AI Static Ad Set — trending format for ads & UGC
For AI agents: find the right skill in one call —
curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
Ten genuinely different still ads for one product, each its own concept with the headline set in the image, ready for Meta and TikTok tests.
- Slug:
want-ai-static-ad-set - Status: wanted
- Publisher: mmmiyama_D (community)
- Source: https://x.com/mmmiyama_D/status/2097995132880773328
- Cost: ~100–300 credits / 10-ad set (estimate) — Images only: an operator reports 12 statics for about $0.73 (claim); premium image models and re-rolls cost more per image.
What it does
A batch of static ad creatives from one brief: the product photo and facts in, 6–10 distinct concepts out (editorial illustration, giant-type poster, forced-perspective key visual, native screenshot, comparison card…), each with the headline rendered in the image and cropped to 1:1, 4:5 and 9:16. Statics rose on X this autumn as image models learned to set exact type. Since Meta's GenRecs (19 Oct) and next-generation Andromeda (28 Oct) read every ad's images and words, colour-swapped look-alikes compete as one ad, so the set has to differ in idea, not in palette. Ready prompts: https://varg.ai/how-to/prompts/ads/#x-2097995132880773328 and https://varg.ai/how-to/prompts/ads/#x-2091768524037333319
Status
A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.
Example: https://x.com/mmmiyama_D/status/2097995132880773328
How an agent would make it: Claude turns the brief into 10 angles and one concept per angle (scene, headline, layout) → gpt_image_2_5 or nano_banana_2_1 with the product photo as a reference and the headline in quotes → check the type and the product against the photo → crops 1:1, 4:5 and 9:16 → file names carry the angle for the test
Models it drives: gpt_image_2_5, nano_banana_2_1
Example output
https://pbs.twimg.com/media/HR2TdFAbgAAzODl.jpg — An urban editorial-illustration ad generated from a profile screenshot (GPT Image 2.5) (credit: @mmmiyama_D, https://x.com/mmmiyama_D/status/2097995132880773328)
More ads & UGC skills
- Ecommerce video ad skills for Claude Code and AI agents: Product videos that sell on TikTok, TikTok Shop, Reels and Meta: angle, hook, format, script, rules, variants.
- Turn a product into scroll-stopping video hooks: The first 3 seconds of a product video: frame, line and text that agree, from a 70-line hook bank.
- Open-source alternative to Arcads: AI UGC ads: AI UGC ads with an AI actor holding your real product: face, voice and label locked, labelled.
- Turn one winning ad into a creative testing plan: How many ads to test, what to change, when to judge, kill or scale — concepts Meta sees as different.
- Turn a product into a dropshipping guide reel: The faceless "comment GUIDE" reel: product hook, a marker pointing at cost and price on a laptop, a skyline ending.
- Turn product photos into a viral product hook: Find a hook that already sells, then remake it with your product as phone or security-cam footage on Seedance 2.5.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt