Image

Finds open-licence illustrations and stock photos, recolors art to the tokens and wires it in. Also adds icons drawn like the few a product already has, from open sets, with their licences.

Produce release-grade 2D game art with AI image generation plus post-processing — style bible, per-asset prompts, consistency control, background keying, spec-compliant resizing, nine-slice validation and final asset gate. Use when the user needs real shippable art instead of placeholder rectangles.

Turn a set of scores/metrics into an accurate AND illustrative graphic — the data literally drives the shape of the artwork, so it's provably faithful while reading as a designed illustration instead of a generic chart.

SVG 可视化专家：作为跨领域专家团队（技术插画师+可视化专家+教育内容设计师），将用户输入的概念或内容转化为高质量、符合 W3C 标准的 SVG 图形，默认 16:10 比例，中文输出。触发词：画图、可视化、svg、图解、画个图、把...可视化、svg-visualizer。

Refactor image-generation or editing prompts into explicit change/preserve constraints and functional reference-image roles.

Generate logos, icons, UI mockups, hero images, product shots, and other design assets using OpenAI GPT Image 2.5 (Sunburst, Flare) or Google Gemini (Nano Banana 2, Nano Banana Pro, Nano Banana 2 Lite). Use whenever the user asks to create, design, generate, mock up, render, or illustrate a visual asset, needs a transparent PNG, or asks for image prompt engineering. Picks the right model and quality for the job, writes a model-specific prompt following the official prompting rules of each...

> 用代码画手绘笔记风（sketchnote）的中文教学配图：写一份 JSON（标题、蓝圆输入 / 橙方生产 / 绿六边形反馈节点、 箭头、批注、图例、清单、便利贴），scripts/render.py 用本机 Chrome 出 PNG，图里每个字都来自 JSON，不会写错字。 适合字多、要反复改的教程图解、流程图、对比图、封面；默认 16:9（3200×1800），竖版平台用 3:4。 也能在浏览器里打开编辑器，让用户拖动、双击改字、⌘S 存回。 触发语："用配图工具画一张图""给这一章配图""画一张手绘笔记风的图""把这段做成图解""改一下这张配图的 JSON""出一下配图"。 需要 macOS（系统自带手写字体）和 Google Chrome。

> 把文章、提纲或一段想法做成单张或一套风格统一的图片：先问清风格与文字密度， 再输出逐张完整、节点化的 JSON 生图提示词，可继续调用可用工具生图。 也能七维拆解一张图片（逐字转录图中文字），并把做过的图或拆过的图存成模板，下次点名复用。 适用于小红书图文、知识图解、信息图、漫画、绘本、海报、PPT、图鉴、练习纸等。 触发语：「把这篇文章做成图」「做一张/一套小红书图」「写生图提示词」「做成 10 张知识卡」「做一页 PPT 配图」 「拆解这张图」「反推这张图的提示词」「把这套存成模板」「用模板 U001」「我有哪些模板」。

Use whenever reference images, views or textures for a 3D model are needed, before modelling or image-to-3D: orthographic front, side and back views with a height bar, A-pose turnarounds, multi-view sets, blockout renders repainted into consistent views, seamless textures and quick normal/height/roughness maps (pw.py texture). Use on 'what references do I need', 'reference sheet', 'front side back views', 'turnaround', 'seamless texture', 'PBR maps from this photo'. Not for flat graphic...

Use whenever an imagined or hypothetical 3D model must be made from a prompt, a drawing, concept art, photos or a blockout: image-to-3D through ComfyUI (TRELLIS.2, Pixal3D, Hunyuan3D-2 via pw.py gen) or hosted (Meshy, Tripo, Rodin), or code (bpy, build123d, CadQuery, OpenSCAD) when it has dimensions; then texturing and the licence record. Use on 'make me a 3D model of a dragon', 'turn this drawing or concept art into 3D', 'image to 3D', 'text to 3D', 'TRELLIS', 'Hunyuan3D', 'Meshy', 'model a...

Edit a photo the way a hired Lightroom photographer would. Read the photo, agree the vibe, show rendered directions side by side, then edit in rounds (render, self-review, show, take notes) until the photo hits the vibe, and hand back the final image for Instagram, LinkedIn or a story. Covers grades and looks, exposure, colour, crop, region edits (face, eyes, sky, mountains, person, background, any object) and object removal. Use when the user shares a photo and asks for edits or a look...

Start here whenever a task needs a 3D model and no sibling below clearly owns it: a model of a real or imagined thing for a game (Unity, Roblox, Unreal, three.js), a 3D print, AI video or AR, or another plugin asking for a mesh. Picks the route (find, capture, generate, code), scaffolds the asset folder and manifest other plugins read, and runs pw.py (inspect, render a sheet, convert, check a budget, bpy headless, match a picture's camera, army blockouts with depth and pose passes for AI...

Use whenever Blender is scripted, automated or debugged, before writing any bpy code: headless runs that report errors (pw.py bpy), the bpy API traps models still write in Blender 5.x (removed importers, renamed sockets, EEVEE names), tested recipes (modifiers, booleans, remesh, UVs, bakes, turntables, depth passes, batch exports), Blender MCP servers and their risks, and other 3D tools per OS. Use on 'write a Blender script', 'automate Blender', 'batch export .blend', any bpy traceback or...

Use whenever a mesh must be made ready for a game engine, the web or AR: is it game-ready, too many polygons, LODs, retopology, UVs, baking, PBR and normal-map conventions, collision, rigging, and axis, unit and format export for Roblox, Unity, Unreal, Godot, three.js (meshopt, KTX2), USDZ and video blockouts. Use on 'is this game-ready', 'make this work in Roblox/Unity', 'optimise for the web', 'reduce polygons', 'add LODs', 'retopologise', 'bake normals', 'imports sideways or tiny', 'flip...

Localize marketing text embedded in existing App Store screenshot PNGs while preserving the original product imagery pixel-for-pixel outside explicit text regions. Use when adapting already-designed screenshots to additional storefront languages, replacing screenshot headlines without redesigning artwork, validating Apple screenshot dimensions and alpha rules, or preparing reviewed screenshot uploads with the asc CLI.

Create image prompts, scoped negatives and canonical references for humans, animals, anthropomorphic animals, creatures, monsters, hybrids, robots and androids. Use for character generation or illustration; editing an existing image to replace clothing, objects, backgrounds or lighting; prompt writing, assessment, revision, translation, expansion or variation; OCs, fursonas, mascots, VTubers, worlds, themes, personalities, casts, relationships and narratives; recurring-character continuity;...

Use when you need a carousel post for Instagram, TikTok, or Facebook. Pick a ready-made numbered template (for example \"template 3, topic: ...\") and get rendered JPG slides right away, or build a custom design system first. Real images only, quality-gated render.

FilmForge painter: writes every shot's image prompt from the shot list, the character sheets and the style lock, on a fixed twelve-slot order with continuity anchors (handles, anchors, scale locks, props, states, forbidden-colour clauses); keeps the continuity ledger; lints every prompt before a credit is spent; paints in batches of four and hands each batch to frame QA. Use this skill whenever the user wants image prompts for a film's shots or a picture book's pages, storyboard frames,...

FilmForge frame QA: inspects every painting at full size against the character sheets and the continuity ledger, measures colour rules, palette and exposure with tools, scores it on a nine-criterion rubric and decides: accept, fix in code (naming the module and the exact parameters), or repaint (with the root cause and the full corrected prompt). Use this skill whenever paintings, stills, keyframes, character sheets or book pages come back from an image model, when the user asks whether...

FilmForge style lock: fixes one image model and setting, one look sentence (or two when the drawing itself carries the story), the palette and colour rules, the line, brush and lens language, the character-sheet specs with scale bars, and the prompt grammar every shot must follow, so every painting in a film or book matches. Use this skill whenever the user starts the visual side of a film, music video or picture book, wants consistent characters or one consistent look across many images,...

Edit a photo with GPT Image using the user's prompt plus preservation constraints, then learn structure-gated local RGB mappings and apply them to the native original while retaining the edited background and transparency. Use for photo style or background edits that should retain real detail and target color and lighting.

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers include title slide image, thumbnail with text, on-image text, legible text in image, brand color palette image, bounding-box layout, Ideogram.

Reverse-engineer a reference image into a visible extraction report and reusable prompts. Extracts style, lighting, lens and optics, color palette and grading, composition, materials and post-processing, each value tagged as observed, inferred or unknown. 根据图片提取风格、光线、镜头、调色色调与构图材质，出结构化反推报告与可复用提示词。 Four modes: extraction report, high-fidelity recreation prompt, style-only extraction with the subject stripped for reuse on a new subject, and person-swap recreation that rebuilds an image with a...

Accept images or PDFs and output a typed, searchable PDF while preserving the original page layout, short lines, whitespace, side notes, colors, tables, diagrams, and mathematical notation. Use for digitizing handwritten notes, photos, scanned PDFs, or mixed printed/handwritten pages rather than summaries or redesigned notes.