Html Ppt logo

Html Ppt

OrganizationPopular
nexu-io
html-ppt

For consulting delivery work: turn diagnosis, frameworks, and project work into a client-adoptable action plan. Built around the core query "consulting-final-deck", with engagement manager judgment, buyer-ready proof, and this outcome: accept the recommendation and commit owners to the roadmap.

Overview

Publishernexu-io
Repositoryopen-design
Skill namehtml-ppt
Stars
98.9K
Forks
11.5K
Bundled files
206
LicenseApache-2.0
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.

  • 206 bundled files

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

  • Open source

    Published by nexu-io on GitHub. Read the source before you install it.

Installation

Install the Html Ppt 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/nexu-io/open-design/tree/main/design-templates/html-ppt
  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/nexu-io/open-design.git /tmp/open-design
mkdir -p .claude/skills
cp -r /tmp/open-design/design-templates/html-ppt .claude/skills/html-ppt
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Html 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 Html 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 Html 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.

html-ppt — HTML PPT Studio

Author professional HTML presentations as static files. One theme file = one look. One layout file = one page type. One animation class = one entry effect. All pages share a token-based design system in assets/base.css.

Install

bash
npx skills add https://github.com/lewislulu/html-ppt-skill

One command, no build. Pure static HTML/CSS/JS with only CDN webfonts.

What the skill gives you

  • 36 themes (assets/themes/*.css) — minimal-white, editorial-serif, soft-pastel, sharp-mono, arctic-cool, sunset-warm, catppuccin-latte/mocha, dracula, tokyo-night, nord, solarized-light, gruvbox-dark, rose-pine, neo-brutalism, glassmorphism, bauhaus, swiss-grid, terminal-green, xiaohongshu-white, rainbow-gradient, aurora, blueprint, memphis-pop, cyberpunk-neon, y2k-chrome, retro-tv, japanese-minimal, vaporwave, midcentury, corporate-clean, academic-paper, news-broadcast, pitch-deck-vc, magazine-bold, engineering-whiteprint
  • 15 full-deck templates (templates/full-decks/<name>/) — complete multi-slide decks with scoped .tpl-<name> CSS. 8 extracted from real-world decks (xhs-white-editorial, graphify-dark-graph, knowledge-arch-blueprint, hermes-cyber-terminal, obsidian-claude-gradient, testing-safety-alert, xhs-pastel-card, dir-key-nav-minimal), 7 scenario scaffolds (pitch-deck, product-launch, tech-sharing, weekly-report, xhs-post 3:4, course-module, presenter-mode-reveal — 演讲者模式专用)
  • 31 layouts (templates/single-page/*.html) with realistic demo data
  • 27 CSS animations (assets/animations/animations.css) via data-anim
  • 20 canvas FX animations (assets/animations/fx/*.js) via data-fx — particle-burst, confetti-cannon, firework, starfield, matrix-rain, knowledge-graph (force-directed), neural-net (pulses), constellation, orbit-ring, galaxy-swirl, word-cascade, letter-explode, chain-react, magnetic-field, data-stream, gradient-blob, sparkle-trail, shockwave, typewriter-multi, counter-explosion
  • Keyboard runtime (assets/runtime.js) — arrows, T (theme), A (anim), F/O, S (presenter mode: magnetic-card popup with CURRENT / NEXT / SCRIPT / TIMER cards), N (notes drawer), R (reset timer in presenter)
  • FX runtime (assets/animations/fx-runtime.js) — auto-inits [data-fx] on slide enter, cleans up on leave
  • Showcase decks for themes / layouts / animations / full-decks gallery
  • Managed Chromium render script for PNG export

When to use

Use when the user asks for any kind of slide-based output or wants to turn text/notes into a presentable deck. Prefer this over building from scratch.

🎤 Presenter Mode (演讲者模式 + 逐字稿)

If the user mentions any of: 演讲 / 分享 / 讲稿 / 逐字稿 / speaker notes / presenter view / 演讲者视图 / 提词器, or says things like "我要去给团队讲 xxx", "要做一场技术分享", "怕讲不流畅", "想要一份带逐字稿的 PPT" — use the presenter-mode-reveal full-deck template and write 150–300 words of 逐字稿 in each slide's <aside class="notes">.

See references/presenter-mode.md for the full authoring guide including the 3 rules of speaker script writing:

  1. 不是讲稿,是提示信号 — 加粗核心词 + 过渡句独立成段
  2. 每页 150–300 字 — 2–3 分钟/页的节奏
  3. 用口语,不用书面语 — "因此"→"所以","该方案"→"这个方案"

All full-deck templates support the S key presenter mode (it's built into runtime.js). S opens a new popup window with 4 magnetic cards:

  • 🔵 CURRENT — pixel-perfect iframe preview of the current slide
  • 🟣 NEXT — pixel-perfect iframe preview of the next slide
  • 🟠 SPEAKER SCRIPT — large-font 逐字稿 (scrollable)
  • 🟢 TIMER — elapsed time + slide counter + prev/next/reset buttons

Each card is draggable by its header and resizable by the bottom-right corner handle. Card positions/sizes persist to localStorage per deck. A "Reset layout" button restores the default arrangement.

Why the previews are pixel-perfect: each preview is an <iframe> that loads the actual deck HTML with a ?preview=N query param; runtime.js detects this and renders only slide N with no chrome. So the preview uses the same CSS, theme, fonts, and viewport as the audience view — colors and layout are guaranteed identical.

Smooth navigation: on slide change, the presenter window sends postMessage({type:'preview-goto', idx:N}) to each iframe. The iframe just toggles .is-active between slides — no reload, no flicker. The two windows also stay in sync via BroadcastChannel.

Only presenter-mode-reveal is designed from the ground up around the feature with proper example 逐字稿 on every slide.

Keyboard in presenter window: ← → navigate (syncs audience) · R reset timer · Esc close popup. Keyboard in audience window: S open presenter · T cycle theme · ← → navigate (syncs presenter) · F fullscreen · O overview.

Before you author anything — infer first, ask only when blocked

Before writing slides, resolve the three decisions below from the user's brief, project metadata, supplied content, and conversation. If they are sufficiently clear, choose a tasteful default and proceed without waiting for confirmation; state the choices briefly in the plan. Ask one consolidated clarification only when a missing answer would materially change the deck.

  1. Content & audience. What's the deck about, how many slides, who's watching (engineers / execs / 小红书读者 / 学生 / VC)?
  2. Style / theme. Which of the 36 themes fits? If unsure, recommend 2-3 candidates based on tone:
    • Business / investor pitch → pitch-deck-vc, corporate-clean, swiss-grid
    • Tech sharing / engineering → tokyo-night, dracula, catppuccin-mocha, terminal-green, blueprint
    • 小红书图文 → xiaohongshu-white, soft-pastel, rainbow-gradient, magazine-bold
    • Academic / report → academic-paper, editorial-serif, minimal-white
    • Edgy / cyber / launch → cyberpunk-neon, vaporwave, y2k-chrome, neo-brutalism
  3. Starting point. One of the 14 full-deck templates, or scratch? Choose the closest templates/full-decks/<name>/. If the user's content suggests something obvious (e.g. "我要做产品发布会" → product-launch), use it confidently instead of asking blindly.

A good clarification, when one is actually needed, follows the active discovery-question-form protocol and contains only unresolved fields. For example, if content and audience are known but the requested tone spans incompatible themes, ask one theme question with 2–3 recommended options. Do not repeat the form as a markdown checklist.

If the known context already resolves them, scaffold the deck and start writing immediately.

Quick start

  1. Scaffold a new deck. From the repo root:
    bash
    ./scripts/new-deck.sh my-talk
    open examples/my-talk/index.html
  2. Pick a theme. Open the deck and press T to cycle. Or hard-code it:
    html
    <link rel="stylesheet" id="theme-link" href="../assets/themes/aurora.css">
    Catalog in references/themes.md.
  3. Pick layouts. Copy <section class="slide">...</section> blocks out of files in templates/single-page/ into your deck. Replace the demo data. Catalog in references/layouts.md.
  4. Add animations. Put data-anim="fade-up" (or class="anim-fade-up") on any element. On <ul>/grids, use anim-stagger-list for sequenced reveals. For canvas FX, use <div data-fx="knowledge-graph">...</div> and include <script src="../assets/animations/fx-runtime.js"></script>. Catalog in references/animations.md.
  5. Use a full-deck template. Copy templates/full-decks/<name>/ into examples/my-talk/ as a starting point. Each folder is self-contained with scoped CSS. Catalog in references/full-decks.md and gallery at templates/full-decks-index.html.
  6. Render to PNG.
    bash
    ./scripts/render.sh templates/theme-showcase.html       # one shot
    ./scripts/render.sh examples/my-talk/index.html 12      # 12 slides

Authoring rules (important)

  • Always start from a template. Don't author slides from scratch — copy the closest layout from templates/single-page/ first, then replace content.
  • Use tokens, not literal colors. Every color, radius, shadow should come from CSS variables defined in assets/base.css and overridden by a theme. Good: color: var(--text-1). Bad: color: #111.
  • Don't invent new layout files. Prefer composing existing ones. Only add a new templates/single-page/*.html if none of the 30 fit.
  • Respect chrome slots. .deck-header, .deck-footer, .slide-number and the progress bar are provided by assets/base.css + runtime.js.
  • Keyboard-first. Always include <script src="../assets/runtime.js"></script> so the deck supports ← → / T / A / F / S / O / hash deep-links.
  • One .slide per logical page. runtime.js makes .slide.is-active visible; all others are hidden.
  • Supply notes. Wrap speaker notes in <div class="notes">…</div> inside each slide. Press S to open the overlay.
  • NEVER put presenter-only text on the slide itself. Descriptive text like "这一页展示了……" or "Speaker: 这里可以补充……" or small explanatory captions aimed at the presenter MUST go inside <div class="notes">, NOT as visible <p> / <span> elements on the slide. The .notes class is display:none by default — it only appears in the S overlay. Slides should contain ONLY audience-facing content (titles, bullet points, data, charts, images).

Writing guide

See references/authoring-guide.md for a step-by-step walkthrough: file structure, naming, how to transform an outline into a deck, how to choose layouts and themes per audience, how to do a Chinese + English deck, and how to export.

Catalogs (load when needed)

File structure

html-ppt/
├── SKILL.md                 (this file)
├── references/              (detailed catalogs, load as needed)
├── assets/
│   ├── base.css             (tokens + primitives — do not edit per deck)
│   ├── fonts.css            (webfont imports)
│   ├── runtime.js           (keyboard + presenter + overview + theme cycle)
│   ├── themes/*.css         (36 token overrides, one per theme)
│   └── animations/
│       ├── animations.css   (27 named CSS entry animations)
│       ├── fx-runtime.js    (auto-init [data-fx] on slide enter)
│       └── fx/*.js          (20 canvas FX modules: particles/graph/fireworks…)
├── templates/
│   ├── deck.html                  (minimal 6-slide starter)
│   ├── theme-showcase.html        (36 slides, iframe-isolated per theme)
│   ├── layout-showcase.html       (iframe tour of all 31 layouts)
│   ├── animation-showcase.html    (20 FX + 27 CSS animation slides)
│   ├── full-decks-index.html      (gallery of all 14 full-deck templates)
│   ├── full-decks/<name>/         (14 scoped multi-slide deck templates)
│   └── single-page/*.html         (31 layout files with demo data)
├── scripts/
│   ├── new-deck.sh                (scaffold a deck from deck.html)
│   └── render.sh                  (managed Chromium → PNG)
└── examples/demo-deck/            (complete working deck)

Rendering to PNG

scripts/render.sh uses Playwright's managed Chromium renderer. Do not call the user's installed Google Chrome directly for PNG export, especially on macOS desktop builds where Crashpad/profile permissions can abort Chrome before a screenshot is written. If the managed renderer fails once, surface that error and stop instead of retrying alternate Chrome launch commands.

For multi-slide capture, runtime.js exposes #/N deep-links, and render.sh iterates 1..N.

bash
./scripts/render.sh templates/single-page/kpi-grid.html        # single page
./scripts/render.sh examples/demo-deck/index.html 8 out-dir    # 8 slides, custom dir

Keyboard cheat sheet

←  →  Space  PgUp  PgDn  Home  End    navigate
F                                       fullscreen
S                                       open presenter window (magnetic cards: current/next/script/timer)
N                                       quick notes drawer (bottom overlay)
R                                       reset timer (in presenter window)
?preview=N                              URL param — force preview-only mode (single slide, no chrome)
O                                       slide overview grid
T                                       cycle themes (reads data-themes attr)
A                                       cycle demo animation on current slide
#/N in URL                              deep-link to slide N
Esc                                     close all overlays

License & author

MIT. Copyright (c) 2026 lewis <sudolewis@gmail.com>.

Bundled files

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

and 140 more files.

Frequently asked questions

What does the Html Ppt AI skill do?

For consulting delivery work: turn diagnosis, frameworks, and project work into a client-adoptable action plan. Built around the core query "consulting-final-deck", with engagement manager judgment, buyer-ready proof, and this outcome: accept the recommendation and commit owners to the roadmap.

Why use Html Ppt on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nexu-io/open-design/tree/main/design-templates/html-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 Html 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 Html Ppt?

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

Is the Html Ppt AI skill free?

Yes. It is published on GitHub by nexu-io under the Apache-2.0 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 👇