Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseOpenClawOpenClaw+21 more

    Escape AI Slop — A Layout Reasoning Guide

    1

    It doesn't write layout code by itself — it reshapes how your agent thinks about layout before it writes any code, wherever that code gets written.

    $15

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned
    Escape AI Slop — A Layout Reasoning Guide

    Escape AI Slop — A Layout Reasoning Guide

    Example session with this skill installed

    Here's our current Hero section for LOOP THREAD (screenshot attached). It reads clean, but a little generic. Before we touch any code, critique it against eye-tracking layout models and cognitive biases, and sketch 3 structurally different directions in plain text — no code yet, I want to pick a direction first.

    Current markup

    • Left: square-ish product photo (~600px)
    • Right: eyebrow label ("Traceable Everyday Basics") → H1 ("Honest thread from seed to garment") → body copy → two CTAs ("Explore the Collection" / "Trace supply chain")
    • White background, roughly 60/40 image-to-text split
    • Read your context and instructions
    • Compiled the escape ai slop
    • Generated the UI component

    Reading the current state first

    • Structure: image-left, text-right, roughly 60/40 — if I described this out loud as "photo on one side, copy and buttons on the other, split down the middle," that description alone is the tell. A topology model may have been intended, but nothing forces the DOM to prove it; this is the default split most agents converge on without deciding to.
    • Color: background is white. That's already the right call under a white-first default — no fix needed here.
    • Cognitive bug risk: both CTAs live together in the one spot every visitor expects a CTA to be — the hero. Nothing below the fold echoes them. That's banner-blindness territory: the exact zone visitors have learned to tune out is the only place asking them to act.

    Three structurally different directions (plain text, no code):


    Direction 1 — Bottom-anchored, photo-led

    ┌──────────────────────────────────┐
    │  Traceable Everyday Basics        │
    │  Honest thread, quietly told.     │
    │  [Explore]  [Trace supply chain]  │
    ├────────────────────────────────────┤
    │                                      │
    │   FULL-BLEED PRODUCT PHOTOGRAPH     │
    │   (edge-to-edge, cropped by the     │
    │    fold — carries the full weight)  │
    └────────────────────────────────────┘
    

    Quiet copy up top, a single large photograph doing all the visual work at the bottom of the first screen. Fits a brand whose whole pitch is "look at the supply chain" — the photo is the proof, not a decoration next to the proof. Bonus: the CTA row now sits above a hard visual break instead of floating in "the usual hero corner," which softens the banner-blindness risk from the current version.

    Direction 2 — Offset, overlapping

    ┌──────────────────────────────────┐
    │ Traceable Everyday Basics          │
    │ Honest thread          ┌────────┐ │
    │ from seed to     ┌─────┤ PHOTO  │ │
    │ garment.         │PHOTO│ (bleeds│ │
    │ [Explore][Trace] └─────┤ off    │ │
    │                         │ edge)  │ │
    └─────────────────────────┴────────┘
    

    Same zigzag idea as the current split, but the photo overlaps the text block and bleeds off the right edge instead of sitting in its own clean column. The asymmetry and overlap are what make it read as designed rather than assembled — a straight 50/50 (or 60/40) division never does.

    Direction 3 — Single-column, punctuated

    ┌──────────────────────────────────┐
    │      Traceable Everyday Basics    │
    │    Honest thread from seed        │
    │       to garment.                 │
    │   [Explore]   [Trace supply]      │
    ├────────────────────────────────────┤
    │       FULL-BLEED PHOTO BREAK        │
    ├────────────────────────────────────┤
    │   (traceability story continues     │
    │    down a single centered column)   │
    └────────────────────────────────────┘
    

    Centered, narrow, one statement at a time — a full-bleed photo interrupts the column rather than sitting beside it. Matches the "basics, nothing extra" brand voice more literally than a side-by-side layout does.


    One cross-cutting note regardless of which direction you pick: add at least one inline CTA further down the page (e.g. after the Traceability Index teaser) so the hero pair isn't the only ask on the page — that's the concrete fix for the banner-blindness risk flagged above.

    No code was touched. Pick a direction (or mix elements from more than one) and it gets implemented from there.

    escape-ai-slop-a-layout-reasoning-guide.tsx

    TSX · React component

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    What you get

    Get a plain-text critique of an existing layout — three structurally distinct alternative directions with ASCII sketches, no code written until you choose one.Break your agent's habit of defaulting to the same centered-hero / 50-50-split "AI slop" layout, regardless of what the brief actually calls for.Get genuinely different structural variations — not just recolors — when you ask for multiple layout options, enforced by a topology-model + rendering + axis system that catches convergence before code is written.Apply concrete countermeasures for real cognitive biases (banner blindness, tunnel vision, the gestalt/proximity trap) at specific, named spots in your layout.Break the reflexive "safe nuance palette" habit with a white-first default and a color-theory-driven combination choice, instead of reaching for cream/sand/terracotta on autopilot.

    About this skill

    This is a reasoning guide, not a generator. It doesn't write layout code by itself — it reshapes how your agent thinks about layout before it writes any code, wherever that code gets written. Use it standalone to critique an existing layout in plain text, or layer it onto your own mockup/LP-building workflow so every generation benefits.

    Left unchecked, a text-based agent defaults to whatever layout is statistically "safest": a centered hero, a symmetric 2-column split, a cream/sand/terracotta background — the pattern now widely recognized as "AI slop." This skill exists to break that reflex by reinterpreting real eye-tracking physiology and cognitive biases as concrete structural constraints.

    What it does

    • Applies four eye-tracking topology models (Z-pattern, F-pattern, I-pattern, bottom-up) as DOM-level structural constraints, not just visual styling
    • Forbids each model's own "reflex rendering" (e.g. Z-pattern always becoming alternating image-left/right rows) and requires picking from genuinely different alternatives
    • Varies density, image treatment, and typographic voice as independent axes, so multiple layout options never converge on "the same design with different colors"
    • Counters three specific cognitive biases — banner blindness, tunnel vision, the gestalt/proximity trap — with named countermeasures at concrete spots in the layout
    • Breaks the "safe nuance palette" reflex: white is the default background unless the brief gives a real reason otherwise, and color combinations are chosen deliberately from color theory (complementary, analogous, triadic, split-complementary, monochromatic, achromatic + accent)
    • When multiple options are requested, sketches one extra candidate internally and prunes the weakest before any code is written — a selection, not just the first ideas that came to mind

    Two ways to use it

    1. Standalone: paste or describe an existing layout and ask for a critique, or for plain-text alternative directions with ASCII sketches — no code until you pick one. Nothing else needs to be installed.
    2. Layered onto your own workflow: if you already generate mockups or landing pages some other way, this skill's reasoning kicks in automatically on a layout request and shapes whatever gets built.

    Also covers

    Retrofitting a single section of an already-working page (spend the structural accent only where it matters, leave proven conventional patterns alone elsewhere), and mobile-primary briefs (Z/F-pattern's left-right alternation has nowhere to go on a narrow viewport, so the model pool correctly narrows instead of forcing a desktop pattern into a single column).

    Requirements

    A Claude Code agent. No dependencies, no Figma, no MCP server. Makes no file, network, or terminal calls of its own — it only reshapes reasoning; any file writes happen wherever the layout is actually built.

    More from KMRVID

    The full Claude Code skill bundle for Figma, Tailwind and Astro workflows is available on Gumroad: https://gaspanik.gumroad.com/l/kmrvid-claudeskills

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean today

    • Passed all security checks, Safe to install

    Listed1 day ago

    What's inside

    Frequently Asked Questions