94 items · Skills 37 · MCP 52 · Plugins 4 · CLI 1
Graphics & design
Graphics, logos and mockups: image generation, Figma, Canva and a consistent brand.
What you can make
- logo and brand identity
- poster
- Figma mockup
- social media graphics
With search, filters and ratings.
Ready-made packs
Ready-made tool sets for this task. Load any of them in your AI with one command.
- Brand kit
An SVG logo, brand palette and fonts collected on a Figma board, plus first graphics in Instagram, Facebook and LinkedIn formats.
/brand-kit
All items (94)
Skills (37)
Generative art in p5.js: flow fields, particles and noise with parameter sliders.
Finds the spots in an article that need illustrations and generates them in one style and palette.
Creates educational comics from source material: art style, tone and panel layout.
Creates article cover images, matching type, palette, style, text and mood to the content.
Draws SVG diagrams: flowcharts, sequence diagrams, architecture and concept illustrations.
Generates images through OpenAI, Google, OpenRouter, Replicate and Chinese provider APIs.
Turns text or an article into an infographic with 21 layouts and 22 visual styles to choose from.
Teaches the agent to prompt FLUX models and use the Black Forest Labs API for images and video.
Applies Anthropic’s brand colors and typography to docs and graphics – a template for a brand skill.
Creates posters and static graphics as PNG or PDF, guided by its own design philosophy.
Teaches the agent to build Carbon UI (React, Web Components, charts) using data from Carbon MCP.
273 skills for designers: research, UX, design systems, UI, prototyping and critique.
Installs animated Lottie icons in your app and lets the agent draw the ones that are missing.
Keeps UI consistent: saves decisions about spacing, color and depth across sessions.
Motion design for agents: timing, easing, choreography and Disney’s 12 principles in UI.
Generates Excalidraw and Mermaid diagrams and Canvas boards for Obsidian from text.
Makes animated GIFs and emoji for Slack, keeping size, frames and palette in check.
Designs app screens in Google Stitch from a description, code or images.
Applies a consistent color and font theme to slides, documents, reports and HTML pages.
AntV Chart Visualization Skills
Picks a chart type and generates charts, graphs and infographics with AntV libraries.
Plans a presentation outline and style, generates the slides as images and merges them into PPTX.
Skills for animation and interface detail from Emil Kowalski, creator of Sonner.
Native-looking Expo screens: system colors, native controls, SF Symbols and visual effects.
Picks fal.ai models and runs video production: shots, prompts, ads and motion graphics.
A bold visual direction for new interfaces instead of the generic “AI-made” look.
Generates video and images in Higgsfield: Veo, Kling, Seedance, ads and thumbnails.
Creates Manim math animations with narration, subtitles and a review viewer for revisions.
Generates polished, well-designed PDFs, fills in forms and restyles documents.
Videos in two styles made entirely in code: watercolor animation and kinetic typography.
Correct PixiJS v8 and PixiJS 3D APIs: sprites, graphics, filters, performance and migration from v7.
Turns one product photo into a main image, a multi-angle shoot and ad creatives.
Sprites, icons, tilesets, isometric maps and parallax backgrounds via Scenario MCP.
2D animation via Scenario: walk cycles in 4 or 8 directions, sprite sheets and GIFs.
Implements and reviews iOS 26 Liquid Glass with native SwiftUI APIs.
Art direction for websites: visual direction, composition, typography and browser checks.
Builds a design system for your industry: style, palette, font pairings and UX rules.
Turns images, SVGs, sketches or a script into a hand-drawn whiteboard animation.
MCP (52)
Over 1,000 fal.ai image, video and audio models: pick, check prices and generate in chat.
Reads and edits Figma files – frames, variables, components – so code matches the design.
Finds brands and pulls their logos, brand assets and company data from Brandfetch.
Generates and edits images and video with Bria models trained on licensed data.
Gives the agent the components, tokens, icons and docs of IBM’s Carbon Design System.
Controls ComfyUI from chat: generates images and video, builds workflows and downloads models.
A knowledge base on design systems, WCAG and ARIA with dates and sources, available to the agent.
Creates draw.io diagrams from a description: flowcharts, architecture, UML – ready to edit.
Generates and edits diagrams and technical docs in Eraser from a description.
Sketches hand-drawn Excalidraw diagrams in the chat window, with full-screen editing.
Reads and writes Figma files: tokens, components, layout and design-to-code parity checks.
Gives the agent slimmed-down Figma layout and style data to code mockups faithfully.
Edits images in GIMP from chat, with the agent checking a preview of the result after each step.
Gives the agent over 420,000 Icons8 icons and illustrations to drop in as PNG or SVG.
Reads, creates and exports artwork in Adobe Illustrator – 66 tools for the agent.
Searches, uploads and tags files in ImageKit and builds image transformation URLs.
Locally crops, resizes and rotates images, removes backgrounds, detects objects and reads text.
Creates and refines animations from a description or SVG artwork and exports them to Lottie, MP4 and WebM.
Creates and edits diagrams in Lucid, searches and summarizes documents and exports them to PNG.
Validates and renders Mermaid diagrams to PNG and saves them to Mermaid projects.
Creates diagrams, docs and tables on Miro boards and reads context from them for coding.
Searches real app and website screens in Mobbin as UI and UX inspiration.
Generates and edits images with Gemini models (Nano Banana 2 and Pro) at up to 4K resolution.
Draws draw.io diagrams from your project’s files, with a live preview in the browser.
Reads, creates and changes elements in Penpot files, the open-source alternative to Figma.
Controls Photoshop from chat: background removal, retouching, color and export for social media.
Generates raster and vector graphics, vectorizes, upscales and removes backgrounds.
Searches, compares and runs models from Replicate: images, video and audio.
Generates images, video, audio and 3D models through the Runware API, with pricing and model picking.
Reads and updates your Supernova design system: docs, tokens, components and contexts.
Creates and edits SVG animations in SVGator and exports projects to SVG, Lottie and MP4.
Generates and edits SVG graphics from a description, vectorizes images and removes backgrounds.
Reads and changes Figma designs through a plug-in: text, shapes, auto layout, instances.
Opens an interactive tldraw canvas in the chat where the agent draws alongside you.
Builds flowcharts, mind maps, wireframes and sequence diagrams in Whimsical from a description.
Gives the agent screen and component specs, annotations and tokens from Zeplin projects.
Finds and generates React/Tailwind components from the 21st.dev catalog in chat.
adb-mcp (Premiere Pro, After Effects)
Controls Premiere Pro and After Effects (plus Photoshop) through app plugins and a local proxy.
Generates more than 25 AntV chart types, from bars and lines to Sankey charts, treemaps and diagrams.
Draws and animates pixel art in Aseprite: layers, palettes, shading and sprite sheets.
Flowbite components for Tailwind CSS, a theme generator and Figma designs turned into code.
Veo, Gemini Image, Lyria, Chirp and Gemini TTS from Google Cloud as agent tools.
Generates game assets: animated sprites, 3D models, music and sound effects.
Speech synthesis, voice cloning and voice design, plus images and video from MiniMax models.
Generates pixel-art characters in 4 or 8 directions, their animations and game tilesets.
Generates real pixel art: sprites, animations and tilesets on a clean pixel grid.
Generates video and images with Runway and partner models (Gen-4.5, Veo, Kling).
Generates images, video, audio, textures and 3D assets: over 750 AI models plus your own.
Generates and animates pixel art at exact sizes from 16 to 128 px, including 8 directions.
Generates pixel art and 2D assets: sprites, icons, sprite sheets and character animations.
Generates UI screens in Google Stitch from a description and fetches their HTML and screenshots.
UI skills from many authors that your agent picks on its own: design, animation, accessibility.
Plugins (4)
Photoshop, Firefly, Express, Lightroom and Premiere tools, controlled from chat in Claude.
Creates, edits and adapts Canva designs: social media formats, brand templates, revisions.
Generates and edits images with Nano Banana models: icons, patterns, diagrams and stories.
Manages Cloudinary images and video: uploads, transformations, AI analysis, automations.
CLI (1)
MiniMax in the terminal: Hailuo video, images, speech, transcription, image descriptions.