Skill1.5k repo starsupdated 5d ago
huashu-slides
从内容到成品PPTX的端到端演示文稿制作,含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
Install in Claude Code
Copygit clone --depth 1 https://github.com/alchaincyf/huashu-skills /tmp/huashu-slides && cp -r /tmp/huashu-slides/huashu-slides ~/.claude/skills/huashu-slidesThen start a new Claude Code session; the skill loads automatically.
Definition
SKILL.md
# AI Presentation Workflow
Create professional presentations: Content → Design → Build → Assembly → Polish.
## Step 0: Choose Workflow Settings
**At the start of every presentation task, ask the user TWO choices:**
### 0-A. Collaboration Mode
| Mode | Description | Checkpoints |
|------|-------------|-------------|
| **Full Auto** | Minimal interaction. Confirm topic only, deliver final PPTX. | 1 checkpoint |
| **Guided** (recommended) | Confirm outline, pick design, preview before assembly. | 3 checkpoints |
| **Collaborative** | Review every slide, approve every illustration, full control. | Per-slide |
If the user doesn't specify, default to **Guided** mode.
### 0-B. Assembly Method
| Method | How it works | Best for |
|--------|-------------|----------|
| **Editable HTML** (Path A) | HTML slides + selective AI illustrations → html2pptx → editable PPTX | Need to edit text later, precise layout, corporate decks |
| **Full AI Visual** (Path B) | Every slide as a complete AI-generated image → create_slides.py → image PPTX | Maximum visual impact, artistic presentations, quick drafts |
**Trade-offs:**
| | Path A: Editable HTML | Path B: Full AI Visual |
|---|---|---|
| Text | Editable in PPT | Baked into image (not editable) |
| Visual quality | Good with illustrations | Excellent — cohesive design |
| Layout control | Pixel-precise | AI-interpreted |
| File size | Smaller (~5-25MB) | Larger (~30-80MB) |
| Chinese text | Perfect (font rendering) | Usually good (AI may occasionally misrender) |
| Speed | Faster (HTML creation) | Slower (image generation per slide) |
If the user doesn't specify, default to **Path A** (Editable HTML).
---
## Step 1: Content Structuring
Turn raw material into a slide-by-slide outline.
**Per slide, define:**
- **Title** — a complete assertion sentence (not a topic word)
- **Key points** — 3-4 maximum
- **Visual type** — illustration / chart / diagram / icon / quote
- **Path A:** Illustration needed? — Yes/No. If yes, one-line description.
- **Path B:** Visual scene description — one paragraph describing the complete slide visual (layout + imagery + mood).
**Assertion-Evidence rule:**
| Bad title | Good title |
|-----------|-----------|
| Q3 Sales | Q3销售增长23%,新用户是主要驱动力 |
| Methodology | 我们通过双盲实验验证了这个结论 |
**语言规则:slide内容一律用中文,仅保留必要的英文术语(人名、品牌名、技术专有名词)。** Section label(如 INSIGHT、TAKEAWAY)可用英文作为设计元素。
### ✅ Checkpoint 1 (Guided + Collaborative)
Present the outline as a table:
**Path A:**
```
| # | Title (assertion) | Key Points | Visual Type | Illustration? |
|---|-------------------|------------|-------------|---------------|
| 1 | Cover: ... | — | Decorative | Yes: ... |
| 2 | ... | 1. ... 2. ... | Chart | No |
| 3 | ... | 1. ... 2. ... | Illustration | Yes: ... |
```
**Path B:**
```
| # | Title (assertion) | Key Points | Visual Scene Description |
|---|-------------------|------------|--------------------------|
| 1 | Cover: ... | — | Dark gradient bg, large title centered, abstract network nodes |
| 2 | ... | 1. ... 2. ... | Split layout: text left, bar chart right, clean white bg |
| 3 | ... | 1. ... 2. ... | Full illustration: person at crossroads with floating clocks |
```
**Ask the user:**
- Approve / adjust slide count
- Path A: Approve / adjust which slides get illustrations
- Path B: Approve / adjust visual scene descriptions
- Any content to add or remove
---
## Step 2: Design System
**Present 3 design system options for the user to choose from.** Each is a complete visual language, not just a color palette.
**CRITICAL: A design system is NOT just colors.** It defines visual philosophy, typography ratios, composition rules, and emotional intent. This is the difference between "boring PPT" and "magazine-quality deck."
### 🗣️ Style Discussion (Optional, if user wants to explore)
**If the user says things like:**
- "我想要XX风格"(田中一光、瑞士国际主义、包豪斯、蒙德里安...)
- "我不确定想要什么风格"
- "能给我看看不同风格的例子吗"
**Then consult the design movements reference:**
`references/design-movements.md` — 设计运动与风格参考库
This file maps classic design movements (Neo-Brutalism, Swiss Style, Bauhaus, etc.) to our AI-ready style presets. Use it to:
1. Translate user's aesthetic language into actionable prompts
2. Build shared vocabulary ("这个方向偏田中一光" vs "那个偏构成主义")
3. Reference when designing new custom styles from scratch
**After discussing movements, proceed to recommend 3 concrete presets below.**
---
### Design System Presets
**⚠️ CRITICAL INSIGHT: 插画/漫画类风格的AI生成效果远好于「专业极简」类风格。**
漫画/插画风格有明确的视觉语言(线条、角色、色块),AI可以充分发挥;极简风格(暗色底+发光文字+大量留白)缺乏视觉元素,生成出来「空」且「平」。
Pick 3 that match the topic/mood. Use the **topic recommendation table** below, then present each with its full description.
**按主题自动推荐(优先从此表选):**
| 主题类型 | 第一推荐 | 第二推荐 | 第三推荐 |
|---------|---------|---------|---------|
| 品牌/产品介绍 | Snoopy温暖漫画 | Neo-Pop新波普 | 浮世绘/敦煌(东方品牌) |
| 教育/培训 | Neo-Brutalism | 学習漫画 | Snoopy温暖漫画 |
| 技术分享 | xkcd白板 | Neo-Brutalism | Ligne Claire |
| 数据报告 | **Pentagram编辑** | **Fathom数据** | Ligne Claire |
| 年轻受众 | Neo-Pop | 像素画 | 孔版印刷 |
| 创意/艺术 | 达达拼贴 | 孔版印刷 | The Oatmeal |
| 国风/东方 | 敦煌壁画 | 浮世绘 | **Takram思辨** |
| 正式商务 | **Pentagram编辑** | **Müller-Brockmann网格** | **Build极简** |
| 产品发布/keynote | 苏联构成主义 | Neo-Pop | **Pentagram编辑** |
| 内部分享 | Neo-Brutalism | The Oatmeal | xkcd白板 |
| 行业分析/咨询 | **Fathom数据** | **Pentagram编辑** | **Müller-Brockmann网格** |
| 培训课件/教材 | **Takram思辨** | 温暖叙事 | 学習漫画 |
| 投资/融资路演 | **Build极简** | **Pentagram编辑** | 苏联构成主义 |
**完整18种风格详细参考:** `references/proven-styles-gallery.md`
**风格样例图片:** `assets/style-samples/` 目录
---
**第一梯队(强烈推荐,效果极好):**
**1. Warm Comic Strip** — Snoopy温暖漫画风
- Philosophy: Peanuts漫画的温暖与哲理感——简单的角色说着深刻的话,日常场景中蕴含人生智慧
- Visual world: 圆头小孩、小狗、小鸟组成一个温暖的小世界。背景极简(草地、天空、狗屋、树)。色调像泛黄的报纸漫画
- Reference: "Like a Peanuts comic strip — warm, philosophical, charming"
- **Style guide:** `references/proven-styles-snoopy.md`
- **⚠️ 关键经验:** 不要在prompt中过度约束视觉细节(颜色比例、构图位置、角色姿势),否则会严重降低多样性。只描述情绪和内容,让AI自由发挥
**2. Manga Educational** — 学習漫画风
- Philosophy: Japanese educational manga (学習漫画) — a chaMore from this repository
huashu-agent-swarmSkill
多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。
huashu-article-editSkill
标准化文章编辑流程,确保修改范围明确、进度可追踪、变更有记录。当用户说"编辑文章"、"修改文章"、"调整内容"、"改一下这篇"时使用此技能。
huashu-article-to-xSkill
长文精简为X平台内容(200-500字),保留核心观点和个人风格。当用户提到"转微博"、"发小红书"、"社交媒体"、"缩短文章"时使用。
huashu-data-proSkill
|
huashu-designSkill
设计哲学顾问,从20种风格中推荐3个方向并生成视觉Demo和AI提示词。当用户提到"设计风格"、"设计方向"、"配色方案"、"视觉风格"、"设计评审"、"推荐风格"时使用。
huashu-douyin-scriptSkill
|
huashu-image-uploadSkill
文章配图一键生成并上传图床,自动插入Markdown链接。当用户提到"配图"、"插图"、"上传图片"、"文章配图"时使用。
huashu-info-searchSkill
多渠道搜索新产品新技术,交叉验证后存入知识库。当用户提到"最新信息"、"新产品"、"搜索资料"、"查资料"、"了解XX"时使用。