Procreate Style OG Image: Image Skill for Claude Code

A black ground with the small name Pigmora and a heavy white two-line headline at the top center and tilted tablets and phones around it full of bright low-poly and paper-cut artwork

Runs in

Install guides

Claude Code Cursor

Generates with

Host Agent LLM

Uses tools

FAL

Similar Skills

View all

A near-black grid with the green Supabase bolt, a two-line Launch Week 12 invite and a spaced monospace date at the left and a tall dark ticket card with a numbered code query and ticket response at the right

Supabase Style OG Image

Pale grey Apple share card with five iPhones fanned out, the center one showing a 9:41 lock screen over a coastal landscape

Apple Style OG Image

Plaid Style OG Image

Headspace Style OG Image

What you get

One 16:9 WebP card with floating screens on black, your brand and headline spelled letter for letter
The exact prompt it sent plus the saved FAL task file; rerunning resumes that request rather than buying a new one
A review of spelling, the 6% safe margin and the 16:9 frame before the card reaches you

Good fit

Drawing, painting and design apps
Releases that span tablet and phone
A name and, at most, one short line

Not for

Bright, airy or minimal identities
Products with no screen worth showing
Copying screens from an app that exists

Social mediaProduct launchMake an OG imageog imagesocial cardcreative appsdevice mockupdark

Good forMake an OG image

About this Skill

You say/ours-procreate-style-og Launch card for Lumaquill, a watercolor painting app for tablets and phones. Headline: "PAINT ANYWHERE". Keep the screens colorful.

Everything happens on a pure black ground. Your name runs large in white across the upper part, and between four and six tablets and phones hover around it, some cut off by the edges of the frame. Each screen pairs saturated artwork, a sketch or a chart with dark tool panels: brush lists, sliders, color wheels. The agent decides what every screen shows, so the gallery reads as your app and nobody else's, and GPT Image 2 on FAL renders the 16:9 WebP. Your brand and headline are checked one letter at a time before you receive it.

How it works

Agree on the name, one headline and one picture idea; drop anything that blurs at thumbnail size
Lay out the card from references/visual-system.md and fit your colors to its four style anchors
Strip out outside names, marks, faces, screens and slogans, then invent the artwork and tool panels on each screen for your brand
Write a prompt about visible things only: frame, layout, light, palette, subject and type position
Send one request with the bundled FAL helper and keep the task file it writes
Read each letter, check the 6% margins and the 16:9 frame, and only then run validate-output.mjs
If a flaw remains, propose one prompt change and wait for your OK before a second paid request

Checked before delivery

validate-output.mjs passes with --require-format webp --require-16-9, and the prompt file has no emoji, arrows or symbol characters
Brand and headline read correctly letter by letter, with key text and faces inside a 6% margin on every side
Every source name, logo, slogan, person, interface and watermark is replaced by the user's own identity or a new one, and the layout is new for this subject
Exactly one paid request per approved generation

What you need before you start

You bring: Brand or project name, spelled as it should appear on the card · One short headline · What the page, product or audience is · Optional: brand colors, a logo the user may use, a mood, owned reference images, a platform safe zone
Dependencies: Node.js 20+ to run the included FAL script · Your own FAL API key, set as FAL_KEY; FAL charges for each image
Outside costs: FAL_KEY
Last tested: v0.1.0 — Claude Code / Codex / Cursor

User reviews

Loading reviews…

FAQ

What will the screens show?

Whatever suits your app: the agent plans new artwork, sketches or charts and its own tool panels for each device, so no existing app screen appears. Your name, headline, colors and any logo you may use carry the identity.

Can it work from an image I already have?

If the image is yours or you may use it, yes. Hand it over with --reference and GPT Image 2 runs in edit mode instead. Only mood, color and layout are taken from the picture; nothing in it is reproduced on the card.

Is there a cost beyond the Skill?

Yes: FAL bills every image to your own account. The helper never retries by itself, and running the same command again only picks up the saved request, so checking on a slow job never pays for a second one.

Preview gallery