Asana Style OG Image: Image Skill for Claude Code

Runs in

Install guides

Claude Code Cursor

Generates with

Host Agent LLM

Uses tools

FAL

Similar Skills

View all

Notion Style OG Image

Plaid Style OG Image

Plum share card for Keyquarry with a frosted launcher window tilted behind a giant headline whose first word is a slanted gradient

FREE

Raycast Style OG Image

Pale gray poster card for Reeltorch with stacked black capitals on the left and a thin orange arrow pointing down along the right

FREE

Runway Style OG Image

Stripe Style OG Image

Linear share card with a large dark issue-list app window floating over a soft purple, blue, amber and coral blur

Linear Style OG Image

A seamless light gray backdrop with a hand holding the pale teenage engineering TP-7 field recorder, its big split disc, small display reading MEMO and a glowing red light

Teenage Engineering Style OG Image

Algolia Style OG Image

What you get

One 16:9 WebP: white page, small centered lockup, warm see-through waves, your brand and headline exact
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

Planning, task and team tools
Calm, hopeful announcements and roadmap posts
Brands that already use a warm gradient

Not for

Screenshots or crowded scenes
Figures, charts or tables
Re-creating a real logo or a real campaign

Social mediaProduct launchMake an OG imageog imagesocial cardproductivitygradientminimal

Good forMake an OG image

About this Skill

You say/ours-asana-style-og We're announcing Driftline, a weekly check-in tool for remote teams. Can you make the OG card? Headline: "Fewer meetings, clearer weeks".

Some announcements read best with almost nothing on the card, and this share-card skill for Claude Fable 5 leaves the white page nearly empty: a small logo and wordmark mid-page with a short line, and two wide, translucent waves overlapping low in the frame, shading from orange and coral into magenta and violet. The agent draws a simple mark if you need one, makes one GPT Image 2 request on FAL and checks the spelling before you get the WebP.

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 a simple 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: v0.1.0 — Claude Code / Codex / Cursor

User reviews

Loading reviews…

FAQ

Can the waves use my colors instead of the sunset range?

Yes. Your colors, name, headline and any logo you have rights to go in; the Skill fits them to the white page and waves, keeping how the colors relate rather than copying exact values. Nothing from another company's mark or campaign is used.

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