agentleFS
ghazanfar111212ghazanfar111212/claude-skills-performance-marketing/skills/landing-page-visual-standards/SKILL.md

landing-page-visual-standards

Skill0 starsChanged 38 days agoMITView on GitHub

A strict visual quality bar and design systems for building landing pages that don't look AI-generated. Use whenever building, designing, or redesigning any landing page, funnel page, or lead-gen page - always load this TOGETHER WITH landing-page-designer (conversion structure) and frontend-design (visual craft). This skill supplies the banned-defaults list, approved design systems, the signature-element rule, conversion non-negotiables, and GHL build constraints. Trigger on "landing page", "lead gen page", "funnel page", "make it convert", "looks like AI made this", or any page built for paid ads or outbound campaigns.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check every choice against the banned list below: If any banned pattern survives, the page fails regardless of how it converts on paper.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Landing Page Visual Standards

Personal quality bar for landing pages. landing-page-designer decides WHAT goes on the page (sections, offer, form). This skill decides HOW it looks - and what it must never look like.

Process (mandatory order)

  1. Declare the signature element before writing any code. Every page gets ONE memorable, subject-specific visual device that dramatizes the visitor's problem or the offer (e.g., the "NOT CITED" stamp on an AEO page, a before/after slider for hardscaping, a live cost counter for ads-waste offers). State it in one sentence. If you can't name one, don't start building - think longer.
  2. Pick a design system from DESIGN-SYSTEMS.md or derive a new one FROM THE SUBJECT's world (its materials, tools, vernacular). Never default to a system because it's easy.
  3. Check every choice against the banned list below. If any banned pattern survives, the page fails regardless of how it converts on paper.
  4. Build, then self-critique against CHECKLIST.md before presenting.
  5. Study examples/aeo-evidence-file.html - this is the approved standard for tone, density, and craft.

Banned defaults (instant fail)

  • Inter, Roboto, Open Sans, Lato, or system-stack-only typography
  • Generic blue (#2563EB-family) or purple CTAs; purple-to-blue gradients anywhere
  • Three rounded-corner cards with icons in a centered grid
  • Everything center-aligned; symmetric hero with text-left/image-right stock layout
  • Gradient blobs, glassmorphism, floating 3D shapes, mesh gradients
  • Stock photos: smiling headset people, laptop-at-café, generic "team" shots
  • Emoji in headlines or section titles
  • Soft drop-shadows on white cards as the only depth device
  • "Welcome to", "We are a leading", "Unlock/Supercharge/Elevate your" copy
  • The three flagged AI-default looks: cream #F4F1EA + serif + terracotta #D97757; near-black + acid green; broadsheet hairline-grid with zero radius everywhere
  • Fake proof: invented client logos, made-up stats, fabricated testimonials. Claims must be defensible or absent.

Conversion non-negotiables

  • ONE saturated CTA color on the entire page; it appears nowhere except CTAs. Contrast isolation beats color psychology.
  • Same single offer repeated 3x (hero, mid-page offer block, final form) + sticky mobile CTA bar.
  • Form: ≤4 fields; one qualifying dropdown (industry/budget) that doubles as niche-signal data.
  • Cold-traffic friction removal: "no call required / no card / no obligation" framing near every CTA.
  • Headline = outcome + specificity, message-matched ≥70% to the ad it receives traffic from.
  • Mobile-first: single column, ≥16px body, 44px tap targets, CTA visible without scroll.
  • Motion: max 2 living details (typing effect, ticker, reveal), all respecting prefers-reduced-motion.

GHL deployment constraints

  • Deliver as ONE self-contained HTML file: inline CSS, one Google Fonts link tag, vanilla JS only.
  • Mark the form with a comment <!-- GHL FORM EMBED SLOT --> so the native form/pipeline embed can replace it.
  • Structure top-level blocks so each maps to a GHL section; note in the handoff that typography-heavy designs go in custom-code sections, not the drag-drop builder.
  • Thank-you step fires pixels (GA4 + Meta), never the page load.

Deeper references

  • Approved palettes & font pairings: DESIGN-SYSTEMS.md
  • Pre-delivery self-critique: CHECKLIST.md
  • Gold-standard example: examples/aeo-evidence-file.html

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.