Image

Use when delivering Illustrator-editable layouts (magazines, profiles, brochures) built as SVG/PDF so each paragraph becomes one editable area-type text box, not grouped lines.

Render Arabic typography, posters, certificates and documents. Use for RTL artwork or calligraphy guidance; distinguish supported fonts from manual compositions.

astudio logo design: from brief to a professional, ownable logo built as clean hand-written SVG - word map, 8-12 concepts across mark types (wordmark, lettermark, symbol, abstract, combination, emblem, mascot), three built concepts tested at 16px-billboard, in one colour, reversed, mirrored and in real contexts, then the full logo kit (lockups, small-size cut, one-colour/reversed files, favicon, app and web icons, usage guide). Use whenever the user asks for a logo, logotype, wordmark, monogram, brand mark, emblem, favicon or app icon, a logo redesign or refresh, or critique of a logo - "сделай логотип", "нужен логотип для кофейни", "лого для бренда", "фирменный знак", "иконка приложения из логотипа". Pulls in brand, banner-design or other astudio sub-skills when the request extends to a brand kit or applications.

Quick AI edits of an existing image (render, viewport capture or photo) with Nano Banana 2 / Pro through Rook: turns the user's rough request into a precise edit prompt, runs it, checks the result for the change and for drift, and retries with a fixed prompt. Use whenever the user wants to change something in an image (swap or remove an object, change a material, planting, sky, light or season, add people), asks to "roast", touch up or AI-edit a picture, or hands over an image-edit prompt to tighten, even if they do not name the skill or the model.

Create and refine posters, images, social graphics, illustrations, diagrams, and icons with deliberate whitespace, proportion, golden ratio where useful, hierarchy, typography, and color. Apply these constraints during generation, review the result, and deliver actual SVG or raster files. Supports direct clean editable SVG creation and PNG, JPEG, or WebP output according to the brief.

Design new geometric logomarks (symbols, lettermarks and monograms) as clean single-colour SVG to the standard of the free Logomarks set at logomarks.ai: the 512 grid, exact fit, the construction kit, the house checks and the set's taste. Use when designing new geometric marks, drawing or iterating on a logo mark, brand symbol, lettermark or monogram, checking an SVG mark against the house rules, or editing, remixing or glitching one of the existing Logomarks.

Add animated pixel icons built from 3D cubes to a web page, using the dependency-free Cube Icons engine (a 2D canvas, no WebGL). Cubes fly in to build the icon, settle, and fly apart; there are 61 ready icons, eleven looks (flat, soft, clay, candy, paper, outline, pixel, glass, neon, wire, holo), scroll-driven building, explode, magnet and morph effects, and a pixel-text font. Use this when someone wants voxel, pixel, 3D-cube or "Minecraft-style" animated icons, a menu where hovering builds an object, an animated empty state, loader, hero or feature-card illustration, scroll-assembled visuals, or a small custom pixel icon drawn and dropped into a site. Works in plain HTML, React/Next.js, Vue, Svelte, Framer, Webflow and WordPress.

Build an app that is designed, honest and verified instead of a template. Use for any request to create, redesign or substantially extend a web app in any stack: a marketing or landing page app, portfolio, local-business app, store front, docs, dashboard, tool, portal, or a learning app such as 'an app for learning a language'. Gives the whole method: reading what the person really wants (an app to read or an app to use), research and content strategy, six-direction inspiration boards chosen from pictures, design craft (visitor modes, a measured design scan, named refinement passes), a binding baseline, a token-driven build with a starter template, honesty rules (no invented proof, nothing fake working), real-browser QA with evidence, repair, and an honest closing report. Includes a starter template, a contrast checker, a QA script with a design scan and an image optimiser.

Full prospect demo pipeline. The user runs "demo website" (or /demo-website) and pastes a prospect's URL or name; redesign their whole existing site with the scroll-craft skill (every page, same logo, same photos, same text, same page structure, new design), deploy it to Vercel, then draft the "here is the demo" reply in the mailbox the outreach went out from. Use for "demo website <url>", "build the demo for X", "X wants to see the demo", "redesign X for the prospect".

Use when the user asks for help designing (or redesigning) a website/landing page/SaaS UI/portfolio. Delivers UX, typography, layout, tokens, components, interaction guidance, and production code—while avoiding generic AI design. Provides both strategic design direction AND implementation.

AI UI prototype and wireframe generation powered by CellCog. Interactive HTML prototypes, wireframes, app mockups, landing pages, mobile screens, SaaS dashboards, design systems, user flows. From description to clickable prototype in one prompt.

Generate or edit images with GPT Image through BUZZ and save them into the project. Use whenever the user wants any image or visual asset (icons, favicons, logos, OG/social cards, banners, illustrations, UI mockups, photos, transparent stickers/cutouts, posters) or wants to change an existing image file (restyle, recolor, remove/replace background, add or fix elements).

Design and build a responsive frontend website or accessible landing page for a small business or creator from the first brief. Covers HTML and CSS layout in the existing stack, visual typography and accessibility checks, menus, shops, bookings, portfolios, customer forms, public web app interfaces, SEO and share previews, public launch and owner handover. Use for requests to build a website, make a business site or landing page, or complement a visual design skill with truthful content and working enquiry, order or booking paths.

Brand asset register: asset type, format, dimensions and aspect ratio, colour mode, background variant, clear space, approved and prohibited uses, rights owner and licence. Use for brand control.

Open Graph and social sharing image design with platform specs, text placement, and branding. Covers OG meta tags, Twitter cards, LinkedIn previews, and dynamic generation. Use for: social sharing images, blog thumbnails, link previews, social cards. Triggers: og image, open graph, social sharing image, twitter card, social card, link preview image, og meta, sharing preview, social thumbnail, meta image, og:image, twitter:image, linkedin preview

Plan and build conversion-focused landing pages with intake, proof-based copy, explicit page structure, and the ELAYA visual system.

Produces professional AI product photography — clean e-commerce shots, lifestyle scenes, hero images, macro detail shots, and flat lays — as generation-ready prompt specs, and generates the files via FAL.ai fal-ai/nano-banana-pro when the automation is configured. Use when the user says 'product photos', 'shots of my product', 'images for my store / listing / landing page', 'hero image for my product', 'lifestyle photos', or shares a product needing marketing imagery. Produces one prompt-spec block per shot (shot type, lighting, background, composition, aspect ratio, negative constraints) with a shot list, variant plan, and file-naming conventions; runs docs/creative_cli.py product when FAL_API_KEY is set.

Logo design principles and AI image generation best practices for creating logos. Covers logo types, prompting techniques, scalability rules, and iteration workflows. Use for: brand identity, startup logos, app icons, favicons, logo concepts. Triggers: logo design, create logo, brand logo, logo generation, ai logo, logo maker, icon design, brand mark, logo concept, startup logo, app icon logo

Design and build striking, memorable websites in hand-written HTML, CSS and a little vanilla JS (landing pages, product and project sites, portfolios, small-business and personal sites), and redesign existing ones, so visitors who load the page think "whoa". Sets an original direction per project or works within an existing brand, designs one wow moment for the first screen, writes real copy, builds a responsive token-based page with a full favicon and app icon set, then screenshots and motion-captures it at phone, tablet and desktop sizes with a bundled Playwright script and fixes what it sees. Use this whenever the user wants to create, design, build, mock up, restyle, redesign, refresh or "make nicer" a website, web page, landing page, homepage or a section of one, even if they only say "make a page for my project" or "this site looks dated", and to design, generate or check a site's favicon or app icons. For critique-only requests where nothing should change, design-critique fits better.

Design landing-page proposals for a product as self-contained HTML grounded in its code, real captures and brand — one memorable device per page, a choreographed hero film, an accessibility and verification bar (axe x8, parser check, smoke test). Use when asked to draw, propose or improve a product's public/landing page, compare directions, or "make it more attractive / more dynamic". Not for porting a chosen design into the app (later job); upstream concept work is website-concept-architect.

Build, iterate and launch an explorable 3D portfolio website (a room or studio in the browser, made with Three.js) for an educator, learning designer, designer or student, with each portfolio section living in an object in the room. Covers planning the room metaphor, image prompts for a reference picture, the single-file Three.js build, filling real content with design notes, linking Google Drive files, round-by-round polishing, testing, deploying on GitHub and Vercel, a custom domain, auto-updating GitHub, and protecting the work and the learners in it. Use this whenever someone wants an interactive, 3D, immersive, game-like or "room" portfolio or personal site, wants to turn a picture of a space into a website, is iterating on such a site ("make the bookshelf glow", "move the menu", "the chest should open a gallery"), or asks how to publish, update or protect one, even if they never say "Three.js" or "skill".

Use when choosing, generating or fixing the photography on a website - hero frames, section and card images, model imagery, product renders - or when a page's images look inconsistent, stocky, off-brand, soft, or do not prove the claim next to them.

Create an art-directed, high-resolution thumbnail image (PNG + lossless WebP) for a website, a local web project, or a single article. Extracts the site's visual identity (imagery, components, colors, fonts, logo) and composes a bespoke design from it, in a portfolio size by default or any platform format (Instagram, TikTok, Snapchat, stories, Open Graph, custom sizes). Use when the user asks for a portfolio thumbnail, project cover, showcase image, social image or link-preview image for a site, project or article, or invokes the thumbnail skill directly.

Use when the user wants to see how a request, command or feature actually runs: call order, "what happens when X", runtime flow, or sequence diagrams. Traces real calls through the code and writes docs/codemap/sequence-flow.md.