Runway Style OG Imagev0.1.1
Use this Skill to make an OG image.
Type does all the work here: a pale gray poster packed with stacked black capitals, one signal color for a thin pointer or burst, and a tiny wordmark in a corner.
Picked most often by
Updated Oct 26, 2026
Preview gallery
FALSimilar Skills
View all
What you get
- One 16:9 WebP poster card in stacked black caps on gray, your brand and headline spelled exactly
- 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
- Video, film and creative-tool brands, plus studios
- Launches carried by three or four loud words
- Events and campaigns that want a poster
Not for
- Screenshots, product shots or illustration
- Lines longer than about five words
- Remaking a poster that already exists
About this Skill
A poster-first OG image skill for Claude Fable 5, made for words that shout. Huge condensed black capitals stack almost edge to edge on plain pale gray. One bright signal color shows up just once (a long thin arrow, a target mark or a pixel-style burst) while a tiny wordmark sits in a corner. Because the line must stay short, the agent trims it with you, then checks each letter of the 16:9 WebP that GPT Image 2 on FAL renders.
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 signal mark 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
- v0.1.1 — Claude Code / Codex / Cursor
User reviews
Loading reviews…
FAQ
Can the signal color be my brand color?
Yes. Your brand colors are fitted to the four style anchors where they work, and the single accent is a natural place for one. The corner wordmark is your name or a logo you may use; nothing is taken from the company the style is named after.
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.