AlphaMoatによると、2026-10時点でopenclaw-slidesのダウンロード数は7,126、スター数は3で、累計ダウンロード数で今回のランキング対象AIスキル10,914件中3,955位、オフィス効率化では909件中407位です。
一覧の初期表示は累計ダウンロード数順で、スター数順にも並べ替えできます。詳細ページの順位は累計ダウンロード数で計算しています。
| プラットフォーム | ダウンロード数 | スター数 | コメント |
|---|---|---|---|
| ClawHub ↗ | 7126 | 1 | - |
| SkillHub ↗ | 5871 | 3 | — |
プラットフォームごとに集計方法と集計時点が異なります。
一からHTMLスライドを作成したり、既存のPPT/PPTXを変換したり、既存HTMLプレゼンテーションを改善できます。文書ではビューポートへの適合を重視しています。変換や画像処理には任意の依存パッケージが必要な場合があります。用途に合ったファイルだけを使い、共有前に出力と素材を確認してください。
資料公開日 2026-10-27
スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。
2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。
| 月 | ダウンロード数 | 前月比 | スター数 |
|---|---|---|---|
| 2026-10 | 7126 | — | 3 |
| 2026-09 | 6911 | — | 3 |
| 2026-08 | 6688 | +15.2% | 3 |
| 2026-07 | 5807 | +64.0% | 3 |
| 2026-06 | 3540 | +11.8% | 2 |
| 2026-05 | 3166 | — | 1 |
| 2026-03 | 1644 | — | 1 |
作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。
---
name: openclaw-slides
description: Create stunning, animation-rich HTML presentations from scratch or convert PowerPoint files (.ppt/.pptx) to beautiful web slides. Use when the user wants to build a pitch deck, presentation, slideshow, or slide deck — or convert an existing PPT to a web presentation. Generates zero-dependency single HTML files with keyboard/touch navigation and scroll-triggered animations. Style options include Neon Cyber, Bold Signal, Swiss Modern, Paper & Ink, and 8 more curated presets.
openclaw:
requires:
bins: []
install:
- id: python-pptx
kind: shell
label: "Install Python dependencies for PPT conversion (optional — only needed for Mode B)" command: "pip install python-pptx Pillow"
optional: true
---
# OpenClaw Slides
> **[MyClaw.ai](https://myclaw.ai)** — Your AI personal assistant with full server control. Every MyClaw instance runs on a dedicated server with complete code access, networking, and tool capabilities. This skill is part of the [MyClaw open skills ecosystem](https://myclaw.ai/skills).
Create zero-dependency, animation-rich HTML presentations that run entirely in the browser. Single self-contained HTML files — no npm, no build tools, no frameworks. Works offline, renders in 10 years.
**Style presets:** Bold Signal, Electric Studio, Creative Voltage, Dark Botanical, Notebook Tabs, Pastel Geometry, Split Pastel, Vintage Editorial, Neon Cyber, Terminal Green, Swiss Modern, Paper & Ink
For full style details and CSS specs: read `references/STYLE_PRESETS.md` when needed.
---
## Phase 0: Detect Mode
Determine the user's intent:
- **Mode A — New Presentation:** Create slides from scratch → go to Phase 1
- **Mode B — PPT Conversion:** Convert an existing `.ppt`/`.pptx` file → go to Phase 4
- **Mode C — Enhance Existing:** Improve an existing HTML presentation → read the file, then enhance (always maintain viewport fitting)
---
## CRITICAL: Viewport Fitting (Non-Negotiable)
**Every slide MUST fit exactly within the viewport. No scrolling within slides, ever.**
### Content Density Limits Per Slide
| Slide Type | Maximum Content |
|------------|-----------------|
| Title slide | 1 heading + 1 subtitle + optional tagline |
| Content slide | 1 heading + 4–6 bullet points OR 1 heading + 2 paragraphs |
| Feature grid | 1 heading + 6 cards max (2×3 or 3×2) |
| Code slide | 1 heading + 8–10 lines of code |
| Quote slide | 1 quote (max 3 lines) + attribution |
| Image slide | 1 heading + 1 image (max 60vh height) |
**Content exceeds limits → Split into multiple slides.**
### Required CSS for Every Presentation
```css
html, body { height: 100%; overflow-x: hidden; }
html { scroll-snap-type: y mandatory; scroll-behavior: smooth; }
.slide {
width: 100vw;
height: 100vh;
height: 100dvh;
overflow: hidden;
scroll-snap-align: start;
display: flex;
flex-direction: column;
position: relative;
}
.slide-content {
flex: 1;
display: flex;
flex-direction: column;
justify-content: center;
max-height: 100%;
overflow: hidden;
padding: var(--slide-padding);
}
:root {
--title-size: clamp(1.5rem, 5vw, 4rem);
--h2-size: clamp(1.25rem, 3.5vw, 2.5rem);
--body-size: clamp(0.75rem, 1.5vw, 1.125rem);
--slide-padding: clamp(1rem, 4vw, 4rem);
--content-gap: clamp(0.5rem, 2vw, 2rem);
}
img, .image-container { max-width: 100%; max-height: min(50vh, 400px); object-fit: contain; }
.card, .container { max-width: min(90vw, 1000px); max-height: min(80vh, 700px); }
.grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(min(100%, 220px), 1fr)); gap: clamp(0.5rem, 1.5vw, 1rem); }
@media (max-height: 700px) { :root { --slide-padding: clamp(0.75rem, 3vw, 2rem); --title-size: clamp(1.25rem, 4.5vw, 2.5rem); } }
@media (max-height: 600px) { :root { --title-size: clamp(1.1rem, 4vw, 2rem); --body-size: clamp(0.7rem, 1.2vw, 0.95rem); } .nav-dots, .keyboard-hint { display: none; } }
@media (max-height: 500px) { :root { --title-size: clamp(1rem, 3.5vw, 1.5rem); --slide-padding: clamp(0.4rem, 2vw, 1rem); } }
@media (max-width: 600px) { .grid { grid-template-columns: 1fr; } }
@media (prefers-reduced-motion: reduce) { *, *::before, *::after { animation-duration: 0.01ms !important; transition-duration: 0.2s !important; } }
```
**⚠️ Never negate CSS functions directly.** Use `calc(-1 * clamp(...))` not `-clamp(...)`.
---
## Phase 1: Content Discovery (New Presentations)
Ask the user (via normal conversation — ask all at once):
1. **Purpose:** pitch deck / teaching / conference talk / internal presentation?
2. **Length:** ~5–10 / 10–20 / 20+ slides?
3. **Content:** ready content, rough notes, or just a topic?
4. **Images:** any images to include? (provide path like `./assets` or `~/Desktop/screenshots`)
5. **Inline editing:** should text be editable in-browser after generation?
If they have content, ask them to share it.
### Image Evaluation (if images provided)
All image processing is done **locally on the user's machine** — images are never sent to external services.
1. `ls` the folder — find all `.png/.jpg/.jpeg/.gif/.svg/.webp`
2. Read each image file locally using the `read` tool
3. Mark each as `USABLE` or `NOT USABLE` (reason: blurry, irrelevant, etc.)
4. Note what each represents (logo, screenshot, chart, etc.) and dominant colors
5. Build slide outline that incorporates usable images as visual anchors
6. Present outline + image assignments to user for confirmation
If user says **no images** → skip image pipeline, use CSS-generated visuals (gradients, shapes, patterns) throughout.
---
## Phase 2: Style Discovery
### Option A — Direct Selection (user knows what they want)
Pick from presets:
| Preset | Vibe |
|--------|------|
| Bold Signal | Confident, high-impact, dark |
| Electric Studio | Clean, professional, split panel |
| Creative Voltage | Energetic, retro-modern |
| Dark Botanical | Elegant, sophisticated |
| Notebook Tabs | Editorial, organized |
| Pastel Geometry | Friendly, approachable |
| Split Pastel | Playful, modern |
| Vintage Editorial | Witty, personality-driven |
| Neon Cyber | Futuristic, techy |
| Terminal Green | Developer-focused, hacker |
| Swiss Modern | Minimal, precise |
| Paper & Ink | Literary, thoughtful |
Skip to Phase 3.
### Option B — Visual Discovery (default for undecided users)
Ask: **What feeling should the audience have?**
- Impressed/Confident → Bold Signal, Electric Studio, Dark Botanical
- Excited/Energized → Creative Voltage, Neon Cyber, Split Pastel
- Calm/Focused → Notebook Tabs, Paper & Ink, Swiss Modern
- Inspired/Moved → Dark Botanical, Vintage Editorial, Pastel Geometry
Generate **3 mini style preview HTML files** in `.tmp-slide-previews/` — each is a single title slide showing typography, colors, and animation. Tell the user the file paths and ask which they prefer.
**Never use:** purple gradients on white, Inter/Roboto/system fonts, generic blue primary colors.
**Use instead:** distinctive font pairings (Clash Display, Satoshi, Cormorant, DM Sans), cohesive personality-driven palettes, atmospheric backgrounds.
For full preset specs (colors, fonts, signature elements): read `references/STYLE_PRESETS.md`.
---
## Phase 3: Generate Presentation
### Image Processing (skip if no images)
If user provided images, process with Python Pillow before generating HTML:
```python
from PIL import Image, ImageDraw
# Circular crop (for logos)
def crop_circle(input_path, output_path):
img = Image.open(input_path).convert('RGBA')
w, h = img.size
size = min(w, h)
img = img.crop(((w-size)//2, (h-size)//2, (w+size)//2, (h+size)//2))
mask = Image.new('L', (size, size), 0)
ImageDraw.Draw(mask).ellipse([0, 0, size, size], fill=255)
img.putalpha(mask)
img.save(output_path, 'PNG')
# Resize large images
def resize_max(input_path, output_path, max_dim=1200):
img = Image.open(input_path)
img.thumbnail((max_dim, max_dim), Image.LANCZOS)
img.save(output_path, quality=85)
```
Install if needed: `pip install Pillow`
**Use direct file paths in HTML** (not base64), e.g. `src="assets/logo_round.png"`. Never overwrite originals — save processed files with `_processed` suffix.
### HTML Architecture
```html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Presentation Title</title>
<!-- Fonts via Fontshare or Google Fonts -->
<style>
/* CSS Custom Properties (theme) */
:root { /* colors, typography with clamp(), spacing */ }
/* Mandatory viewport base CSS (see above) */
/* Slide-specific styles */
/* Animations (.reveal → .visible .reveal) */
/* Responsive breakpoints */
</style>
</head>
<body>
<div class="progress-bar"></div>
<nav class="nav-dots"></nav>
<section class="slide title-slide">
<h1 class="reveal">Title</h1>
<p class="reveal">Subtitle</p>
</section>
<!-- More slides... -->
<script>
class SlidePresentation {
// Keyboard nav (arrows, space)
// Touch/swipe support
// Mouse wheel navigation
// Progress bar + nav dots
// Intersection Observer for .reveal animations
}
new SlidePresentation();
</script>
</body>
</html>
```
### Required JS Features
- Keyboard navigation: arrow keys, space
- Touch/swipe support
- Mouse wheel navigation
- Progress bar + navigation dots
- Intersection Observer → adds `.visible` class → triggers CSS animations
- Staggered reveal delays (nth-child 0.1s, 0.2s, 0.3s...)
### Inline Editing (only if user opted in)
**⚠️ Do NOT use CSS `~` sibling selector for hover-based show/hide** — `pointer-events: none` breaks the hover chain. Use JS with delay timeout:
```javascript
// Hotzone hover with 400ms grace period
const hotzone = document.querySelector('.edit-hotzone');
const editToggle = document.getElementById('editToggle');
let hideTimeout = null;
hotzone.addEventListener('mouseenter', () => { clearTimeout(hideTimeout); editToggle.classList.add('show'); });
hotzone.addEventListener('mouseleave', () => { hideTimeout = setTimeout(() => { if (!editor.isActive) editToggle.classList.remove('show'); }, 400); });
editToggle.addEventListener('mouseenter', () => clearTimeout(hideTimeout));
editToggle.addEventListener('mouseleave', () => { hideTimeout = setTimeout(() => { if (!editor.isActive) editToggle.classList.remove('show'); }, 400); });
// Keyboard: E key (skip when editing)
document.addEventListener('keydown', (e) => {
if ((e.key === 'e' || e.key === 'E') && !e.target.getAttribute('contenteditable')) editor.toggleEditMode();
});
```
Features: contenteditable text, auto-save to localStorage, export/save file.
### Code Quality
- Comment every major CSS and JS section
- Semantic HTML: `<section>`, `<nav>`, `<main>`
- ARIA labels on interactive elements
- `@media (prefers-reduced-motion: reduce)` support
---
## Phase 4: PPT Conversion
```python
from pptx import Presentation
import os
def extract_pptx(file_path, output_dir):
prs = Presentation(file_path)
assets_dir = os.path.join(output_dir, 'assets')
os.makedirs(assets_dir, exist_ok=True)
slides_data = []
for i, slide in enumerate(prs.slides):
data = {'number': i+1, 'title': '', 'content': [], 'images': [], 'notes': ''}
for shape in slide.shapes:
if shape.has_text_frame:
if shape == slide.shapes.title:
data['title'] = shape.text
else:
data['content'].append({'type': 'text', 'content': shape.text})
if shape.shape_type == 13: # Picture
img = shape.image
name = f"slide{i+1}_img{len(data['images'])+1}.{img.ext}"
path = os.path.join(assets_dir, name)
with open(path, 'wb') as f: f.write(img.blob)
data['images'].append({'path': f"assets/{name}"})
if slide.has_notes_slide:
data['notes'] = slide.notes_slide.notes_text_frame.text
slides_data.append(data)
return slides_data
```
Install: `pip install python-pptx`
After extraction: show user the slide structure for confirmation, then proceed to Phase 2 (style), then Phase 3 (generate).
---
## Phase 5: Delivery
1. Delete `.tmp-slide-previews/` if created
2. Tell user the output file path
3. Provide navigation instructions:
- Arrow keys / Space to navigate
- Scroll or swipe
- Click nav dots to jump
4. Mention how to customize: `:root` CSS variables for colors/fonts
5. If inline editing enabled: hover top-left corner or press `E`
6. Ask if any adjustments needed
---
## Style → Feeling Quick Reference
| Feeling | Use |
|---------|-----|
| Dramatic/Cinematic | Slow fades (1–1.5s), dark + spotlight, parallax |
| Techy/Futuristic | Neon glow, particles, grid pattern, monospace accents |
| Playful/Friendly | Bouncy easing, rounded corners, pastels, floating anim |
| Professional/Corporate | Fast subtle anim (200–300ms), navy/slate, data-focused |
| Calm/Minimal | Very slow motion, high whitespace, serif type, muted palette |
| Editorial/Magazine | Strong type hierarchy, pull quotes, grid-breaking layouts |
MCP 経由で Tencent Docs の文書を作成、編集、管理するための手順書です。
WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.1新增:kingdoc云端桥接(白名单探测+配置预检+subprocess上传+差异检查)、条件格式/数据验证跨引擎IO(JSON中间格式保真往返)、会议纪要三段式要素化(待办清单+决策记录+风险异议)+说话人标注(MFCC聚类);v5.2新增:公文一键排版(GB/T 9704 规则库约束+结构识别套版+红头预留位+联合行文)、批量水印与敏感信息打码(身份证/手机号/银行卡/邮箱双轨识别+黑色矩形覆盖+打码清单)、跨文档知识检索与问答(本地TF-IDF零依赖+跳转+可选zwjh记忆桥接);删除:与contract-review重复的轻量合同审查模块,改为文档互链引导;v5.2.5修复:MS Office引擎下Excel/PPT创建必然失败(错用Word COM对象),新增get_ms_excel/get_ms_ppt及三槽位统一释放release_ms,MS Office路径透传filepath参数;v5.3.5修复:SKILL.md frontmatter 修复 tags 块序列误混入联系方式行导致标准 YAML 解析失败;v5.4.0新增:留存型功能——定时任务与报告中心(schedule_register 升级为三平台统一调度层 schtasks/cron/launchd,错过策略 skip/run_once,注册表 JSON 可导出导入;新建 report_center.py 报告中心,templates/reports/*.json 参数化模板 + ECharts 单文件 HTML 输出(图表内联、无服务端、双击即开);report_generator 升级支持 --format html;wps.py CLI 统一埋点 SQLite,自动供 report_center 生成周度使用摘要附在报告末尾;watch.py 职责收窄为纯事件采集);v5.3.0新增:统一CLI入口 wps(registry.json注册表分发,office --app/--action 与 convert 子命令、--list 一屏列出全部命令,薄路由层不改脚本内部逻辑)、全命令 --json 机器可读输出(固定 ok/error_id/elapsed/data 四字段,对齐 E001-E015,wps_error.py 新增 emit_json 统一出口)、_worker 启动优化(wps_pure 改惰性加载,pywin32/python-docx/openpyxl 经核查已惰性导入,ENGINE_CACHE 进程级单例复用,COM 释放统一走 release_ms 三槽位)、转换三入口合并为 convert(format_converter/md_converter/wps_docx_to_ppt 内部按目标格式路由,旧脚本保留为兼容别名并提示新命令,v6.0.0 移除)
テーマとスタイルから PPT 資料を自動生成するスキルです。
体制内资深办公室主任+管理学博士,自学编程开发的智能公文写作Skill,让所有办公室同仁少掉头发、少加无用的班,材料一稿过关,省下的时间留给自己、享受生活!————————我们能给你带来的核心价值:1、颠覆传统写作:逻辑建模38类公文全链条,特有模板化引导问答模式,分分钟省心生成高质量大稿。--------2、替你“向上管理”:独有审稿人画像机制,文稿一键结构性修改,精准匹配审稿人画像,过稿率提升至少10倍!----------3、杜绝AI编造:缺失的数字、文号、人名、日期一律用[待补]标注,绝不杜撰,守住公文底线。-----------4、算法格式托底:数十万全量智控知识库+6500行前沿核心控制代码,格式精准对齐GB/T 9704,出稿零失误。——————————————————本skill历史版本开放了5%知识库的免费试用版,下载即可使用,但需注意:知识库有著作权,仅用于个人使用,不可用于其他任何目的。有兴趣的可以试试。——————————————————————单次付费版skill已发布,2元一次使用全量知识库。具体在发布者“熵衍信息”主页skill里。
WPS Office 全家桶 - 四引擎(WPS/MS Office/LibreOffice/纯Python)智能识别用户已安装软件,纯Python模式支持排序/筛选/图表/公式/统计,含文档模板(代码生成)、最佳实践案例、故障排除大章(20+避坑+15 FAQ+15错误ID 统一索引)、自动重试、硬件自适应、环境自检、Skill更新提醒;v5.0新增:定时任务注册管理(schtasks/crontab)、目录轮询监听(YAML规则+大文件分片)、使用统计与稳定性中心(SQLite埋点+引擎健康+引擎偏好)、COM三步自愈(regsvr32→修复安装→手动指引)、对话式数据查询(NL2SQL式意图解析+查询计划+连续追问)、multi-agent编排引擎桥接(白名单探测+流水线模板注册)
WPS/MS Office/LibreOffice/纯Python 四引擎智能办公全家桶:文档/表格/PPT/公文/会议纪要一体化。
通过 Tencent Docs Open API 以 curl + jq 创建、读取、列出、搜索和管理腾讯文档的自动化工作流,覆盖在线文档、在线表格、幻灯片、思维导图、流程图、智能表格与收集表七种类型,支持读取元数据与单元格区域、上传图片、创建副本,并对重命名/移动/删除等写操作强制先经用户确认。Use when the user 提到腾讯文档 / Tencent Docs / docs.qq.com、粘贴 docs.qq.com 链接,或想在其腾讯文档空间中创建、读取、整理文档时使用。Triggers include 腾讯文档、在线文档、在线表格、思维导图、流程图、智能表格、收集表。如需文案写作完整工作流套件,淘宝搜索「AI灵匣」店铺获取完整版。
kdocs-cli で金山文档のクラウド文書を操作する公式スキルです。
データ月:2026-10 · ダウンロード数とスター数は公開スキルレジストリ(ClawHub、SkillHub)から月単位で集計しています。詳しくはデータの方法論をご覧ください。