agentleFS
delphinelil09-sysdelphinelil09-sys/universal-design/design-promo/SKILL.md

design-promo

Skill3 starsChanged 49 days agoMITView on GitHub

Landing page / promo site lens. Use when the site's purpose is to convince and convert — landing pages, product launches, service promos, event pages. Load after design-core has established why the site exists and confirmed the goal is sale or signup. Does not replace design-core; adds subtype-specific priorities, typical failures, layer-by-layer guidance, and audit specifics. For subscription software (SaaS), design-saas replaces this lens.

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:

    If the composition puts anything else in the top 3, revise it.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Design Promo — Landing Pages

A subtype lens for design-core. Load this after design-core has run its three entry steps and confirmed the goal is sale, signup, or conversion.

This file does not redefine the eight elements, the four layers, the two modes, or the two phases. It only adds what is specific to landing pages.

Focus

The first screen is a promise: what this is, who it's for, why it matters — understood within 3 seconds. Everything below the first screen is proof and path. The gaze moves promise → proof → action.

Marketing leads by default when the goal is sale. See design-core/references/marketing.md. Air serves focus, not beauty.

Typical failures

  • Multiple equal CTAs. The eye doesn't know where to go. Fix: one primary, everything else visibly subordinate.
  • First screen about the company, not the visitor. "We are..." instead of "You get...". Fix: rewrite from the visitor's side.
  • Proof buried at the bottom. Trust must appear where hesitation appears, not after it.
  • Broken mobile. Landing pages are read on phones first. A desktop-first hero fails on arrival.
  • Decorative hero. A beautiful image that promises nothing. Fix: make the hero carry the promise, not sit behind it.

Layer-by-layer

Frame (composition, space). The composition follows the gaze path — Z or F, chosen deliberately. Space groups blocks: tight space clusters related ideas, wide space separates them. The first screen owns the strongest composition on the page.

Body (form, color). Color carries trust or energy depending on the subject. Button forms are large and obvious — primary button visibly dominates secondary. One accent color, used almost exclusively for the primary CTA.

Surface (texture, typography). Typography is readable, not decorative. The headline is a real headline, not a slogan in display weight. Body text stays plain so proof (numbers, testimonials) can be scanned.

Accent (point, line). Icons and dividers support comprehension, not fill space. Every icon earns its place by helping the visitor understand something faster.

Reading order

The landing page has one reading order and it does not vary by taste:

  1. Promise (first screen)
  2. Proof (why you can be trusted)
  3. Path (the one action)

If the composition puts anything else in the top 3, revise it.

Audit specifics

Beyond the common grid, these are the landing-page breakages to hunt:

  • Space → Frame → the hero asks for attention in six places (headline, subhead, two CTAs, image, logos) → one job per hero; the promise owns it.
  • Typography → Surface → the headline is a slogan about the company, not a promise to the visitor → rewrite from the visitor's side (see design-core/references/copy.md).
  • Point → Accent → icons decorate instead of explain → remove every non-functional icon.
  • Color → Body → accent spread across links, badges, and borders erases the CTA → accent belongs to the primary action.
  • Line → Frame → proof buried below trust-breaking sections → where hesitation starts, proof answers.

Return to core

For the method (three entry steps, modes, phases, error handling), see design-core/SKILL.md. For the marketing filter, see design-core/references/marketing.md. For the layers protocol, see design-core/references/layers.md.

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.