[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BSNM53P7BD7FGE501CSH16":3,"skill-same:01M7BSNM53P7BD7FGE501CSH16":59},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7BSNM53P7BD7FGE501CSH16","atelier-zero-image-generation-prompt-pack-mrrxpegw",null,"YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002Fcommunity\u002Fatelier-zero-image-generation-prompt-pack-mrrxpegw\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"# Atelier Zero — Image Generation Prompt Pack\n\nThis pack is consumed by the `open-design-landing` skill. Every page-level\nimage is rendered with `gpt-image-fal` (preferred) or `gpt-image-azure`.\n\nThe pack has three layers:\n\n1. **Style anchor** — the long block that tells the model what\n   universe we are in. Always prepend to every prompt.\n2. **Variable slots** — the per-render content (subject, motifs,\n   accent, page type).\n3. **Per-slot variants** — explicit composition templates for hero,\n   about, capabilities, method tiles, lab cards, work cards,\n   testimonial, and CTA.\n\nRender at 1024×1024 minimum for square slots (hero \u002F about \u002F capabilities\n\u002F testimonial \u002F cta), 816×816 for the four method tiles, and 768×1024 for\nportrait slots (lab cards, featured work). Authoritative per-slot\ndimensions and aspect ratios live in `image-manifest.json` — treat that\nfile as the source of truth. Save as PNG to `assets\u002F\u003Cslot>.png`.\n\n---\n\n## 1. Style anchor (always prepend)\n\n```text\nUse case: ads-marketing\n\nAsset type: editorial website hero \u002F creative studio landing page visual\n\nPrimary request: Generate a refined editorial web page composition in the\nsame visual language as a high-end creative AI research studio.\n\nStyle\u002Fmedium: sophisticated digital collage, modern Swiss editorial layout,\nBauhaus geometric composition, classical plaster sculpture fragments,\nbrutalist\u002Fminimal architecture, art-direction website mockup, premium\nagency aesthetic.\n\nScene\u002Fbackdrop: warm off-white handmade paper background with subtle\ngrain, faint vertical folds, scanned paper fibers, lightly aged print\ntexture, thin drafting lines and registration marks.\n\nSubject: a surreal collage combining a cropped classical plaster head or\nface fragment, abstract architectural blocks, archways or stairs, sky\ncutouts, one small human figure, a delicate tree or botanical element,\nand geometric color planes.\n\nComposition\u002Fframing: wide 16:9 web page layout, strong asymmetrical\ngrid, generous negative space, large typography area on the left or\ntop-left, collage focal object on the right or center-right, precise\nalignment, thin divider lines, small UI navigation details.\n\nLighting\u002Fmood: soft diffused daylight, museum-like calm, intelligent,\nrestrained, tactile, poetic, premium, research-driven.\n\nColor palette: warm ivory, stone beige, soft concrete gray, deep black\ntext, muted charcoal, washed coral-red accent, occasional mustard-yellow\naccent, pale sky blue only inside small sky\u002Fimage cutouts.\n\nMaterials\u002Ftextures: matte plaster, limestone, travertine, concrete, rough\ntorn paper edges, halftone print grain, translucent vellum-like overlays,\nfine grid paper, dotted matrix patterns.\n\nTypography: large clean grotesk sans-serif for main headline, elegant\nhigh-contrast italic serif for emphasized words, tiny uppercase coral\nlabels, compact UI microcopy. Text must be crisp, readable, and spelled\nexactly as provided.\n\nGraphic details: thin hairline circles, partial arcs, crosshair marks,\nsmall black dots, dotted grids, fine coordinate lines, numbered\nannotations, small arrow buttons, simple pill buttons, minimal logo mark.\n\nConstraints: preserve a high-end editorial web design feel; keep spacing\nelegant and uncluttered; no cartoon style; no neon colors; no glossy 3D;\nno busy gradients; no generic stock-photo look.\n\nAvoid: distorted typography, misspelled text, extra random words, heavy\nshadows, childish illustration, cyberpunk, saturated purple\u002Fblue palette,\nplastic materials, overly decorative UI cards, cluttered composition,\nlow-resolution textures, watermarks.\n```\n\n## 2. Variable slots (substitute per render)\n\n```text\nBrand\u002Flogo text:        \"\u003CBRAND_NAME>\"\nNavigation text:        \"\u003CNAV_1>\", \"\u003CNAV_2>\", \"\u003CNAV_3>\", \"\u003CNAV_4>\", \"\u003CNAV_5>\"\nEyebrow label:          \"\u003CEYEBROW>\"\nMain headline:          \"\u003CMAIN_HEADLINE>\"\nItalic emphasis words:  \"\u003CITALIC_WORDS>\"\nBody copy:              \"\u003CBODY_COPY>\"\nPrimary button:         \"\u003CPRIMARY_CTA>\"\nSecondary button:       \"\u003CSECONDARY_CTA>\"\nFooter\u002Fmicro labels:    \"\u003CFOOTER_LABELS>\"\nMain collage subject:   \u003Cplaster head | eye | hand | arch | stair | tree | landscape | object>\nInserted texture motifs:\u003Csky, mountain, ocean, eye close-up, dancer, stone, fabric, map, grid, handwritten note>\nAccent color:           \u003Cwashed coral red | mustard yellow | pale blue | muted sage>\nPage type:              \u003Chero | about | capabilities | method tile | lab card | work card | testimonial | cta>\n```\n\n## 3. Per-slot composition templates\n\n### `hero.png` — 1:1 (1024×1024)\n\n```text\nComposition\u002Fframing: left half is intentionally empty\u002Fquiet to allow real\nHTML headline overlay; right half holds a tall surreal collage of a\ncropped classical plaster head with the top sliced open, sky\u002Farchitecture\ncutouts visible inside the head, a delicate young tree growing through\nthe composition, a coral sun disk behind, a mustard accent ring at the\nbase, hairline coordinate marks and dotted matrices around it, a small\nhuman figure standing for scale in the lower-left of the image. Page\ntype: hero landing.\n```\n\n### `about.png` — 1:1 (1024×1024)\n\n```text\nComposition: a surreal museum-vitrine arrangement of a partial plaster\nprofile head facing right, with an open archway carved through the\ntorso, sky cutout inside the arch, a tree seedling growing out of the\nshoulder, and a coral half-circle behind the head. Tiny dotted hairlines\ntrace contours. Strong negative space top-left for a side-note overlay.\nPage type: about \u002F manifesto plate.\n```\n\n### `capabilities.png` — 1:1 (1024×1024)\n\n```text\nComposition: a Bauhaus-grid stack of architectural fragments — a coral\narch on the left, a beige concrete column center, a mustard small disc\nupper-right, a delicate tree mid-frame, a small classical hand fragment\nholding a pencil bottom-center. Crosshair and circular hairlines\noverlay. Page type: capabilities matrix.\n```\n\n### `method-1.png` … `method-4.png` — 1:1 (816×816)\n\n```text\nComposition: a single visual metaphor per step.\n  method-1 — a magnifying glass over a small architectural map (Detect)\n  method-2 — a clipboard with a tiny questionnaire and a coral pen (Discover)\n  method-3 — a compass + ruler + color swatch fan (Direct)\n  method-4 — a printer's tray with stacked paper sheets exiting (Deliver)\nEach on the warm paper ground with hairline grid, a single coral or\nmustard accent piece, and one numbered annotation tag. Page type:\nmethod tile.\n```\n\n### `lab-1.png` … `lab-5.png` — 3:4 (768×1024)\n\n```text\nComposition: portrait-oriented experiment cards. Each is a square-ish\nplaster-and-architecture vignette, vertical, with a single dominant\nsubject:\n  lab-1 — a stack of folded magazine spreads\n  lab-2 — a film strip + a synthetic eye + a soundwave hairline\n  lab-3 — a typewriter with prompt cards in the carriage\n  lab-4 — five small dotted gauges arranged in a circle (5-dim critique)\n  lab-5 — a glass dome \u002F cloche over a tiny sandbox cityscape (Sandbox)\nUse the same paper ground; allow soft drop shadow but stay restrained.\nPage type: lab card.\n```\n\n### `work-1.png` & `work-2.png` — 3:4 (768×1024)\n\n```text\nComposition: featured work plates.\n  work-1 — guizang-ppt: an oversized open magazine spread on a desk,\n           coral spine, mustard tab. Slight perspective.\n  work-2 — dating-web: a concrete dashboard slab, a coral graph bar\n           rising, a small classical bust beside it for scale.\nBoth on the warm paper ground with crop marks.\nPage type: work card.\n```\n\n### `testimonial.png` — 1:1 (1024×1024)\n\n```text\nComposition: a classical plaster bust facing 3\u002F4 left, slightly cropped,\nwith a small sky cutout where the eye would be, a thin coral arc around\nthe back of the head, mustard dot at the chin. Quiet background, lots of\nnegative space upper right. Page type: testimonial portrait.\n```\n\n### `cta.png` — 1:1 (1024×1024)\n\n```text\nComposition: a closing-plate collage — a mustard sun behind a single\ncoral arch on the right, a delicate tree growing through the arch, a\nsmall human figure in the lower-left foreground reading a folded\nbroadsheet, hairline coordinate ladder up the left edge, and a small\n\"FIN.\" dotted seal in the upper-right. Page type: closing CTA plate.\n```\n\n## 4. Chinese project input template\n\nUse only when the model copy must be Chinese; otherwise prefer English\nfor legibility. Keep verbatim text short.\n\n```text\n请生成一张 16:9 横版网页视觉稿，风格为高级创意 AI 工作室官网：现代瑞士编辑排版、\n包豪斯几何、古典石膏雕塑拼贴、极简建筑、手工纸张肌理、细线工程制图标记。\n\n品牌文字：\"\u003C品牌名>\"\n导航：\"\u003C导航1>\", \"\u003C导航2>\", \"\u003C导航3>\", \"\u003C导航4>\"\n小标签：\"\u003C小标签>\"\n主标题必须逐字渲染：\"\u003C主标题>\"\n强调词（斜体衬线）：\"\u003C强调词>\"\n正文必须逐字渲染：\"\u003C正文>\"\n按钮文字：\"\u003C按钮1>\", \"\u003C按钮2>\"\n\n画面主体：\u003C主体描述>\n贴图与元素：\u003C天空 \u002F 石材 \u002F 植物 \u002F 人物 \u002F 眼睛 \u002F 山脉 \u002F 水面 \u002F UI 截图等>\n构图：\u003C左文右图 \u002F 右文左图 \u002F 顶部大标题下方横向卡片 \u002F 中央拼贴 \u002F 时间线分栏>\n色彩：暖象牙白纸张、黑色文字、石灰\u002F混凝土灰、炭黑、低饱和珊瑚红点缀、\n     少量芥末黄或浅天蓝。\n\n限制：文字清晰可读、不添加多余文字、不要水印、不要卡通、不要霓虹、\n     不要厚重阴影、不要俗套科技蓝紫渐变。\n```\n\n## 5. Calling convention\n\nPseudocode for an agent driver:\n\n```ts\nfor (const slot of imageManifest.slots) {\n  const prompt = [\n    STYLE_ANCHOR,\n    fillVars(VARIABLE_SLOTS, brand),\n    PER_SLOT[slot.id],\n  ].join('\\n\\n');\n\n  await gptImageFal({\n    prompt,\n    width:  slot.width,\n    height: slot.height,\n    quality: 'high',\n    output: `assets\u002F${slot.id}.png`,\n  });\n}\n```\n\nIf `gpt-image-fal` is unavailable, the same prompts work with\n`gpt-image-azure` — but mask-based inpainting is azure-only.\n\n## Provenance\n\nFormalized by Open Design from candidate fac45c04-0d8e-4cc8-ba38-7ccb32fde405.\n",{},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002Fcommunity\u002Fatelier-zero-image-generation-prompt-pack-mrrxpegw",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill atelier-zero-image-generation-prompt-pack-mrrxpegw",{"tool":37,"command":38},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill atelier-zero-image-generation-prompt-pack-mrrxpegw",{"tool":40,"command":41},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill atelier-zero-image-generation-prompt-pack-mrrxpegw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002Fcommunity\u002Fatelier-zero-image-generation-prompt-pack-mrrxpegw\u002FSKILL.md",true,[45,51,55],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"open-design.json","REFERENCE","参考文档",626,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002Fcommunity\u002Fatelier-zero-image-generation-prompt-pack-mrrxpegw\u002Fopen-design.json",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fprovenance.json",552,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002Fcommunity\u002Fatelier-zero-image-generation-prompt-pack-mrrxpegw\u002Freferences\u002Fprovenance.json",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fsource-1-imagegen-prompts.md",9931,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Design-设计资源\u002FYYC3-Design-设计资源-open-design\u002Fplugins\u002Fcommunity\u002Fatelier-zero-image-generation-prompt-pack-mrrxpegw\u002Freferences\u002Fsource-1-imagegen-prompts.md",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]