Design & Media Agent Skills for DeepSeek Harness

AI Sprunki OC maker — create a Sprunki-style original character from a person photo

AI wild graffiti generator — create wild-style spray paint graffiti art from text or image

AI image generation — create high-quality images from text with Z-Image by Alibaba

Wireframe a screen — text/ASCII by default, or hand-drawn HTML when the user says "sketch", "hand-drawn", "lo-fi HTML", "whiteboard"…

Generates and edits high-quality images across multiple AI providers including ModelScope, Gemini, and RunningHub.

Use when working with Sonner or troubleshooting React toasts, including Toaster setup, toast variants, promise/loading flows, dismissal…

WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.

Integrates WPF-UI (Wpf.Ui) library for Fluent Design in WPF applications.

Use whenever a task writes or modifies React code, including JSX or TSX components, hooks, React tests, and React code snippets.

UX writing and interface copy, from voice and button labels to error messages and empty states.

Author, extract, and maintain a project's DESIGN.md following the Google design.md spec (https://github.com/google-labs-code/design.md).

Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support.

Implement modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first breakpoint strategies.

Creates the cards of an X / Twitter carousel ad at X's dimensions, as a series of coherent visuals.

Creates the X / Twitter profile visuals (profile photo and header / banner) at X's official dimensions.

Generates realistic, customizable X (Twitter) post cards with engagement metrics for video overlays and social sharing.

Creates an image for an X / Twitter post (a tweet image) at X's ratios, in the chosen orientation.

Transforms Chinese articles, video voiceovers, and business workflows into sparse, hand-drawn 4:3 conceptual illustrations and diagrams.

Use when creating retro-grain portrait, fan, or editorial collage posters from user-supplied photos.

Start the dev server, inspect the feature in browser, and iterate on polish.

Creates zero-dependency, animation-rich HTML presentations from scratch or via PowerPoint conversion with a focus on visual discovery.