agentleFS
MithunWijayasiriMithunWijayasiri/dotclaude/skills/html-landing-page/SKILL.md

html-landing-page

Skill4 starsChanged 18 days agoMITView on GitHub

Static landing pages — single/few-file HTML/CSS/JS for project sites, GitHub Pages, product one-pagers. Build, redesign, or review. Layers on frontend-design; not for app UIs, dashboards, or framework SPAs.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Mine the project: Read real material first: files, structure, vernacular, concrete numbers, command strings.

    line 28
  2. Distinctive:

    Verify copy: Check every factual claim against project source.

    line 36
  3. Very specific:

    All motion inside @media (prefers-reduced-motion: no-preference).

    line 63

≈ “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

HTML Landing Page

Landing-page layer on top of frontend-design:frontend-design.

Precedence

  • Invoke frontend-design:frontend-design via Skill tool first, unless already loaded this session. It owns: grounding, plan → self-check → build → critique passes, AI-default looks, typography, motion budget, copy voice, general quality floor, screenshot critique.
  • This file adds only static-landing-page specifics. frontend-design updates far more often than this file → never restate or override its guidance here.
  • Conflict on design taste → frontend-design wins. Conflict on landing-page constraints (checkpoint, copy verification, assets, deploy, Quality floor below) → this file wins.
  • Editing this skill: before adding a rule, check frontend-design doesn't already cover it; delete rules here once it does.

Modes

  • Build — new page → full Process.
  • Review — existing page → audit against frontend-design's AI-default list, Landing-page tells, Quality floor, copy accuracy (Process step 6). Report findings, most severe first. Wait for go-ahead before changing anything.
  • Redesign — Review, then run Process only on what failed; keep what passes.

Process

Runs inside frontend-design's passes; adds these steps.

  1. Mine the project. Read real material first: files, structure, vernacular, concrete numbers, command strings. Distinctive choices come from the subject's own world.
  2. Extend the plan. Beyond frontend-design's token plan, add:
    • Signature: the ONE element the page is remembered by; must embody something true about the subject.
    • Contrast: every text/bg pair ≥ 4.5:1 (body), ≥ 3:1 (large text, UI). Distinctive palettes fail this most often.
    • Theme: light-only, dark-only, or follows prefers-color-scheme. State it — otherwise it gets decided by accident.
  3. Checkpoint. Show plan (palette, type, layout sketch, signature, theme); wait for approval before writing HTML. Skip only if user said to build without review. Plan changes are cheap; built-page changes aren't.
  4. Build to the approved plan.
  5. Render. Open page in a browser; screenshot at ~375px and ~1280px; check console for errors. Judge screenshots, not source — overflow, spacing, and specificity bugs only show rendered.
  6. Verify copy. Check every factual claim against project source. Plausible-but-false → cut.

Landing-page tells

Additions to frontend-design's AI-default list; same rule — use only when the brief asks.

  • Same skeleton every time: centered hero → 3 feature cards → CTA band.
  • Bento-grid feature sections.
  • "Trusted by" logo strips; invented testimonials or user counts (also fail step 6).
  • Purple-blue gradients, gradient text, glassmorphism.
  • Glowing blurred blobs behind hero; dotted-grid or noise-texture backgrounds.
  • Emoji as feature icons; decorative sparkle/rocket emoji anywhere.
  • Scroll reveal on every section.

Copy

frontend-design owns voice. Additions:

  • Specific > clever: real numbers, names, and file/command strings from the project.
  • Banned slop: Unleash, Elevate, Seamless, Effortless, Supercharge, Empower, Revolutionize, "Built for the modern web".

Quality floor

Build silently, never announce.

  • Body never scrolls horizontally; wide code/tables scroll in own overflow-x: auto container.
  • aria-label on figure-like code blocks.
  • All motion inside @media (prefers-reduced-motion: no-preference). No JS / no IntersectionObserver → all content visible (content starts visible; JS hides it pre-reveal).
  • <title>, meta description, favicon (inline SVG or emoji data URI), og tags. og:image = absolute URL to a real image (~1200×630); relative URLs break link previews.
  • Self-contained assets: inline SVG, data URIs; no icon/JS CDNs. Google Fonts is the only allowed external.
  • Fonts: preconnect to fonts.googleapis.com and fonts.gstatic.com (crossorigin), display=swap, request only weights actually used.
  • Relative asset paths only. GitHub Pages project sites serve from /<repo>/ → root-absolute /style.css 404s.

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.