Art & Design

Compare a portfolio website route with an approved visual reference at desktop and mobile sizes, then report evidence-backed visual defects and fixes.

Prüft Websites auf SEO, GEO und KI-Sichtbarkeit, Seitenarchitektur, strukturierte Daten, Nutzerführung, Barrierefreiheit und Conversion. Verwenden für belegbare Website-Audits, Verbesserungspläne und regelmäßige Qualitätskontrollen, einschließlich Shops, lokaler und internationaler Websites.

Set up and work with Far & Wide, the AI-visibility platform that measures whether ChatGPT, Gemini, Perplexity, Copilot and Google's AI answers mention and recommend a brand, and writes the fixes behind it. Use when the user mentions Far & Wide or farandwide, wants to connect Far & Wide to their agent, fill in their brand on Far & Wide, check their AI visibility, read their Far & Wide audit, or apply Far & Wide recommendations or fixes. Covers connecting the MCP server, the steps only the person can do, filling in the brand from their repository and website, and the day-to-day loop of reading results and applying fixes.

Check whether a website has a valid /llms.txt (llmstxt.org format, working links, size) and whether robots.txt lets AI crawlers such as GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot and Google-Extended in. Use when the user asks about llms.txt, AI crawler access, blocking or allowing AI bots, or whether ChatGPT/Claude/Perplexity can read their site. Read-only.

Give one web page a quick 0-100 AI search visibility (GEO/AEO readiness) score from its server-rendered HTML - AI crawler access, Organization/WebSite JSON-LD, structured data, title/meta, question headings, answer-first opening, llms.txt and freshness - with the top 5 fixes. Use when the user asks if a page is ready for ChatGPT, Perplexity, Google AI Overviews or other AI search, or wants a GEO/AEO score.

Polish, translate, or faithfully revise Chinese or English TeX academic manuscripts; verify source-to-output TeX, math, citation, numerical, and claim preservation; audit cross-section terminology, mathematical notation, and numerical consistency; or apply an author-approved notation mapping. Use for sentence-level through full-manuscript engineering-journal language work when technical truth and protected TeX must remain fixed. For full manuscripts, run terminology, notation, and numerical-consistency audits by default. Do not use as the main skill for novelty review, literature selection, or argument redesign.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

Develop and maintain existing repositories, implement features, fix bugs, refactor, and update dependencies with project context, verification, documentation, and clean commits. Use for hands-on repository work that should read AGENTS, PRD, design, state, and worklog documents and keep them aligned with the delivered change.

Aggressively review code changes for departures from repository-specific coding conventions, local implementation patterns, UI component choices, and test-writing style. Complements bug-focused reviews; use before submitting a PR.

Build or migrate a UI's neutral palette (grounds, surfaces, lines, ink/text) as an OKLCH formula driven by a few inputs instead of dozens of hand-picked hex values, with light and dark themes, per-step ladder overrides, a fit script that reproduces existing colours, and a browser contrast audit. Use when creating a theme, adding dark mode, retinting a product, auditing text contrast, or consolidating several apps' palettes. Triggers on: palette, neutrals, grey ramp, dark mode, theme tokens, oklch, retint, hue, contrast audit, design tokens, Tailwind @theme colours.

Consolidate several apps or prototypes onto one shared component library without flattening their looks. Covers finding duplicated local components (buttons, selects, fields, modals, pagers, toasts), making shared components token-sized so each suite or app sets its own measurements, mapping variant names, deciding what stays app-specific, and the tailwind-merge traps that silently break custom tokens. Use when several apps each grew their own Btn/Select/Modal, when a design system's components "don't fit" a second product, or when retheming a family of apps. Triggers on: shared component library, design system consolidation, duplicate components, retheme, suite of apps, shadcn retokened, token-driven components, cn tailwind-merge custom tokens, variant mapping.

Check frontend readiness from a working diff, PR URL, release target, or full repository audit. Use for app, UI, accessibility, performance, and frontend PR reviews.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Resolve the natural-language `ask "..."` selectors in a pipeline .demo script against the live app, using the Claude in Chrome extension, and write the <script>.selectors.json sidecar. Use when a script has unresolved intents, when compiling or recording fails with "selector(s) still state an intent", or when a redesign has broken selectors that used to work.

host0 lets agents publish websites and apps to live URLs in seconds. Publish a folder and get a live URL at {slug}.host0.app — private by default, open to anyone with the link (unlisted) or public on the web on request. Apps can also declare record collections in an h0.json and get a shared database on their own origin, with no server code. Use when asked to "publish this", "deploy this", "host this", "put this online", "deploy to host0", "make this public", "give me a link", "share this site with someone", "roll back the last deploy", or to build a small team tool (todo list, tracker, sign-up sheet) several people use together.

>- Make or fix the visual things a small company needs, and keep them all looking like the same company: pitch decks, ads, social posts, one-pagers, landing page mockups, event banners, email headers. Use this for "make this deck look good", "design an ad for the launch", "we need a post for instagram", "our slides all look different", "make a one-pager for the sales team", "is this on brand", "we don't have a brand, can you start one", or any time a layout, font, colour or image choice needs a decision.

>- Audit a funnel end to end and come back with the ONE leak worth fixing plus the test that proves it — instrument the steps, measure step-to-step conversion against real benchmarks, find where users actually drop, separate a traffic-quality problem from a product problem, and design an experiment with a pre-committed success number. Use this for "signups are flat", "traffic is up and revenue isn't", activation and onboarding drop-off, checkout or paywall abandonment, trial-to-paid conversion, landing-page and pricing-page performance, retention/churn cliffs, and A/B test design or readout (including calling a test dead). Also use it to kill vanity metrics and pick a north-star. NOT for building dashboards or wiring an analytics SDK — this is the decide-what-to-fix layer that sits on top of the numbers.

Design and refine Readiz websites and web apps with compact controls, icon actions, useful tables, and progressive disclosure. Use when creating or changing web UI, especially dashboards, charts, learning pages, and tools.

Set up and manage an Asyntai AI customer support agent (website chatbot) through the Asyntai MCP server - add knowledge, edit the agent's instructions, change the widget look, read conversations, leads and analytics, find topics that need more knowledge, and reply live to visitors. Use when the user wants to train, configure, review or run their Asyntai chatbot, or when the asyntai MCP server needs to be connected.

Hover textures and motion for websites from Textures (textures.dev): fields of bars, dots, dashes or tiles that react to the pointer, behind or inside a hero, header, panel, pricing card, feature card, empty state, button or background. Use when a task asks for a hover effect, hover animation, hover state on a panel or card, micro-interaction, subtle or brand motion, animated background, interactive background, pattern, texture or brand feel, or when a hero, section, panel or page should feel designed, premium, more alive, less flat, less static or less plain. Not for tooltips, dropdown menus, button colour states, page or route transitions, scroll-triggered reveals, loaders or carousels. Finds, installs and wires a Texture, and can remember Textures for the project on request.

Install a complete, lean favicon set on any website or web app — the five files modern browsers, iOS and Android actually use, one block of head markup added once in the root layout, and a check that every file resolves. Covers finding the public folder per framework, generating the set from one SVG (or from a RealFaviconGenerator package), dark-mode SVG icons, maskable manifest icons, cache busting and verification. Use when adding, replacing or auditing a favicon, app icon, apple-touch-icon or web manifest. Triggers on: favicon, favicon.ico, favicon.svg, apple-touch-icon, site.webmanifest, manifest.json, app icon, PWA icon, maskable icon, tab icon, RealFaviconGenerator.

Add an AI chatbot (AI customer support agent and live chat widget) to a website or web app with Asyntai. Use when the user asks to add a chatbot, AI assistant, support chat, live chat or chat widget to a site, store, docs site or app, on any stack (HTML, React, Next.js, Vue, Nuxt, SvelteKit, Angular, Astro, Laravel, Django, Rails) or platform (WordPress, Shopify, Wix, Webflow, Squarespace and 100 more).

Make a website, web app or online store ready for AI agents. Scan it with Cloudflare's Agent Readiness checks, decide which checks apply to this kind of site, ship the discovery files and headers in priority order, and add the AI-first basics the scanner does not score (server-rendered content, JSON-LD, llms.txt). Covers robots.txt AI rules, Content Signals, sitemap, Markdown for Agents (Accept text/markdown), Link headers, API catalog, OAuth discovery, auth.md, MCP server card, A2A agent card, agent skills index, WebMCP, and commerce protocols (ACP, UCP, AP2, MPP, x402). Use when making a site AI-ready, agent-ready or AI-first, or fixing an isitagentready.com or Cloudflare Agent Readiness report. Triggers on: AI ready, agent ready, AI-first, agent readiness, isitagentready, AI Crawl Control, Markdown for Agents, text/markdown, llms.txt, GPTBot, ClaudeBot, AI crawlers, Content-Signal, ai-train, api-catalog, .well-known, oauth-protected-resource, auth.md, MCP server card, agent card, agent skills, WebMCP, a...

Publish the website. Use only when Irena or Alex explicitly says something like "deploy it", "make it live", "publish it", "put it live" or "push". Pushes the saved local versions to GitHub main, which Netlify then builds and puts live. Never use it just because a change is finished.