agentleFS
MelvynxMelvynx/ai-maxxing-skills/skills/create-landing/SKILL.md

create-landing

Skill32 starsChanged 24 days agoMITView on GitHub

Create a landing page, sales page or waitlist on Cloudflare with TanStack Start, shadcn/ui, a Lumail email form and an optional Stripe or Codeline buy button, no database or sign-in. Use when the user wants a landing, sales, waitlist, launch or lead magnet page.

  • Reads credentials
  • Installs packages
  • Sends data out

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you got this skill from a link instead of a local folder, install nothing else from the repo: fetch a file only when a step needs it, …

    line 11
  2. Distinctive:

    Keep this stack, with no Convex, no Better Auth and no database:

    line 13
  3. Very specific:

    Check access and fix what fails with the matching setup skill (setup-github, setup-cloudflare, setup-convex, setup-lumail, setup-node when …

    line 23
  4. Very specific:

    Run the grill-me skill in its landing mode and build only once the user confirms the brief.

    line 31
  5. Distinctive:

    Follow the 1 or 2 sites the user likes: one font pair, one accent color, generous spacing, mobile first, WebP images with width and height …

    line 35
  6. Very specific:

    If it sells, link the buy button to the Stripe payment link or the Codeline checkout with the success URL set to /merci.

    line 47
  7. Distinctive:

    Add analytics only if the user asks: one privacy-friendly script, nothing that needs a cookie banner.

    line 48

≈ “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

Build one fast page that turns visitors into emails or buyers, and put it live on the user's Cloudflare domain. Do every step yourself with the CLIs and only ask for what needs a human (a browser login, a payment link, a photo). Talk to the user in their language, short messages, no jargon. If the page needs accounts, a dashboard or saved data, switch to create-software; for a private tool, create-internal-app.

If you got this skill from a link instead of a local folder, install nothing else from the repo: fetch a file only when a step needs it, with curl -fsSL https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/create-landing/<path> -o <scratch>/<file>, and read another skill it names only when you reach it, from https://raw.githubusercontent.com/Melvynx/ai-maxxing-skills/main/skills/<skill-name>/SKILL.md.

Keep this stack, with no Convex, no Better Auth and no database:

  • Page, routing, form server function: TanStack Start (React, TypeScript, Vite), pages prerendered.
  • UI: shadcn/ui on Base UI + Tailwind CSS v4, lucide-react icons, sonner toasts.
  • Email form: TanStack Form + zod, a server function that calls the Lumail API.
  • Buy button, only if it sells: a Stripe Checkout payment link or the user's Codeline checkout URL.
  • Video, optional: a Tella embed from the URL the user pastes.
  • Hosting, domain, DNS: Cloudflare Workers with @cloudflare/vite-plugin, deployed with cf.
  • Code: Git and one private GitHub repo.
  1. Check access and fix what fails with the matching setup skill (setup-github, setup-cloudflare, setup-convex, setup-lumail, setup-node when npx is missing) first. When a login needs the browser, give the exact link or code and wait for "done".

    git --version && gh auth status       # GitHub
    cf --version && cf auth whoami        # Cloudflare (npm i -g cf, then cf auth login)
    npx lumail@latest auth test           # Lumail (npx lumail@latest setup --authenticate)
  2. Run the grill-me skill in its landing mode and build only once the user confirms the brief.
  3. Write the copy before the code, in the user's language and voice, and show it as plain text for a yes. Unless the brief says otherwise: hero (promise, sub-promise, call to action), the problem, the solution, what they get, proof, offer and price, FAQ for the objections, final call to action, footer with legal links. Use only the testimonials, numbers and deadlines the user gave, or leave a clear placeholder.
  4. Scaffold TanStack Start + Tailwind + npx shadcn@latest init (Base UI flavor) with only the components you need. git init, then gh repo create <name> --private --source . --push.
  5. Build / from the sections, plus /merci (after signup or purchase) and /mentions-legales or /legal, all prerendered, each with a real <title>, a meta description, an Open Graph image (1200x630) and a favicon. Keep one page, one goal, one call to action repeated, and no menu that leads visitors away.
  6. Follow the 1 or 2 sites the user likes: one font pair, one accent color, generous spacing, mobile first, WebP images with width and height set, no layout shift, no heavy animation library.
  7. Build the email form with TanStack Form + zod on the client and a createServerFn that posts to Lumail. Create LUMAIL_API_KEY yourself with lumail tokens --help; it stays a Cloudflare secret, never in a committed file or the browser.

    await fetch("https://lumail.io/api/v1/subscribers", {
      method: "POST",
      headers: { Authorization: `Bearer ${process.env.LUMAIL_API_KEY}`, "Content-Type": "application/json" },
      body: JSON.stringify({ email, tags: ["<page-slug>-lead"] }),
    });

    Keep double opt-in on, since a landing form is cold and the email is not verified. Add a hidden honeypot field, reject empty or fake emails on the server, and go to /merci after a success. If the brief asks for a welcome email or lead magnet, create the tag workflow with the lumail skill.

  8. If it sells, link the buy button to the Stripe payment link or the Codeline checkout with the success URL set to /merci. Never collect card details on the page.
  9. Add analytics only if the user asks: one privacy-friendly script, nothing that needs a cookie banner.
  10. Deploy on Cloudflare. wrangler.jsonc gets main: "@tanstack/react-start/server-entry", compatibility_flags: ["nodejs_compat"] and the custom domain in routes with custom_domain: true. Set LUMAIL_API_KEY as a Cloudflare secret, then build and deploy with cf (cf build, cf deploy, or cf cli search "deploy worker"), never by hand in the dashboard; see the cloudflare skill. If the domain is not in the user's Cloudflare account, tell them to move the name servers or buy it there.
  11. Prove it on the live URL: every section shows on desktop and at phone width with no horizontal scroll, every link and button works, a real email signup lands on /merci and shows up in Lumail with the right tag and its confirmation email arrives, the buy button opens the right checkout and price, Lighthouse on mobile scores 90 or more in performance and accessibility, and a chat link preview shows the title, description and image. Fix every error you see before saying it is live.

Reply with the live URL, the Lumail tag the signups get, and what is left to do.

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.