Workdsh Ppt Design logo

Workdsh Ppt Design

Community
techflag
workdsh-ppt-design

通过需求对齐、逐页叙事和视觉设计,在 WorkDSH 原生 PPT 编辑器中实时创建、改写和美化演示文稿。支持红金政务、咨询与学术风格;通过 Office content_* 工具逐页保存并导出 PPTX。

Overview

Publishertechflag
Repositoryworkdsh
Skill nameworkdsh-ppt-design
Stars
262
Forks
73
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by techflag on GitHub. Read the source before you install it.

Installation

Install the Workdsh Ppt Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/techflag/workdsh/tree/main/packages/plugins/skills/resources/skills/workdsh-ppt-design
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/techflag/workdsh.git /tmp/workdsh
mkdir -p .claude/skills
cp -r /tmp/workdsh/packages/plugins/skills/resources/skills/workdsh-ppt-design .claude/skills/workdsh-ppt-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workdsh Ppt Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Workdsh Ppt Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Workdsh Ppt Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PPT 制作

入口与执行

使用 WorkDSH /office.ppt 对应的原生 Office 流程制作演示文稿,不转交 PPT Master 或其他文件生成技能。设计资源提供叙事和视觉方法,实际制作使用 content_open/content_capabilities/content_read/content_edit/content_export。此内置版由工程维护,执行差异见 原生适配。

制作步骤

  1. 提供客户标准 PPTX 时先调用 content_import_pptx(path,title,operationId),保留原包作为实时工作副本;导入失败不得空白重绘。文字替换优先 presentation.updateText(slideId,elementId,expectedText,text),保留模板位置和首段样式。普通新建时,先调用 content_open,input 使用 kind:"presentation"、source:"new"、title 和唯一 operationId,立即打开右侧编辑器;不要先写完整大纲或创建中间文件。已有实时 PPT 按真实 documentId 重新打开并读取,保留用户编辑。独立上传 PPTX 不自动成为实时文档,不猜 documentId。
  2. 读取 content_capabilities 和 content_read,获取实际文档 ID、revision、原生页面及画布尺寸。立即使用 presentation.updateSlide 保存第一张有用页面,再按需展开设计。不得以回复文字代替页面提交。
  3. 利用用户主题、材料、风格和场景,只问决定内容的缺失信息,一次最多三个问题。按需阅读 需求对齐 的优先级;未指定具体风格时,按需求对齐流程调用 content_preview_styles 展示四套封面,再用官方 ask_user_question 等待选择。只指定“红色”时展示四种红色方向,不自动套用红金;明确红金政务时才读取 红金设计。选定后重新打开步骤1的原生 presentation documentId,保留首张页面与用户编辑。
  4. 阅读 叙事方法 和 视觉设计,提炼逐页主题、来源、重点、版式、配色与节奏。咨询或学术场景按需读取 designs 下对应资料。将这些方法应用到实时编辑器;不强制创建 STORY.md、DESIGN.md、.slide 或脚本。材料缺失的数据保留明确待补项,不添加虚构事实。
  5. 按实际原生 schema 制作:presentation.insertSlides/updateSlide 每次 content_edit 只提交一页内容;使用返回的 revision、稳定 slideId、元素 ID。updateSlide 的 elements 替换整页元素,须保留用户未要求删除的内容。根据实际画布缩放设计参考的1280×720布局,不硬编码画布大小;不使用 CSS、JSX 或 SlideDSL 属性。
  6. 原生图表使用 chartData 的 chartType、categories、series[{name,values}],保持数据可编辑;不要以图片或形状拼装代替实际图表。图片只使用支持的真实素材,不构造图片字节。新建、替换、排序、删除均使用实际 content_capabilities 支持的操作。遇到 revision 冲突先重读,HUMAN_EDITING 时等待用户完成编辑,不循环重试。
  7. 逐页检查边界、文字溢出、图表可读性、母版对齐、章节对应、配色和材料忠实度。完成后读取最新保存版本,调用 content_export 导出真实 PPTX 并显示文件交付卡;工具不可用时说明右侧下载方式和未验证项,不声称已经导出。

工具与边界

不加载 PPT Master,不使用 Python、Bash、PptxGenJS、officecli、slidep 或 WorkBuddy editor_sdk 来生成/修改这份实时 PPT。原版 create-from-、component- 和 scripts 仅保留用于来源比对,其专有命令和运行时不适用。四套封面由 content_preview_styles 保存为独立 HTML 规划预览,PPT 本身仍使用原生编辑器;预览卡不直接提交答案。不调用未注册的 show_widget 或 AskUserQuestion;官方提问工具名为 ask_user_question。

交付

右侧可编辑演示文稿及从最新保存版本导出的真实 .pptx。报告实际保存页数;渲染不可用时说明视觉未验证。Office 工具缺失或模型 API 余额不足时说明实际原因,不切换生成引擎、不伪造文件或完成状态。

图表与真实文件交付补充读取 图表与交付;已有叙事与排版补充见 叙事与设计。这些资料共同服务同一原生 PPT 流程,不构成第二个技能。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Workdsh Ppt Design AI skill do?

通过需求对齐、逐页叙事和视觉设计,在 WorkDSH 原生 PPT 编辑器中实时创建、改写和美化演示文稿。支持红金政务、咨询与学术风格;通过 Office content_* 工具逐页保存并导出 PPTX。

Why use Workdsh Ppt Design on TypingMind?

Because you install it once and use it with any model. Workdsh Ppt Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Workdsh Ppt Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/techflag/workdsh/tree/main/packages/plugins/skills/resources/skills/workdsh-ppt-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Workdsh Ppt Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Workdsh Ppt Design?

As many as you like. As long as a model supports skills, you can use Workdsh Ppt Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Workdsh Ppt Design AI skill free?

Yes. It is published on GitHub by techflag under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇