Loading...
Loading...
Found 15 Skills
Design social media creative and one-off graphics on Moda: organic posts, carousels, story/reel covers, static social ads, display banners, profile headers (Instagram, LinkedIn, TikTok, Facebook, X, YouTube) — plus simple standalone graphics that aren't a deck/document/diagram/website: quote cards, single-image visuals, ad-hoc designs with no platform attached. Use for a social post, carousel, story, platform creative, static ad, banner ad, channel header/cover, quote card, or "a simple graphic of/for X". Produces platform- or purpose-sized pages on a live Moda canvas, exporting png/jpeg or pdf (multi-page carousel → zip). Moda animates these too: for an animated ad/post or anything delivered as gif/mp4, load moda-video. Slide decks → moda-deck; printable flyers, posters, PDFs → moda-one-pager; live hosted pages → moda-website.
Create a Xiaohongshu cover for a fitness coach serving local in-person members, using Ye Tong’s original live-action photography style. Use when a specific topic or body copy is already available and a cover, prompt, numbered composition choice, continued optimization, or direct generation is needed; after reading the user’s activated DNA, execute the original step-by-step, one-question-at-a-time workflow, with five fixed compositions, a 3:4 ratio, oversized top-and-bottom text, and a white, warm-orange, and yellow visual style. It does not handle broad topic ideation, publication-title-only changes, or full-note audits.
Use to write great prompts for Nano Banana (Google's Gemini image model: Nano Banana Pro = Gemini 3 Pro Image) to generate or edit images for social media — the image-prompt-craft mini-skill. Run when the user wants a nano-banana / Gemini image prompt, an AI image for a post (quote graphic, carousel slide, thumbnail, infographic, product shot, ad creative), or conversational image editing. Reads brand-profile for brand colours/style. Strengths: best-in-class legible in-image text (route typography/layout-led design to ideogram), multi-image consistency, conversational editing, and Google's photoreal lane (Imagen deprecated); surreal art stays Midjourney's. Teaches prompt anatomy, the text-first approach, reference-image consistency, and per-platform aspect ratios. Honest: SynthID watermark + AI disclosure; never real identifiable people or copyrighted characters/logos; verify spelling/data. The API/connection and WoopSocial upload flow live in tools/integrations/nano-banana.md.