support claims on a page for a product nobody has used yet. Unverifiable numbers destroy trust on first read.
Fix: Delete the row. Replace it with one true, specific sentence about what the product does today.
- TypographyMedium
Gradient-clipped headline
Why: The headline is painted white-to-violet instead of being allowed to rank. Decoration where hierarchy should do the work.
Fix: Solid ink, tighter tracking, one clear size jump between H1 and body.
## Fix 1: Hero surface
Swap the indigo-to-violet ramp on body and .hero for one solid
background. Keep a single accent (#2456F6) for buttons and links.
NEVER: reintroduce stacked gradients, glass panels, or glow shadows.An excerpt. The full FIX.md turns every finding into a directive your tool can run: what to change, what to preserve, how to verify it worked.
Pricing
Free
$0
Slop Score, category breakdown, top 3 findings, shareable score card.
Full Audit
$29 one-time
Every finding with before/after, a tailored FIX.md, one re-audit to verify.
No subscription.
FAQ
What exactly do you mean by “slop”?
The defaults nobody chose: the stock purple gradient, the glass cards, the invented stat row, the filler adjectives every AI tool ships when you don't push back. Slop is not a verdict on your taste. It is the absence of decisions, and it makes real products look like templates.
What do you check, and how long does it take?
A scan renders your page and runs a curated catalog of concrete checks across six categories: color and gradients, typography, layout and spacing, components and effects, copy voice, authenticity. Each finding deducts points by severity and visibility. A scan takes about a minute.
Do you store my code?
No. There is nothing to hand over: you give us a URL, we render what's publicly reachable, like any visitor's browser does. No account, no access, no code.
Is this a human review?
The scan is automated so it stays fast, cheap and repeatable. What it checks is not: every rule in the catalog was written and calibrated by a designer, and the paid audit only keeps findings that survive strict evidence rules. No vibes, either way.
Do you redesign my site?
No. We diagnose and write the recipe. The FIX.md is applied by your own AI tool, so the changes land in your codebase, in your style, under your control. We never touch your site.
What if my page can't be scanned?
You only pay after a successful scan. If a paid run fails anyway, you get an automatic refund.
Which tools does FIX.md work with?
Any agent that reads markdown: Cursor, Claude Code, Codex, Lovable, Bolt, v0.
Who's behind this?
Built by an indie dev who ships his own apps, and got tired of seeing good products look generic.
Will this make my site look minimal?
No. Fixes remove machine defaults, not style. If you chose a look on purpose, it stays. Every fix is anchored to your existing palette, type and voice; only the concrete slop tells always go: fabricated stats, gradient spam, badge noise. A playful site stays playful.
Is a score of 100 the goal?
No. 100 means the page follows every rule in the catalog, not that it's a perfect site. It is reachable, and that's deliberate: the score counts concrete, checkable defaults, so a page with zero of them scores 100. A memorable site sometimes breaks a rule on purpose, takes the point hit, and is better for it.