Image

motlab-assets

github.com

Make reusable assets as code for motlab videos, without any AI image, video or 3D generator: icons, illustrations, vector logos, rigged 2D characters, 3D objects, transitions, textures and backgrounds, kept in one kit so every video looks the same. Outputs transparent PNG plus SVG, or GLB, FBX and OBJ with PBR textures. Use whenever someone asks for assets, an asset kit, a mascot, an icon set, a 3D model or textures, even if they never say motlab.

$ npx skills add staryone/motlab
Skill anzeigen→

designprint

github.com

Design and print physical pieces for the user and have them shipped: business cards, flyers, posters, menus and invitations. Use when the user wants something printed, wants business cards made or ordered, is designing something that is meant to be printed, or asks for a physical copy of a design from the conversation. Makes two-sided business cards from a name and contact details, or prints any design (HTML or an image) at an exact size in inches, and returns a proof, the price and one link where the person pays as a guest. Works through the Designprint MCP tools when they are connected, and over plain HTTPS with curl when they are not, with no account and no API key. Not for on-screen graphics such as social posts, slides or web images. Ships within the United States only.

$ npx skills add thedesignprint/designprint
Skill anzeigen→

etsy-listing-image-studio

github.com

Generate and quality-check Etsy listing thumbnails or fidelity pilots from a scoped product brief, preserving original design and exact supplied copy.

$ npx skills add trevor94899234-maker/shineon-design-skills
Skill anzeigen→

gpt-image-26-pe

github.com

Use when a user asks an Agent to write, optimize, or restructure a prompt for GPT Image 2.6 (gpt-image-2.6-sunburst / gpt-image-2.6-flare) — text-to-image, image-reference, multi-image compositing, image editing with markup, SVG export, and animated GIF generation. Turns a brief or an existing prompt into one clean, directly submittable prompt under the official OpenAI image-prompting fundamentals.

$ npx skills add sliu2024/laoliu-ai-prompt-skills
Skill anzeigen→

gpt-image-25-pe

github.com

Use when a user asks an Agent to write, optimize, or restructure a prompt for GPT Image 2.5 (gpt-image-2.5-sunburst / -flare) — text-to-image, image-reference, multi-image compositing, or image editing. Turns a brief or an existing prompt into one clean, directly submittable prompt under the official OpenAI image-prompting fundamentals.

$ npx skills add sliu2024/laoliu-ai-prompt-skills
Skill anzeigen→

review-gallery

github.com

Show visual work to the user as a local HTML review page - every screenshot, generated image, design option and before/after (GIF for anything that moves) in numbered sections, each with Looks good / Needs work buttons or an option pick, a note box, and a Copy feedback button whose numbered text the user pastes back for the next round. Use this by default whenever you have UI, screens, game art, icons, illustrations, VFX, animations, logos, layouts or any other visual result to show or to get feedback on - for requests like "show me the screens", "put the screenshots together", "make a few options", "mockups", "before and after", "compare these", "which one is better", "let me pick", "improve the UI", "let me mark what to fix", "review", "feedback" in any language - and whenever the user pastes back text that starts with a page header such as "UI round 2 feedback" followed by lines like "12. [Hero detail] Needs work - ...". Prefer it over describing images in chat or sending loose...

$ npx skills add RevStudio/review-gallery
Skill anzeigen→

visual-instructions

github.com

Design user manuals, how-to guides, tutorials, onboarding docs, SOPs and step-by-step instructions that people can follow without reading much - visual, low cognitive load, one action per step, annotated screenshots, concise copy, clear hierarchy. Use this whenever the user asks to write, redesign, review, correct or improve a manual, user guide, instructivo, manual de usuario, guía, paso a paso, tutorial, quick-reference, help article, job aid or any "how do I do X in this app" / "cómo se hace X" document; when they share screenshots or capturas to turn into instructions ("armame el instructivo", "te paso las capturas"); when a client or reviewer sends corrections to a manual; or when they say a guide is confusing, too long, too dense or "nadie lo lee" - even if they never say "instructional design".

$ npx skills add milagrosgonzalezarguello-des/visual-instructions-skill
Skill anzeigen→

research-figure

github.com

Generate publication-quality figures for academic papers: LaTeX TikZ method pipelines and Blender 3D renders. Use this skill for method overview figures, pipeline diagrams, architecture diagrams, system flowcharts, 3D rendered teasers, SMPL/FBX mesh renders, skeleton visualizations, method comparisons, or any research figure need. Trigger on: "method figure", "pipeline figure", "architecture diagram", "flow diagram", "teaser", "3D render", "SMPL", "FBX", "mesh render", "Blender", "blender figure", "teaser figure", "skeleton render", "3D comparison", "方法流程图", "画图", "渲染", "三维", "draw my method", "I need a figure for my paper", "help me make a figure".

$ npx skills add retrocognition023/my-agent-skills
Skill anzeigen→

seedream-5-5

github.com

Write prompts that work for ByteDance Seedream image models (5.5, 5.0, 4.5) and generate or edit images through BytePlus ModelArk, Volcengine Ark, Runware, WaveSpeed, Kie.ai, Evolink, fal, Replicate or OpenRouter. Use when the user wants to create, edit, restyle, translate or combine images with Seedream, or needs images for a project they are building in one consistent style: hero and section images, OG cards, favicons and app icons, empty states, game sprites and icons, App Store screenshots. Also for product shots, ads, posters with exact text (including Chinese), infographics, app, website, game HUD or kiosk UI mockups, dark-mode variants, event graphics, consistent characters, storyboards, video keyframes (Seedance, Kling), transparent PNGs, or splitting a flat image into editable layers; or debugging bad Seedream output, square outputs or safety-filter refusals. Not for SVG, vector, HTML or code-native graphics.

$ npx skills add mazen320/seedream-5-5-skill
Skill anzeigen→

pcb-render

github.com

把立创EDA/嘉立创EDA(EasyEDA)专业版导出的 PCB 素材包渲染成照片级 3D 效果图(Blender Cycles):STEP 3D + DXF 图形层 → 每个元件独立分色的 PBR 材质、蓝色阻焊 + 金色焊盘 + 白色丝印 + 铜箔走线,输出 2K/4K 主图、俯视图、微距。Use when the user asks to render a PCB / circuit board / product shot / 电路板效果图 / 板子 3D 图 from an EDA export package (.zip containing *.step + *.dxf), or asks to re-render an existing board at another angle/resolution, or asks to add a macro/bottom view. 中文触发:渲染 PCB、电路板效果图、板子 3D、出图、换角度重渲、加微距、导出的素材包渲染。

$ npx skills add maker114/PCB-Render-Kit
Skill anzeigen→

desenho-de-veiculos

github.com

Desenhar veículos e implementos (caminhão, cavalo mecânico, carreta, ônibus, van, carro, máquina pesada) com realismo e medidas corretas: SVG 2D em vistas ortográficas (lateral, de cima, frente, traseira) e modelo 3D de verdade (Blender pelo MCP, ou three.js com a skill teardown), a partir de referência real (foto, planta, ficha técnica). Usar quando pedirem para desenhar, redesenhar, deixar mais realista, conferir ou comparar com a referência o desenho de um veículo, ou modelá-lo em 3D. NÃO usar para ícone, logotipo, gráfico ou ilustração genérica.

$ npx skills add LucasDias777/skills-e-mcps
Skill anzeigen→

fractalwright

github.com

Render, animate, measure and identify fractals as reproducible recipes (PNG or mp4 plus a recipe JSON that redraws it): Mandelbrot, Julia, Burning Ship and Multibrot stills, deep zooms, zoom, morph and loop videos with a flash check, audio-reactive music videos and visualizers from a song, fractal flames, IFS, L-systems, strange attractors, fBm terrain, box-counting dimension. Use whenever the user wants a fractal image, wallpaper or video, asks 'render a Mandelbrot zoom', 'make a fractal flame', 'winamp-style visualizer for this song', 'what fractal is this picture', 'measure the fractal dimension of this coastline', or wants to redraw a fractal exactly. Also 'refresh fractalwright'. Not for general shaders (threewright), mastering music (musicwright) or pixel art (pixelwright).

$ npx skills add m4bwav/fractalwright
Skill anzeigen→

brand-kickstart

github.com

Brainstorm brand or project names and check which ones are free as the same handle on Instagram, Threads, Facebook, TikTok, YouTube, X, GitHub, npm, PyPI and as domains (.com, .id, ...), then draws a logo, favicons, app icons and social banners for the chosen name. Use when the user is naming a brand, business, creator account, app, library or product, asks whether a username, handle or domain is available, wants consistent social media handles, or wants a logo, favicon, app icon or social banner for a brand.

$ npx skills add M-Julius/brand-kickstart
Skill anzeigen→

Game Asset Pipeline

github.com

Local AI game asset generation pipeline for sprites, textures, 3D props, and video. Covers model selection, workflows, quality, and licensing for indie game dev.

$ npx skills add konqiDAM/void-skills
Skill anzeigen→

modernist-synthesis

github.com

Develop a contemporary editorial visual language that synthesizes modern Japanese graphic design, Swiss typography, minimalist architectural thinking, Bauhaus form-and-colour studies, and culturally grounded illustration. Use when this synthesis is requested by name or by these combined influences, to direct, create, adapt, or critique visual work across subjects and media, including image-generation prompts. A generic request for a poster, minimalist layout, or Japanese imagery alone is insufficient.

$ npx skills add fedeclavero/modernist-synthesis
Skill anzeigen→

excalidraw-architecture

github.com

Use when asked to diagram, draw, sketch, or visualise a software architecture, message flow, event-driven or microservices system in Excalidraw. Produces .excalidraw files in Enterprise Integration Patterns notation (channels, routers, translators, endpoints, DLQs, sagas) from a small JSON spec via scripts/eip_excalidraw.mjs, with a preview SVG and a render check. Not for UI mockups, slide decks, or freeform whiteboarding.

$ npx skills add jamescarr/diagram-skill
Skill anzeigen→

cad-view

github.com

Resolves STEP assembly occurrences and exports target-isolated orthographic SVG views with provenance manifests. Use for requests such as "export the front view of this door", "render only this occurrence", or "create a vector illustration for a document". Supports spatial selectors and an explicitly assumed-front heuristic; preserves camera versus semantic-front assumptions and never infers dimensions from pixels. PNG, photorealistic rendering, VLM interpretation, and declared/functional front recognition are not implemented.

$ npx skills add EthanLoveQueen/cad-to-facts
Skill anzeigen→

krita-flat-colouring

github.com

Segment clean Krita lineart into watertight semantic material regions using connected-component topology, Voronoi EDT attribution, contour polygon selections, +0.58 px Krita 6.0.4 brush fills, and non-destructive alpha-locked layer hierarchies. Strictly terminates at uniform flat base colours with zero shading, lighting, gradients, or autonomous rendering.

$ npx skills add ashdawgthegoat/krita-illustration-skills
Skill anzeigen→

cad-parts

github.com

Author physical 3D parts as local .stl/.step files with CadQuery, run as one-shot RAM-watchdogged subprocesses against C:\cadquery-venv. Use whenever the user wants to design, model, create, resize, trim, or remix a printable part (an adapter, standoff, spacer, bracket, mount, enclosure, keycap, robot or chassis piece), asks for an STL or STEP file, wants a dimension changed on an existing part script, wants a part rendered, measured, or verified, wants a broken STL repaired, or wants a part re-checked against a parent part that changed, even if they never say "CadQuery" or "CAD". NOT for PCB design or slicer/print settings.

$ npx skills add ColinE0/cad-parts
Skill anzeigen→

krita-lineart-reconstruction

github.com

Reconstruct clean, native Krita lineart at native 1x resolution using G1 cubic Bezier fitting, Priority-Queue Recursive Cubic Bezier Subdivision, dual-regime Krita 6.0.4 brush pressure calibration, +0.58 px coordinate calibration, and closed-loop visual feedback. Strictly scoped to lineart only (no supersampling, no flat colouring, no shading or autonomous rendering).

$ npx skills add ashdawgthegoat/krita-illustration-skills
Skill anzeigen→

brand-board

github.com

Crea el brand board de una marca como diseño editable: un tablero principal (logotipo, paleta, sistema de logo, ilustración, símbolo, tipografía, voz y regla de color) más piezas de aplicación en tamaño real (afiches, una pieza informativa del rubro y posts para redes), cada una con un solo color protagonista. Usa el logo SVG, la paleta, las tipografías y las ilustraciones del usuario. Úsala siempre que pidan un brand board, tablero de marca, hoja de identidad, "mostrar la marca aplicada", mockups o piezas de ejemplo de una identidad, o aplicar un logo y paleta a afiches y posts, aunque no digan "brand board". No la uses para la estrategia o propuesta de marca en texto (eso es propuesta-branding), para el manual de marca o brandbook con normas de uso (eso es manual-de-marca), ni para diseñar el logo desde cero.

$ npx skills add albdanyb22/skills-branding
Skill anzeigen→

blender-live-rigging

github.com

Rig, edit, verify and export 3D assets live in the user's open Blender app through the official Blender MCP socket bridge. Use for armatures, skinning, mechanical/hinge rigs, drivers, custom-property controls, evaluated-mesh verification, baked glTF export, and renders only when the owner explicitly requests them.

$ npx skills add andypratama3/blender-mcp
Skill anzeigen→

archimaid

github.com

Write, validate and render ArchiMate® 3.2 diagrams as text in the archimate-beta Mermaid syntax. Use when the user asks for an ArchiMate diagram, an enterprise architecture view (business, application, technology layers, capabilities, motivation), or edits .mmd files or Markdown mermaid blocks that start with archimate-beta.

$ npx skills add Archimaid/claude-plugin
Skill anzeigen→

pr-diagram

github.com

Draw a Mermaid (.mmd) diagram of what a pull request changes, so reviewers see the flow before reading the diff. Use when the user says "pr diagram", "diagram this PR", "visualize the PR", "draw the changes", "add a diagram to the PR", or /pr-diagram. Takes a PR number/URL, or uses the current branch. Picks the diagram type from the change, color-codes new/changed/unchanged parts, and offers to post it to the PR description after showing the full new description for approval.

$ npx skills add amihali1/claude-skills
Skill anzeigen→