[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFEK6KHH8JEZWNJHPSXYXC":3,"skill-same:01M6CFEK6KHH8JEZWNJHPSXYXC":74},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6CFEK6KHH8JEZWNJHPSXYXC","generate-image",null,"Generate photos, illustrations, posters, and project assets through OpenBitFun's configured default image model. Shape prompts, inspect results, and make targeted refinements using generate_image. Not for image analysis, prompt-only discussions, or edits that must preserve an existing image.","openBitFun\u002FOpenBitFun","openBitFun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F272396808?v=4","01M70PGYVNDWCH7MV3FRCZWGVA","OpenBitFun","01M6CFDJ2B5TESE4PW4Y04PPY4",4022,"MIT","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fgenerate-image\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"generate","generate image","image","preserve","Existing","for","inspect","make","image analysis","project","photos","default","shape","prompts","only","results","prompt","assets","model","analysis","2026-11-10 10:12:30",false,"---\nname: generate-image\ndescription: Generate photos, illustrations, posters, and project assets through OpenBitFun's configured default image model. Shape prompts, inspect results, and make targeted refinements using generate_image. Not for image analysis, prompt-only discussions, or edits that must preserve an existing image.\n---\n\n# Generate Image\n\n## Define the asset\n\nInfer purpose, subject, framing, quantity, required text, and destination from context. Ask only for information that blocks success. Preserve detailed requests; enrich brief ones with useful composition, lighting, and material cues without inventing brands, slogans, characters, or story elements.\n\nPrefer native formats for existing SVGs, icon systems, and editable charts. Deliver actual raster images when the user asks for photos or illustrations.\n\n## Shape the prompt\n\nFor complex requests, use the following structure, keeping only useful fields. Choose the prompt language for the task; preserve required in-image text verbatim, including its original language and punctuation.\n\n```text\nPurpose: placement, audience, and intended effect\nContent: subject, action, setting, and essential details\nStyle: photo\u002Fillustration\u002F3D, materials, lighting, and palette\nComposition: viewpoint, framing, crop-safe margins, and necessary negative space\nText: exact copy, hierarchy, placement, and number of occurrences\nConstraints: required invariants and important exclusions\n```\n\n| Asset | Prompt emphasis |\n| --- | --- |\n| Photography and products | Describe texture, reflections, perspective, contact shadows, and product structure instead of stacking vague quality adjectives. |\n| Web assets and covers | Match the actual container and crop; place negative space around existing copy. Keep headings and buttons in page code when appropriate. |\n| Posters and infographics | Supply exact copy, verified data, relationships, hierarchy, and reading order. Do not let the model invent facts. |\n| Illustrations and sets | Repeat concrete medium, palette, lighting, and subject descriptions. Give each image one clear purpose. |\n\nUse `view_image` or `analyze_image` to describe visual references when available. The generation tool accepts no reference images, masks, or editing inputs; do not promise preserved identity, exact product details, or unchanged pixels.\n\n## Generate and inspect\n\n- Generate only with `generate_image`. Omit `service_id` by default to use the configured default image model. Do not mix in external `imagegen`, `image_gen`, genmedia, or direct API calls.\n- Use `n: 1` unless another quantity was requested. Call separately for distinct content; `n` is for variants of one prompt. Track actual returned counts without silently adding candidates.\n- Use `size` and `negative_prompt` only when supported by the service. Put style and layout in `prompt`; do not invent tool arguments.\n- When inspection is available, check subject and count, structure and cropping, verbatim text, and consistency across sets. Verify actual dimensions, format, and alpha when required; a white or checkerboard background is not transparency. Disclose unverified requirements.\n- Refine one specific defect at a time, retaining the original goal, valid constraints, and previous versions for comparison. Regeneration is not a local edit. Stop when the goal is met and stay within the user's quantity and budget.\n- Report configuration, authentication, quota, or transport failures without automatically switching services or retrying without cause. For configuration issues, point to Settings → Models → Image generation model.\n\n## Deliver\n\nShow or deliver images using returned file paths. Place project assets in the agreed asset directory, update references within the task's scope, and check their actual display. Keep previous versions unless replacement was requested. Operate on remote files through their workspace, not as controller-local files.\n\nReport delivered quantity, locations, and known limitations, including unmet text, size, transparency, or consistency requirements.\n","# Generate Image\n\n## Define the asset\n\nInfer purpose, subject, framing, quantity, required text, and destination from context. Ask only for information that blocks success. Preserve detailed requests; enrich brief ones with useful composition, lighting, and material cues without inventing brands, slogans, characters, or story elements.\n\nPrefer native formats for existing SVGs, icon systems, and editable charts. Deliver actual raster images when the user asks for photos or illustrations.\n\n## Shape the prompt\n\nFor complex requests, use the following structure, keeping only useful fields. Choose the prompt language for the task; preserve required in-image text verbatim, including its original language and punctuation.\n\n```text\nPurpose: placement, audience, and intended effect\nContent: subject, action, setting, and essential details\nStyle: photo\u002Fillustration\u002F3D, materials, lighting, and palette\nComposition: viewpoint, framing, crop-safe margins, and necessary negative space\nText: exact copy, hierarchy, placement, and number of occurrences\nConstraints: required invariants and important exclusions\n```\n\n| Asset | Prompt emphasis |\n| --- | --- |\n| Photography and products | Describe texture, reflections, perspective, contact shadows, and product structure instead of stacking vague quality adjectives. |\n| Web assets and covers | Match the actual container and crop; place negative space around existing copy. Keep headings and buttons in page code when appropriate. |\n| Posters and infographics | Supply exact copy, verified data, relationships, hierarchy, and reading order. Do not let the model invent facts. |\n| Illustrations and sets | Repeat concrete medium, palette, lighting, and subject descriptions. Give each image one clear purpose. |\n\nUse `view_image` or `analyze_image` to describe visual references when available. The generation tool accepts no reference images, masks, or editing inputs; do not promise preserved identity, exact product details, or unchanged pixels.\n\n## Generate and inspect\n\n- Generate only with `generate_image`. Omit `service_id` by default to use the configured default image model. Do not mix in external `imagegen`, `image_gen`, genmedia, or direct API calls.\n- Use `n: 1` unless another quantity was requested. Call separately for distinct content; `n` is for variants of one prompt. Track actual returned counts without silently adding candidates.\n- Use `size` and `negative_prompt` only when supported by the service. Put style and layout in `prompt`; do not invent tool arguments.\n- When inspection is available, check subject and count, structure and cropping, verbatim text, and consistency across sets. Verify actual dimensions, format, and alpha when required; a white or checkerboard background is not transparency. Disclose unverified requirements.\n- Refine one specific defect at a time, retaining the original goal, valid constraints, and previous versions for comparison. Regeneration is not a local edit. Stop when the goal is met and stay within the user's quantity and budget.\n- Report configuration, authentication, quota, or transport failures without automatically switching services or retrying without cause. For configuration issues, point to Settings → Models → Image generation model.\n\n## Deliver\n\nShow or deliver images using returned file paths. Place project assets in the agreed asset directory, update references within the task's scope, and check their actual display. Keep previous versions unless replacement was requested. Operate on remote files through their workspace, not as controller-local files.\n\nReport delivered quantity, locations, and known limitations, including unmet text, size, transparency, or consistency requirements.\n",{"name":5,"description":7},"main","3b649c6a86d5ada26f67391412fd0aee90b95652","src\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fgenerate-image",305,"https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun","openbitfun.com","https:\u002F\u002Fgithub.com\u002FopenBitFun","2026-11-15 02:03:36",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add openBitFun\u002FOpenBitFun --skill generate-image",{"tool":66,"command":67},"bunx","bunx skills add openBitFun\u002FOpenBitFun --skill generate-image",{"tool":69,"command":70},"pnpm","pnpm dlx skills add openBitFun\u002FOpenBitFun --skill generate-image","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fgenerate-image\u002FSKILL.md",true,[],[75,83,101,126,164,188],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"01M743HH8XDWZBVK8TTREYQPXF","openbitfun-skin-designer","Create or update an importable OpenBitFun visual skin from reference images or an art brief, using the target product's actual paint contract and checking the result in the existing UI.","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fopenbitfun-skin-designer\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":47},"01M6CFEP4X1GN4X24VH42JWHQ2","miniapp-dev","Generate, operate, and refine OpenBitFun MiniApps. Use when the user wants a new MiniApp, asks the Agent to inspect or operate a running MiniApp, or wants an existing MiniApp redesigned or extended. Typical triggers: \"做一个小应用\", \"操作这个 MiniApp\", \"查看小应用当前状态\", \"改造 mini app\".","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fminiapp-dev\u002FSKILL.md",[],[90,91,92,27,93,94,31,95,96,33,97,98,99,100],"miniapp dev","dev","use","refine","when","new","triggers","operate","app","running","user",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":110,"publishedAt":47},"01M6CFF33T7RM4A44X3X0K6YXN","openbitfun-frontend-dev","Safely customize the running packaged OpenBitFun desktop frontend through a draft, a provisional hot apply, and a 15-second user-confirmed rollback window. Use only in OpenBitFun Creative mode when the user asks to change OpenBitFun's own client UI.","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fopenbitfun-frontend-dev\u002FSKILL.md",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[111,91,112,113,114,115,94,116,117,118,99,100,119,120,121,122,123,124,92,41,125],"frontend","openbitfun frontend dev","frontend dev","mode","client","apply","draft","window","ui","creative","rollback","desktop","change","customize","second",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":147,"publishedAt":47},"01M6CFF99YP8CWRVWG5C6S06YS","ppt-design","使用 HTML 设计与生成高质量演讲幻灯片（PPT\u002FDeck）。当用户希望生成、设计、修改幻灯片、deck、slides、presentation、汇报、提案、pitch、课件时触发。主干：1280×720px 可编辑 HTML 幻灯片 + 唯一 editable HTML→EditableSlideScene→OOXML 管线 + 数据\u002F信息可视化意识 + 5 种设计哲学 + 反 AI slop + 单页自包含 `slide-XX.html`。不生图；缺图用可编辑原语或占位并标注建议补图。","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fppt-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fppt-design\u002FSKILL.md",[133,136,139,144],{"categoryNo":134,"categoryName":135,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":140,"categoryName":141,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":145,"categoryName":146,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000033","数据分析师",[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163],"pptx","design","ppt design","数据","deck","editable","presentation","ai slop","可视化","pitch","slop","演讲","html","提案","生成","slides",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":47},"01M6CFE1RT1YFKD6RCDE6KRY0T","create-agent","Create or update OpenBitFun custom modes and subagents. Turn the user's needs into a role prompt and a suitable tool selection, then save an agent definition. Use for reusable roles, not ordinary delegation to an existing subagent.","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fcreate-agent\u002FSKILL.md",[170],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[172,173,174,175,176,31,177,178,32,179,180,181,100,182,183,184,43,92,185,186,187],"create agent","create","subagents","role","roles","custom","modes","agent definition","definition","save","update","subagent","reusable","delegation","selection","tool",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":47},"01M6CFF5WX7MT7KVVQ9HTH6EYK","plan","Research and write an actionable implementation plan without implementing it. Use when the user asks to plan, design an approach, or inspect a change before coding; stop applying the planning restriction once the user explicitly asks to implement.","https:\u002F\u002Fgithub.com\u002FopenBitFun\u002FOpenBitFun\u002Fblob\u002Fmain\u002Fsrc\u002Fcrates\u002Fassembly\u002Fcore\u002Fbuiltin_skills\u002Fplan\u002FSKILL.md",[],[190,195,196,197,198,123,199,92,149,200,201,202,203,94,204,205,33,206,100],"coding","implementation","write","research","implement","planning","stop","it","to plan","implementation plan","implementing","actionable"]