[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-77809":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":14,"starSnapshotCount":14,"syncStatus":13,"lastSyncTime":29,"discoverSource":30},77809,"visual-style-ppt-skill","irenerachel\u002Fvisual-style-ppt-skill","irenerachel","【Skill】视觉风格 PPT 生成工作流",null,168,16,1,2,0,6,12,50,18,3.69,false,"main",true,[24,25],"claude-skill","skill","2026-06-12 02:03:44","# visual-style-ppt\n\nStyle-driven Codex Skill for turning documents, articles, and visual references into image-first presentation decks.\n\n## Highest Priority Rule\n\nThis skill must use the Image 2 model for every generated slide image, thumbnail board, visual page, infographic, article illustration, and PPT page image. HTML output is forbidden: do not use HTML\u002FCSS, browser screenshots, SVG\u002FHTML mockups, canvas renders, PIL, or local scripts as final or intermediate image outputs. If Image 2 is unavailable, stop and state that Image 2 access is required.\n\n\u003Cdetails open>\n\u003Csummary>中文\u003C\u002Fsummary>\n\n一个用于「风格驱动 PPT」的 Codex Skill。\n\n它把视觉风格当成可复用资产：先提炼或选择一个视觉风格，再基于文档、文章、提纲或主题生成图片版幻灯片提示词，并在需要时把逐页图片组装成 image-only PPTX。\n\n## 仓库简介\n\n`visual-style-ppt` 适合把内容策划、视觉风格提炼、Image2 生图提示词和图片版 PPT 打包流程串成一套稳定 SOP。它不追求可编辑 PPT 排版，而是把每页幻灯片视为一张高完成度视觉图片，再用 PPTX 作为最终交付容器。\n\n推荐 GitHub About 简介：\n\n```text\nStyle-driven Codex Skill for creating image-first PPT decks from documents, articles, and visual references.\n```\n\n推荐 Topics：\n\n```text\ncodex-skill, ppt, presentation, image2, visual-style, prompt-engineering, slide-deck, markdown-to-ppt\n```\n\n## 适合做什么\n\n- 把文章、Markdown、文档内容转成图片版 PPT\n- 从截图、参考图、网页、已有 deck 中提炼视觉风格\n- 保存、复用、维护一套 PPT 视觉风格库\n- 用指定风格生成 `outline.md` 和 `prompts.md`\n- 生成逐页幻灯片图片，并最终打包成 PPTX 和 zip\n- 做小红书信息图、文章配图、视觉化报告页等风格统一的页面资产\n\n## 核心原则\n\n- **Image 2 only**：所有幻灯片图片、缩略图板、信息图和配图都必须由 Image 2 模型生成，严禁 HTML 出图或任何等价替代路线。\n- **一页一图**：每一页最终幻灯片都应保存为单独图片，例如 `slide-01.png`、`slide-02.png`。\n- **风格隔离**：一个 deck 只使用一个选定风格和一个 `Style Lock`，避免混入历史任务或无关参考图的视觉 DNA。\n- **低信息密度**：默认内页保持克制，一页一个主标题、一个简短 takeaway，最多 2-3 个信息点。\n- **中文优先**：默认使用中文标题、中文模块名和中文支持文档；产品名、模型名、API 等保留英文。\n- **不自动加日期**：除非来源或用户明确要求，否则不在页面、脚注或元数据中添加日期和时间。\n\n## 目录结构\n\n```text\n.\n├── SKILL.md\n├── agents\u002F\n│   └── openai.yaml\n├── references\u002F\n│   ├── output-package.md\n│   ├── page-types.md\n│   ├── revision-workflow.md\n│   ├── style-interview.md\n│   └── workflow.md\n└── styles\u002F\n    ├── french-editorial-commerce.md\n    ├── impact-grid-editorial.md\n    └── terminal-tech-magazine.md\n```\n\n## 安装\n\n把这个仓库放到 Codex 的 skills 目录下：\n\n```bash\ncd ~\u002F.codex\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Firenerachel\u002Fvisual-style-ppt-skill.git visual-style-ppt\n```\n\n如果你已经有本地目录，也可以直接更新：\n\n```bash\ncd ~\u002F.codex\u002Fskills\u002Fvisual-style-ppt\ngit pull\n```\n\n## 使用前提\n\n- 已安装并可使用 Codex Skills。\n- 需要生成图片时，当前环境必须具备可调用的 Image 2 模型；没有 Image 2 时不得用 HTML 或其它图像生成\u002F本地渲染能力替代。\n- 需要组装 PPTX 时，环境应具备 PPTX 创建能力；本 Skill 默认生成 image-only PPTX。\n- 如果输入是 PDF、Word、Markdown 或网页内容，先确保 Codex 能读取对应文件或链接。\n\n## 使用示例\n\n```text\n调用终端风格，把这篇文章做成 8 页 PPT\n```\n\n```text\n用 CodeBuddy 那种科技杂志风格，把这个 Markdown 做成图片版 PPT，16:9\n```\n\n```text\n提炼这张图的风格，保存成一个可复用 PPT 风格\n```\n\n```text\n列出现在可用的 PPT 风格\n```\n\n```text\n用保存的 terminal-tech-magazine 风格，先给我 outline 和 prompts，我确认后再生成图片\n```\n\n## 什么时候不适合用\n\n- 需要高度可编辑的 PPT 源文件，例如每个文本框、图表和形状都要可单独修改。\n- 需要严格品牌 Logo 复现，并要求模型在每页图片中稳定绘制相同 Logo。\n- 需要大量表格、长段落、报告正文堆叠在单页里。\n- 需要自动加入今天日期、导出时间或时间戳，但来源没有明确要求。\n\n## 标准工作流\n\n1. 判断任务类型：提炼风格、调用风格、文档转 PPT、图片版 PPT 修订，或风格库管理。\n2. 选择或创建一个视觉风格文件。\n3. 从内容中抽取故事线、受众、页数建议和关键视觉时刻。\n4. 先生成 `outline.md` 和 `prompts.md`。\n5. 多页 deck 优先生成 thumbnail board，用于锁定整体节奏。\n6. 用户确认后，再逐页生成最终幻灯片图片。\n7. 用户确认全部图片后，组装 image-only PPTX。\n8. 打包最终图片、PPTX、提示词、提纲、风格文件和修订记录。\n\n## 风格库\n\n可复用风格放在 `styles\u002F` 目录，每个风格是一个 Markdown 文件。\n\n每个风格文件都应该包含 `## Style Lock`，用于控制整套 deck 的字体气质、布局网格、色彩比例、边框系统、页眉页脚、文本密度、Logo 处理和 Image2 negative constraints。\n\n当前内置风格：\n\n| 风格文件 | 适合内容 | 视觉气质 |\n| --- | --- | --- |\n| `terminal-tech-magazine.md` | AI、开发者工具、技术产品、深色视觉报告 | 终端科技杂志风格 |\n| `impact-grid-editorial.md` | 观点型内容、趋势判断、强标题页面 | 冲击力网格编辑风格 |\n| `french-editorial-commerce.md` | 品牌、消费、生活方式、审美型商业内容 | 法式编辑商业风格 |\n\n## 新增风格规范\n\n新增风格时，在 `styles\u002F` 下创建一个稳定命名的 Markdown 文件，例如：\n\n```text\nstyles\u002Fminimal-founder-deck.md\n```\n\n每个风格至少包含：\n\n- 风格定位和适用场景\n- 颜色系统，最好包含 hex 色值\n- 字体气质与标题\u002F正文层级\n- 页面网格、留白、页眉页脚规则\n- 卡片、边框、分割线、装饰元素规则\n- `## Style Lock`\n- Image2 negative constraints\n\n## 生成物约定\n\n推荐输出文件包括：\n\n- `outline.md`\n- `prompts.md`\n- `style-used.md`\n- `thumbnail-board.png`\n- `slide-01.png`\n- `slide-02.png`\n- `deck.pptx`\n- `revision-log.md`\n- final `.zip`\n\nPPTX 是交付容器，不是可编辑排版源文件。真正的视觉结果以逐页图片为准。\n\n## 命名约定\n\n- 风格文件使用 kebab-case，例如 `terminal-tech-magazine.md`。\n- 生成图片使用两位数序号，例如 `slide-01.png`。\n- 中间文档使用稳定文件名，例如 `outline.md`、`prompts.md`、`revision-log.md`。\n- 同一个项目的最终交付建议放入独立目录，避免不同 deck 的图片混在一起。\n\n## 维护建议\n\n- 修改工作流时更新 `SKILL.md` 和 `references\u002F`。\n- 新增视觉风格时只添加 `styles\u002F*.md`，不要为了改风格重写 `SKILL.md`。\n- 每个风格都要写清楚自己的 `Style Lock`。\n- 避免在风格文件里写过多一次性项目内容，保持它可复用。\n- 如果生成流程、包装方式或修订规则变化，同步更新 `references\u002F` 中对应文档。\n\n## 授权与使用\n\n当前仓库按个人 Skill 仓库维护。若后续计划公开分发、接受外部贡献或作为模板复用，建议再补充正式开源协议，例如 MIT License。\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>English\u003C\u002Fsummary>\n\nA Codex Skill for style-driven visual presentation creation.\n\nThis skill treats visual style as a reusable asset: extract or select a visual style first, then use documents, articles, outlines, or topics to create image-based slide prompts. When needed, it assembles the generated slide images into an image-only PPTX deck.\n\n## Repository Summary\n\n`visual-style-ppt` connects content planning, visual style extraction, Image2 prompt writing, and image-first PPT packaging into a reusable workflow. It does not aim to create fully editable PowerPoint layouts. Instead, it treats each slide as a polished visual image and uses PPTX as the final delivery container.\n\nSuggested GitHub About description:\n\n```text\nStyle-driven Codex Skill for creating image-first PPT decks from documents, articles, and visual references.\n```\n\nSuggested topics:\n\n```text\ncodex-skill, ppt, presentation, image2, visual-style, prompt-engineering, slide-deck, markdown-to-ppt\n```\n\n## What It Is For\n\n- Turn articles, Markdown files, and documents into image-based presentations\n- Extract visual style from screenshots, reference images, webpages, or existing decks\n- Save, reuse, and maintain a visual style library for PPT creation\n- Generate `outline.md` and `prompts.md` from a selected style\n- Generate one slide image per page and package the result as PPTX and zip\n- Create Xiaohongshu-style infographics, article visuals, visual reports, and consistent page assets\n\n## Core Principles\n\n- **Image 2 only**: Every slide image, thumbnail board, infographic, and illustration must be generated with the Image 2 model; HTML image output and equivalent substitute routes are forbidden.\n- **One image per slide**: Each final slide should be saved as an individual image, such as `slide-01.png` or `slide-02.png`.\n- **Style isolation**: Each deck uses exactly one selected style and one `Style Lock`, avoiding visual DNA from past tasks or unrelated references.\n- **Low text density**: Inner slides stay calm by default: one title, one short takeaway, and at most 2-3 information points.\n- **Chinese-first by default**: Slide titles, section labels, and support documents default to Chinese; product names, model names, and API terms stay in English when clearer.\n- **No automatic dates**: Dates and timestamps are not added unless the source or the user explicitly requires them.\n\n## Structure\n\n```text\n.\n├── SKILL.md\n├── agents\u002F\n│   └── openai.yaml\n├── references\u002F\n│   ├── output-package.md\n│   ├── page-types.md\n│   ├── revision-workflow.md\n│   ├── style-interview.md\n│   └── workflow.md\n└── styles\u002F\n    ├── french-editorial-commerce.md\n    ├── impact-grid-editorial.md\n    └── terminal-tech-magazine.md\n```\n\n## Installation\n\nPlace this repository under your Codex skills directory:\n\n```bash\ncd ~\u002F.codex\u002Fskills\ngit clone https:\u002F\u002Fgithub.com\u002Firenerachel\u002Fvisual-style-ppt-skill.git visual-style-ppt\n```\n\nIf you already have a local copy, update it with:\n\n```bash\ncd ~\u002F.codex\u002Fskills\u002Fvisual-style-ppt\ngit pull\n```\n\n## Requirements\n\n- Codex Skills should be installed and available.\n- Image generation requires the Image 2 model in the current environment; HTML and other image-generation or local-rendering substitutes are not allowed.\n- PPTX assembly requires an environment capable of creating PPTX files; this skill defaults to image-only PPTX.\n- If the input is a PDF, Word document, Markdown file, or webpage, make sure Codex can access the file or link.\n\n## Example Prompts\n\n```text\nUse the terminal-tech style and turn this article into an 8-slide PPT.\n```\n\n```text\nUse the CodeBuddy-like tech magazine style to turn this Markdown file into a 16:9 image-based presentation.\n```\n\n```text\nExtract the style from this image and save it as a reusable PPT style.\n```\n\n```text\nList the available PPT styles.\n```\n\n```text\nUse the saved terminal-tech-magazine style. Give me the outline and prompts first, then wait for confirmation before generating images.\n```\n\n## When Not To Use It\n\n- You need a highly editable PPT source file where every text box, chart, and shape must remain separately editable.\n- You need strict logo reproduction and expect the image model to redraw the same logo consistently on every page.\n- You need dense tables, long paragraphs, or report-style body copy packed into a single slide.\n- You need automatic dates, export times, or timestamps when the source does not explicitly require them.\n\n## Standard Workflow\n\n1. Classify the task: style extraction, style application, document-to-PPT, image-only PPT revision, or style library management.\n2. Select or create a visual style file.\n3. Extract the story arc, audience, page count suggestion, and key visual moments from the source.\n4. Generate `outline.md` and `prompts.md` first.\n5. For multi-page decks, generate a thumbnail board first to lock the visual rhythm.\n6. After user confirmation, generate each final slide image one by one.\n7. After all images are approved, assemble an image-only PPTX.\n8. Package the final images, PPTX, prompts, outline, style file, and revision log.\n\n## Style Library\n\nReusable styles live in the `styles\u002F` directory. Each style is a Markdown file.\n\nEvery style file should include a `## Style Lock` section that controls the deck's font mood, layout grid, color ratios, border system, headers and footers, text density, logo handling, and Image2 negative constraints.\n\nBuilt-in styles:\n\n| Style file | Best for | Visual mood |\n| --- | --- | --- |\n| `terminal-tech-magazine.md` | AI, developer tools, technical products, dark visual reports | Terminal tech magazine |\n| `impact-grid-editorial.md` | Opinion pieces, trend analysis, strong title pages | High-impact editorial grid |\n| `french-editorial-commerce.md` | Brand, consumer, lifestyle, aesthetic business content | French editorial commerce |\n\n## Adding A New Style\n\nCreate a stable Markdown file under `styles\u002F`, for example:\n\n```text\nstyles\u002Fminimal-founder-deck.md\n```\n\nEach style should include:\n\n- Style positioning and suitable use cases\n- Color system, preferably with hex values\n- Font mood and title\u002Fbody hierarchy\n- Page grid, spacing, header, and footer rules\n- Card, border, divider, and decorative element rules\n- `## Style Lock`\n- Image2 negative constraints\n\n## Output Convention\n\nRecommended output files include:\n\n- `outline.md`\n- `prompts.md`\n- `style-used.md`\n- `thumbnail-board.png`\n- `slide-01.png`\n- `slide-02.png`\n- `deck.pptx`\n- `revision-log.md`\n- final `.zip`\n\nThe PPTX is a delivery container, not the editable layout source. The final visual result is defined by the per-slide images.\n\n## Naming Conventions\n\n- Use kebab-case for style files, such as `terminal-tech-magazine.md`.\n- Use two-digit numbering for generated images, such as `slide-01.png`.\n- Use stable names for intermediate documents, such as `outline.md`, `prompts.md`, and `revision-log.md`.\n- Keep each final project in its own output directory to avoid mixing images from different decks.\n\n## Maintenance\n\n- Update `SKILL.md` and `references\u002F` when changing the workflow.\n- Add new visual styles as `styles\u002F*.md`; do not rewrite `SKILL.md` just to change a style.\n- Make sure every style includes a clear `Style Lock`.\n- Keep style files reusable and avoid embedding too much one-off project content.\n- If the generation flow, packaging rules, or revision workflow changes, update the matching document in `references\u002F`.\n\n## License And Usage\n\nThis repository is currently maintained as a personal skill repository. If you plan to distribute it publicly, accept external contributions, or use it as a reusable template, consider adding a formal open source license such as the MIT License.\n\n\u003C\u002Fdetails>\n","`visual-style-ppt-skill` 是一个用于将文档、文章和视觉参考材料转换为以图片为主的PPT的工作流。其核心功能是通过指定的视觉风格生成高质量的幻灯片图片，并最终打包成仅含图片的PPTX文件，强调使用Image 2模型进行图像生成，禁止HTML输出。该项目适合需要将内容快速转化为统一风格的视觉化展示场景，如制作信息图、报告页或小红书风格的文章配图等。它特别适用于那些重视视觉效果一致性且不需要高度可编辑性的演示文稿制作需求。","2026-06-11 03:56:05","CREATED_QUERY"]