Slop*Detector

SUSPICIOUSLY VIBEY — slop score 56/100

The hero alone gives this away, with an amber 'Jellyfin plugin' pill floating above a gradient-clipped headline and 'Now in beta' sitting in the exact spot every AI-generated landing page puts its badge. Pair that with the 'X, not Y' reframe showing up three separate times and the kicker-headline-blurb rhythm repeating section after section, and you've got a template someone ran through a model rather than a human laying out a page by hand. Still, the product copy holds up better than the chrome around it: the feature grids list specific behaviors like 'Retries with judgment' and 'TV sync just works' instead of generic filler, and the three-item lists name real failure modes such as 'an offline watch, a skipped episode, a restart mid-file' rather than marketing triads. At 56, this reads as a developer who built a working plugin and then ran the marketing page through an AI generator without touching the defaults, not a site invented wholesale by a model. Confidence in that read is moderate, since the structural tells are consistent and plentiful but the substance underneath them is too specific to be pure slop.

Findings

• Pill tags — Little fully-rounded pill badges sprinkled across the page ("New", "Beta", category chips) are a default garnish of vibe-coded UI.
• Announcement pill above hero — A small rounded badge floating above the h1 ("✨ Now in beta →") is the canonical AI-generated hero opener.
• Gradient backgrounds / gradient text — Large gradient washes and gradient-clipped headline text (usually blue→purple) are the default decoration of generated UI.
• Repeated kicker + headline + blurb hierarchy — Several sections follow the exact same three-level pattern: small all-caps kicker label, oversized serif headline, two-line explanatory paragraph. This rhythm repeats almost verbatim across the page.
• Feature-tile-style grids — Two separate 3-across card grids present bold subheader + two-line blurb per card, the shape the scanner treats as a feature-tile tell, though the copy itself is unusually specific rather than generic filler.
• Scattered pill-shaped badges — Numerous small fully-rounded status/label chips are scattered through the hero and sections. Some are legitimate live-status indicators, but their density across the page still matches the pill-proliferation pattern.
• Warm amber accent as a possible default palette — The entire site leans on a single gold/amber accent against near-black, which the guide flags as an emerging 'tasteful default' alongside indigo and emerald, though here it's applied consistently enough to read as an intentional brand choice rather than an unexamined default.
• One/two-word punch sentences — Single dramatic words dropped as their own sentence ("Done." "Gone." "Period.") are an LLM emphasis habit, not a human one.
• Announced sincerity — Flagging your own honesty ("honestly", "real talk", "the honest truth") manufactures sincerity instead of earning it.
• "X, not Y" reframe construction — The banned appositive/contrast reframe appears three separate times across the page, which is the kind of repeated rhetorical tic the guide flags even when each instance is short.
• Faux-subtle 'quietly' phrasing — Describing resilience as happening 'quietly' is the softened, falsely-profound analyst voice the guide warns about, even though it's a minor single instance.
• Short demonstrative payoff closer — "That's it" functions as the tacked-on demonstrative payoff sentence the guide calls out, though it's used sparingly and fits the casual instructional tone.
• Recurring rule-of-three lists — Several three-item lists appear across sections; the items are concrete and technical rather than generic marketing triads, but the frequency is worth noting.