AI Agent Skills
Hand-picked Skills for Claude Code and other AI agents, most with a real-run demo and all with source, license and risk notes. Anything we have not tried is clearly marked.
ComfyUI Image Generation
Generate an image with your own local ComfyUI: improve the prompt, fill the values of your API-format workflow, check that its nodes and model files exist, submit it to localhost, wait and save the picture. Works with any workflow you export.
Penpot UI/UX Design (via Penpot MCP)
Design web, mobile and desktop interfaces inside Penpot through its MCP server, with design-system checks, component and accessibility rules and platform sizes.
Draw.io Diagrams and PNG Export
Generate native .drawio diagrams and export them to PNG, SVG or PDF with the editable XML embedded, using a bundled Node.js export script.
Draw.io Diagram Generator
Create, edit and validate draw.io diagram files with correct mxGraph XML: flowcharts, architecture, sequence, ER and UML class diagrams, with templates and helper scripts.
Excalidraw Diagram Generator
Turn a plain-language description into an Excalidraw diagram file: flowcharts, mind maps, architecture, sequence, ER, class and swimlane diagrams, with templates and helper scripts.
Codex Image Studio
Generate images from text and edit reference images with Codex CLI’s built-in image tool. No separate API key required.
Logo Design
Explore six genuinely different logo concepts (AI-generated with a local FLUX model and drawn in code), compare them on light and dark backgrounds at 64/32/16px, then export a full kit: lockups, favicon, app icon and OG image.
Vane Cinematic Poster
Design film posters with a library of 36 composition and typography layouts.