theme-handler
Manage and update application themes using shadcn and tweakcn.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Manage and update application themes using shadcn and tweakcn.
Create TikZ diagrams in Obsidian using TikZJax plugin. Use when visualizing geometric shapes, coordinate systems, game scenes, circuit diagrams, chemical structures, or complex technical drawings that require precise positioning.
Final visual polish for an existing UI without redesigning it. Use after structure is clear, when asked to improve spacing, alignment, text hierarchy, readability, shadows, highlights, effects, action placement, or overall production feel. For screen structure, layer naming, code handoff, preview scenes, or animation planning, use pencil-ui-structure first.
Design, critique, and revise UML diagrams from a modeling and communication perspective. Use when Codex is asked to create or improve UML; when the user asks for a graphical representation, diagram, schema, visual model, process map, state view, architecture view, or system representation of software/system behavior or structure; when the user does not explicitly choose UML but needs a model-like visual explanation; when Codex must autonomously choose the right UML diagram type or split across multiple UML diagrams. Use for reasoning about diagram form, abstraction level, boundaries, grouping, lifecycle/state design, behavior vs structure, interaction design, or diagnosing why a diagram feels wrong at the modeling level. This skill treats notation as the final representation, not as the core task.
Create interactive single-file HTML prototypes for UX validation. Use when the user asks to create a prototype, mockup, or interactive wireframe based on specs/architecture/ux.md or any UX specification. Triggers include requests like "create a prototype", "build a prototype from the UX spec", "make an interactive mockup", "prototype the user flow", or "validate the UX".
Design video concepts, scripts, shotlists, transitions, and editing notes for VEO, Gemini, and Nano Banana-based pipelines. Use when turning a marketing idea into concrete video assets.
Guides educational visual asset creation using professional creative briefs, proficiency alignment, prerequisite validation, and duplicate prevention.
Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT) — use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB VRAM; includes anime inpainting via Anima-LLLite ControlNet
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows — local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control
Lay out and organize a ComfyUI workflow cleanly on the live panel canvas — dependency-layered node placement with no overlaps, subgraphs, colored group boxes, and subgraph rail alignment. Use when asked to tidy / clean up / organize / arrange a workflow, add groups or subgraphs, fix overlapping nodes, or build a workflow that should look good from the start.