Dsh Ppt

Community

STARDUSTLC666

dsh-ppt

Turn one sentence or a Markdown document into a complete, presentation-ready deck: a standalone HTML web slideshow plus an editable PPTX export, with 5 built-in visual themes (Swiss Pulse / Velvet Standard / Data Drift / Soft Signal / Maximalist Type), slide transitions + bullet entrance animations (motion, on by default), and bilingual Chinese/English support. Use when the user asks for a PPT, slides, deck, keynote, 演示文稿, 幻灯片, 汇报, 提案, 路演, 培训材料, or wants to turn a document into a presentation. 中文：把一句话或一篇文档变成完整演示文稿（HTML 网页放映 + PPTX 导出），内置 5 套视觉主题、页间转场与要点入场动画，中英双语。

Overview

Publisher	STARDUSTLC666
Repository	`dsh-ppt`
Skill name	`dsh-ppt`
Stars	20
Forks	3
Bundled files	17
License	MIT
Links	Skill source Repository

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.
17 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by STARDUSTLC666 on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/STARDUSTLC666/dsh-ppt/tree/master/skills/dsh-ppt
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.

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/STARDUSTLC666/dsh-ppt.git /tmp/dsh-ppt
mkdir -p .claude/skills
cp -r /tmp/dsh-ppt/skills/dsh-ppt .claude/skills/dsh-ppt

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dsh Ppt 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 Dsh Ppt 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 Dsh Ppt 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.

dsh-ppt

一句话或一篇文档 → 完整演示文稿：独立 HTML 网页放映 + 可编辑 PPTX。本文件只做路由与纪律；具体规则按需读取 references/。

触发条件

用户要做 PPT / 幻灯片 / 演示文稿 / deck / 汇报 / 提案 / 路演 / 培训材料，或给一句话、一段文字、一篇 Markdown 想变成可放映的演示。

执行纪律（每次都要遵守）

默认直接交付成品，不自动触发 AI 预审或答辩。用户可在设置页成品下载区主动开启两个可选模式；选择模型、范围与调用上限后再发送材料。AI 演练不等于事实核验，不编造实验、数据或引用；采纳建议另存副本，原件保留。
用户需要 AI 看图检查时，可在 DSH 设置 → 演示文稿 → 视觉检查与修复主动开启。它需要支持图片输入的模型与官方渲染引擎，修复只调整排版、另存副本并复查。AI 未发现问题不等于人工验收；模型调用失败、输出截断、停止和未检查页面必须如实说明，不能声称视觉通过。
数字溯源和现场推演也按需启用。提供 dataModel 与结构化 slides 的 {{metricId}} 绑定；先读 references/data.md。源事实必须对应真实材料行或单元格；用户假设用 kind:input 标注，禁止虚构来源。修改数据先 ppt_data(action:preview)，展示指标与页面差异，得到确认后携带原预览凭证和修订号保存；默认新副本。离线 HTML 参数必须回存确认后才能交付对应静态 PPTX。
修改工程先 ppt_check。外部编辑过的 HTML/PPTX、缺少成品校验记录的旧工程不可覆盖；告知用户 saveAs:true 只从 JSON 另存新副本，原件保留，Office 手工修改不会导入。不得绕过校验或自行篡改校验值。
一页一个观点；标题是判断句，不是名词短语。
内容语言由你撰写；lang 只决定界面文字。
先选主题再构建；不确定就用默认 data。
交付前逐项过一遍文末「质量门禁」。
目标是可用成品：先组织真实内容，再调用生成器；未填模板必须标注草稿，不编造缺失事实。
渲染报告缺失字体时，替换为环境和接收方机器可用字体，重新生成并逐页检查；未解决需标注字体问题，不能声称已验收。

核心流水线

Probe 需求：读入用户的句子/文档，确定听众、目标、语气。一句话输入不要反问，直接按发布场景推断。
Outline 大纲：产出 5–12 页大纲（封面 → 问题/背景 → 方案/论点 3–6 页 → 证据 → 行动号召 → 结束页）。 → 写大纲与正文前先读 references/copywriting.md。
Theme 主题：调 ppt_themes（DSH）或 node scripts/build-deck.mjs --list-themes（跨 harness）。 → 拿不准选哪套时读 references/themes.md 的情绪决策树。
Build 生成：
- DSH 内：调 ppt_create，大纲写成 Markdown 传 content（推荐），或传结构化 slides。
- 跨 harness：node <skill-dir>/scripts/build-deck.mjs --title "标题" --content deck.md --theme data --lang zh --out dist。
- 动效默认开（页间转场 + 要点逐条入场）；严肃/打印场景传 motion: 'off'。 → 用表格 / 金句 / 备注 / 结构化 slides 前读 references/syntax.md。
Verify 校验与修正：调 ppt_check 检查具体页；在浏览器操作放映、总览和备注，查看图片/图表。若可选官方引擎可用，调 ppt_render 读取最终 PPTX 生成逐页 PNG/PDF，逐页看画面。修正用 ppt_edit，以 expectedRevision 防冲突；需要时 ppt_undo。修改后重新渲染，以收据复核当前文件。文件头/结构通过不等同于视觉验收，静态估算、渲染、视觉检查必须分开说明。
Deliver 交付：给用户三个绝对路径，说明 HTML 直接放映（← → 翻页 · F 全屏 · G 总览 · S 备注 · P 打印），PPTX 用 PowerPoint / WPS / Keynote 打开（备注在演示者视图可见，bullets 页放映时逐条点击出现）。DSH 用户也可在「设置 → 演示文稿」修改文字、替换 PNG/JPEG、移动/复制/删除页面、撤销和下载最新文件；已有 JSON 工程先 ppt_check 才会出现在项目列表。ppt_edit.order 使用每个稳定页面 ID 各一次；duplicate、remove 使用修改前的页码或稳定 ID，复制保留图片/图表/备注，最终保留 1–120 页。结构与正文修改可合为一次撤销。

按需装载索引

何时读	文件	内容
写大纲 / 正文前	`references/copywriting.md`	叙事骨架、单页规则、双语规则
选主题拿不准	`references/themes.md`	5 套主题色板 + 情绪决策树
用表格/金句/备注/结构化 slides	`references/syntax.md`	Markdown 解析、进阶语法、slides JSON、motion 开关
图片/图表/模板/品牌/编辑/渲染	`references/advanced.md`	参数、限制、草稿与成品、收据语义
数字溯源与现场推演	`references/data.md`	来源绑定、公式、更新预览与离线参数回存
交付异常	`references/troubleshooting.md`	症状 → 处理对照表

质量门禁（交付前逐项确认）

页数 3–60，首屏是封面，末屏是结束页。
每页有明确标题；bullets 页 1–8 条，中文每条 ≤ 20 字、英文 ≤ 12 词。
HTML 与 PPTX 使用同一主题，配色一致。
主题色对比度足够（深底浅字或浅底深字）。
中文内容无错别字；英文标题用 Title Case。
最后一页有可执行的行动号召，不只是「谢谢」。
文件已写到用户工作区，路径为绝对路径。
没有未填模板；保留真实数据来源，检查每页画面而非只检查生成成功。
图片嵌入成功，图表与原始数据一致；渲染收据匹配最终 PPTX，说明尚未验证的部分。

跨 harness 安装

把整个 dsh-ppt 技能目录复制到目标 agent 的技能目录，使用 Node ^22.19.0 || >=24.0.0，在该目录运行 npm install --ignore-scripts。纯文本可直接运行；图片/图表/品牌导出需要 Office Kit，PNG/PDF 需另外安装可选官方引擎：

Agent	技能目录
DeepSeek Harness	`dsh plugin --profile web add dsh-ppt`
Claude Code	`~/.claude/skills/`
Cursor	`.cursor/skills/`
Gemini CLI	`~/.gemini/skills/`
OpenAI Codex	`~/.codex/skills/`

一次编写，处处可用。

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 Dsh Ppt AI skill do?

Why use Dsh Ppt on TypingMind?

Because you install it once and use it with any model. Dsh Ppt 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 Dsh Ppt in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/STARDUSTLC666/dsh-ppt/tree/master/skills/dsh-ppt. 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 Dsh Ppt?

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 Dsh Ppt?

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

Is the Dsh Ppt AI skill free?

Yes. It is published on GitHub by STARDUSTLC666 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

Unified Memory

affaan-m

CommunityPopular

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer…

Draw Your Font

Turn a handwriting photo into an installable TTF font.

Adversarial Ux Test

Roleplay a hostile user to find and triage UX pain points.

3 Statement Model

Build integrated IS/BS/CF financial workbooks in Excel.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

dsh-ppt

触发条件

执行纪律（每次都要遵守）

核心流水线

按需装载索引

质量门禁（交付前逐项确认）

跨 harness 安装

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now