[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DBS4BSX2FKB38ZMHBVD0XG":3,"skill-same:01M7DBS4BSX2FKB38ZMHBVD0XG":71},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M7DBS4BSX2FKB38ZMHBVD0XG","image-poster",null,"Single-image generation skill for posters, key art, and editorial\nillustrations. Defaults to gpt-image-2 but is provider-agnostic — the\nsame workflow drives Flux, Imagen, or Midjourney via the active\nupstream tooling. Output is one or more PNG\u002FJPEG files saved to the\nproject folder.","feimacode\u002Fopen-design-agent-kit","feimacode","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264390570?v=4","01M7D3HQSP5EP4Z4JECTSQ7EBD","Feima Code","01M7D3HQT72Q4EVQJP89MR9WP1",1129,"MIT","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fexamples\u002Fimage-poster\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: image-poster\ndescription: |\n  Single-image generation skill for posters, key art, and editorial\n  illustrations. Defaults to gpt-image-2 but is provider-agnostic — the\n  same workflow drives Flux, Imagen, or Midjourney via the active\n  upstream tooling. Output is one or more PNG\u002FJPEG files saved to the\n  project folder.\ntriggers:\n  - \"poster\"\n  - \"key art\"\n  - \"illustration\"\n  - \"image\"\n  - \"cover art\"\n  - \"海报\"\n  - \"插画\"\nod:\n  mode: image\n  surface: image\n  scenario: design\n  preview:\n    type: html\n    entry: example.html\n  design_system:\n    requires: false\n  example_prompt: |\n    Editorial poster for an indie film festival — one bold abstract\n    silhouette over a warm, slightly grainy paper background; hand-set\n    sans serif title at the top, festival dates and venue at the bottom\n    in monospace. Muted ochre + ink palette.\n---\n\n# Image Poster Skill\n\nProduce **one** finished image asset per turn unless the user asks for\nvariations. Image generation rewards a tight, structured prompt — your\njob is to assemble that prompt from the user's brief, then dispatch.\n\n## Resource map\n\n```\nimage-poster\u002F\n├── SKILL.md         ← you're reading this\n└── example.html     ← what the resulting card looks like in Examples\n```\n\n## Workflow\n\n### Step 0 — Read the project metadata\n\nThe active project carries `imageModel`, `imageAspect`, and (optional)\n`imageStyle` notes. Use them as the upstream model + canvas + style\nanchor. When a value is not provided, infer a safe default from the brief and\nmedia contract. Ask only when the choice would materially change the requested\nresult and no safe default can be inferred.\n\n### Step 1 — Compose the prompt\n\nPlan in this exact order before calling any tool:\n\n1. **Subject + composition** — what is in the frame, where, at what\n   scale; eye-line and crop.\n2. **Lighting + mood** — natural \u002F studio \u002F moody; warm \u002F cool; key\n   plus rim plus fill; time of day if outdoor.\n3. **Palette + textures** — hex anchors when the user gave a brand\n   palette; otherwise a 3-word mood tag (e.g. \"muted ochre + ink\").\n4. **Camera \u002F lens** — only if the user wants photographic realism\n   (\"85mm portrait, shallow DOF\") or a specific film stock.\n5. **What to avoid** — common AI-slop patterns (\"no extra fingers, no\n   warped text, no logo placeholders\").\n\n### Step 2 — Dispatch via the media contract\n\nUse the unified dispatcher — do **not** call upstream provider APIs by\nhand. Run from your shell tool:\n\n```bash\n\"$OD_NODE_BIN\" \"$OD_BIN\" media generate \\\n  --project \"$OD_PROJECT_ID\" \\\n  --surface image \\\n  --model \"\u003CimageModel from metadata>\" \\\n  --aspect \"\u003CimageAspect from metadata>\" \\\n  --output \"\u003Cshort-descriptive-name>.png\" \\\n  --prompt \"\u003Cthe full assembled prompt from Step 1>\"\n```\n\nThe command prints one line of JSON: `{\"file\": {\"name\": \"...\", ...}}`.\nThe daemon writes the bytes into the project folder; the FileViewer\npicks it up automatically.\n\n### Step 3 — Hand off\n\nReply with a one-paragraph summary of the prompt you used and the\nfilename returned by the dispatcher (e.g. *I generated `hero-poster.png`\nwith `gpt-image-2` at 1:1.*). Do **not** emit an `\u003Cartifact>` tag.\n\n## Hard rules\n\n- One image per turn unless asked for variations.\n- Honor `imageAspect` exactly — the upstream cost is the same; matching\n  the aspect avoids a re-render.\n- No filler typography in the image itself unless the user asked for\n  in-frame text. Real copy beats lorem.\n- Save every render — never describe an image without producing the\n  file. The user expects something to open in the file viewer.\n","# Image Poster Skill\n\nProduce **one** finished image asset per turn unless the user asks for\nvariations. Image generation rewards a tight, structured prompt — your\njob is to assemble that prompt from the user's brief, then dispatch.\n\n## Resource map\n\n```\nimage-poster\u002F\n├── SKILL.md         ← you're reading this\n└── example.html     ← what the resulting card looks like in Examples\n```\n\n## Workflow\n\n### Step 0 — Read the project metadata\n\nThe active project carries `imageModel`, `imageAspect`, and (optional)\n`imageStyle` notes. Use them as the upstream model + canvas + style\nanchor. When a value is not provided, infer a safe default from the brief and\nmedia contract. Ask only when the choice would materially change the requested\nresult and no safe default can be inferred.\n\n### Step 1 — Compose the prompt\n\nPlan in this exact order before calling any tool:\n\n1. **Subject + composition** — what is in the frame, where, at what\n   scale; eye-line and crop.\n2. **Lighting + mood** — natural \u002F studio \u002F moody; warm \u002F cool; key\n   plus rim plus fill; time of day if outdoor.\n3. **Palette + textures** — hex anchors when the user gave a brand\n   palette; otherwise a 3-word mood tag (e.g. \"muted ochre + ink\").\n4. **Camera \u002F lens** — only if the user wants photographic realism\n   (\"85mm portrait, shallow DOF\") or a specific film stock.\n5. **What to avoid** — common AI-slop patterns (\"no extra fingers, no\n   warped text, no logo placeholders\").\n\n### Step 2 — Dispatch via the media contract\n\nUse the unified dispatcher — do **not** call upstream provider APIs by\nhand. Run from your shell tool:\n\n```bash\n\"$OD_NODE_BIN\" \"$OD_BIN\" media generate \\\n  --project \"$OD_PROJECT_ID\" \\\n  --surface image \\\n  --model \"\u003CimageModel from metadata>\" \\\n  --aspect \"\u003CimageAspect from metadata>\" \\\n  --output \"\u003Cshort-descriptive-name>.png\" \\\n  --prompt \"\u003Cthe full assembled prompt from Step 1>\"\n```\n\nThe command prints one line of JSON: `{\"file\": {\"name\": \"...\", ...}}`.\nThe daemon writes the bytes into the project folder; the FileViewer\npicks it up automatically.\n\n### Step 3 — Hand off\n\nReply with a one-paragraph summary of the prompt you used and the\nfilename returned by the dispatcher (e.g. *I generated `hero-poster.png`\nwith `gpt-image-2` at 1:1.*). Do **not** emit an `\u003Cartifact>` tag.\n\n## Hard rules\n\n- One image per turn unless asked for variations.\n- Honor `imageAspect` exactly — the upstream cost is the same; matching\n  the aspect avoids a re-render.\n- No filler typography in the image itself unless the user asked for\n  in-frame text. Real copy beats lorem.\n- Save every render — never describe an image without producing the\n  file. The user expects something to open in the file viewer.\n",{"od":24,"name":5,"triggers":32,"description":39},{"mode":25,"preview":26,"surface":25,"scenario":29,"design_system":30,"example_prompt":31},"image",{"type":27,"entry":28},"html","example.html","design",{"requires":20},"Editorial poster for an indie film festival — one bold abstract\nsilhouette over a warm, slightly grainy paper background; hand-set\nsans serif title at the top, festival dates and venue at the bottom\nin monospace. Muted ochre + ink palette.",[33,34,35,25,36,37,38],"poster","key art","illustration","cover art","海报","插画","Single-image generation skill for posters, key art, and editorial\nillustrations. Defaults to gpt-image-2 but is provider-agnostic — the\nsame workflow drives Flux, Imagen, or Midjourney via the active\nupstream tooling. Output is one or more PNG\u002FJPEG files saved to the\nproject folder.\n","main","e38061066b92c298798dbddc1decbae8c026464f","packages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fexamples\u002Fimage-poster",104,"https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit","https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=feima.open-design-agent-kit","https:\u002F\u002Fgithub.com\u002Ffeimacode","2026-11-14 17:32:48",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add feimacode\u002Fopen-design-agent-kit --skill image-poster",{"tool":54,"command":55},"bunx","bunx skills add feimacode\u002Fopen-design-agent-kit --skill image-poster",{"tool":57,"command":58},"pnpm","pnpm dlx skills add feimacode\u002Fopen-design-agent-kit --skill image-poster","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fexamples\u002Fimage-poster\u002FSKILL.md",true,[62,67],{"path":28,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"REFERENCE","参考文档",3651,"https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fexamples\u002Fimage-poster\u002Fexample.html",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"open-design.json",8142,"https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fexamples\u002Fimage-poster\u002Fopen-design.json",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DDR9C4RR6E8F46YBJ8MW64","youtube-clipper","YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7DDR57XHXAFBGKX3SYTGSJB","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7DDR2RM4F3FM5642JZBGJSF","wpds","WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fwpds\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DDQX3G9QDCBV5GGZGQ1NZN","weread-year-in-review-video-template","WeRead-inspired HyperFrames video template for vertical annual reading reports,\npersonal reading dashboards, book-note recaps, and shareable year-in-review\nstories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper\ntexture, editorial Chinese typography, book-page metaphors, data highlights,\nand deterministic motion.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fweread-year-in-review-video-template\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7DDQRGJEHQST6TXDH6ZAV5G","web-design-guidelines","Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7DDQKADVPZW1Z1HTVKXY542","web-clone","网站复刻 \u002F 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互\u002FWebGL\u002FCanvas\u002FThree.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 \u002F React-Vue-Next 内容站 \u002F WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。","https:\u002F\u002Fgithub.com\u002Ffeimacode\u002Fopen-design-agent-kit\u002Fblob\u002Fmain\u002Fpackages\u002Fvscode\u002Fassets\u002Fopen-design\u002Fskills\u002Fweb-clone\u002FSKILL.md",[],[]]