Loom Style OG Image: Image Skill for Claude Code

Split share card for Showpebble with a dune photo and app window on the left and a warm oat text panel on the right

Runs in

Install guides

Claude Code Cursor

Generates with

Host Agent LLM

Uses tools

FAL

Similar Skills

View all

Plaid Style OG Image

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

Runway Style OG Image

What you get

A 16:9 WebP split into text and photo panels, your brand and headline correct to the 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

Screen recording, demo and video-message tools
Walkthroughs, webinars and onboarding
Updates delivered by a person on camera

Not for

Detailed charts or tables
More than one short headline
Copying an existing promo card

Social mediaProduct launchMake an OG imageog imagesocial cardvideo messagingsplit layoutwebcam bubble

Good forMake an OG image

About this Skill

You say/ours-loom-style-og Clipwise records short screen videos that explain expense reports to new finance staff. I need the share card for our tutorials page, headline: "Watch, then file."

For tools where a person explains the product, this Claude Fable 5 OG image skill builds a presenter-led card. The frame divides in two. A warm oat panel carries a large dark headline; the other half is a landscape photo where a clean app window floats, with a circular webcam shot of an invented presenter over one corner. The agent designs both for your message, renders the card with GPT Image 2 on FAL and checks every letter.

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 presenter and the app window 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: v0.1.2 — Claude Code / Codex / Cursor

User reviews

Loading reviews…

FAQ

Is the person in the webcam bubble real?

No, the presenter is invented, as is the app window. You bring the name, headline and colors (a logo or images too, if you may use them), and the layout is built around your brand without anyone else's people or screens.

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