Agent skill

Report Ppt Generator Pro

by LeoYeAI in LeoYeAI/openclaw-master-skills

Generate professional PowerPoint presentations from text manuscripts and style examples.

MITAuto-check passedDocuments & Office

Install Report Ppt Generator Pro

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill report-ppt-generator-pro -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills report-ppt-generator-pro --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/report-ppt-generator-pro .claude/skills/report-ppt-generator-pro && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
report-ppt-generator-pro
GitHub stars
2.2k
Token cost
~3.3k tokens
SKILL.md length
340 words
Files
10 (incl. references, assets)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

Generate professional PowerPoint presentations from text manuscripts and style examples.

  • Works in 6 steps: 风格分析 → 大纲生成 → 5: AI 配图生成(可选) → …
  • Users want to create PPT slides from written content
  • SKILL.md covers ⚠️ 依赖和权限声明, Workflow, Step 1: 风格分析 and Step 2: 大纲生成, plus 3 more sections
  • Runs JavaScript scripts from its folder; calls python3; needs GEMINI_API_KEY

What it does

Report Ppt Generator Pro is an agent skill from LeoYeAI/openclaw-master-skills. Generate professional PowerPoint presentations from text manuscripts and style examples. Use when users want to create PPT slides from written content, especially for work reports. Triggers: generate PPT, create slides, make presentation, convert to PowerPoint, PPT from document. Supports style extraction from example images, AI-generated illustrations, image embedding, and interactive HTML preview before export.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files and assets (for example `_meta.json`, `assets/scripts/html-to-pptx.js` and `package.json`).

It sits in Documents & Office, covering PowerPoint presentations. It works with Microsoft PowerPoint and Google Gemini. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Users want to create PPT slides from written content
  • Especially for work reports

Example prompts

  • “/report-ppt-generator-pro”

Requirements

  • Python 3
  • Node.js
  • A credential in GEMINI_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 风格分析
  2. 大纲生成
  3. 5: AI 配图生成(可选)
  4. HTML 生成
  5. Canvas 预览
  6. 导出 PPTX

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GEMINI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Report Ppt Generator Pro loads about 3.3k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 110 tokens; SKILL.md has 340 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 340 words, ~3,263 tokens.

Download SKILL.mdSave it as .claude/skills/report-ppt-generator-pro/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
report-ppt-generator-pro
description
Generate professional PowerPoint presentations from text manuscripts and style examples. Use when users want to create PPT slides from written content, especially for work reports. Triggers: generate PPT, create slides, make presentation, convert to PowerPoint, PPT from document. Supports style extraction from example images, AI-generated illustrations, image embedding, and interactive HTML preview before export.
descriptionZh
提供你的文稿及想要的风格示例图,会自动总结内容及风格,先通过 HTML 生成 PPT 预览,定稿后自动导出类似风格的.pptx 文件。

PPT Generator

⚠️ 依赖和权限声明

必需依赖
依赖用途配置要求
nanobanana-skillAI 配图生成(可选功能)需要安装此 skill
支持图片识别的 LLM风格分析、大纲生成用户自行配置任意支持图片识别的模型
文件系统访问
权限用途说明
读取本地文件读取用户提供的风格示例图、文稿文件仅读取用户明确指定的文件
写入本地文件保存生成的 HTML 预览、PPTX 文件、AI 配图默认保存到 ~/clawd/output/ 目录
读取 skill 目录读取 assets/ 和 references/ 中的模板文件仅限本 skill 目录内
外部 API 调用
API用途凭证要求
Google Gemini APIAI 配图生成(通过 nanobanana-skill)需要在 nanobanana-skill 中配置 GEMINI_API_KEY
LLM API风格分析、内容生成用户自行配置(支持图片识别的任意模型)
可选功能
功能依赖是否必需
AI 配图生成nanobanana-skill + Gemini API Key❌ 可选
风格分析支持图片识别的 LLM✅ 必需
HTML 预览Canvas 工具或本地服务器✅ 必需
PPTX 导出pptxgenjs (内置)✅ 必需

Generate professional, editable PowerPoint presentations from text manuscripts with style matching.

Workflow

用户输入(文稿 + 风格示例图 + 可选图片)
              │
              ▼
    ┌─────────────────┐
    │  Step 1: 风格分析 │
    │  支持图片识别的  │
    │  LLM 模型        │
    │  提取配色/布局   │
    └────────┬────────┘
             │
             ▼
    ┌─────────────────┐
    │  用户确认/调整   │  ← 对话迭代
    └────────┬────────┘
             │
             ▼
    ┌─────────────────┐
    │  Step 2: 大纲生成 │
    │  总结文稿内容    │
    │  规划每页结构    │
    └────────┬────────┘
             │
             ▼
    ┌─────────────────┐
    │  是否需要AI配图?│  ← 可选项
    │  (Step 2.5)     │
    └────────┬────────┘
             │
    ┌────────┴────────┐
    │                 │
   是                否
    │                 │
    ▼                 │
┌─────────────┐       │
│ AI配图生成  │       │
│ nanobanana  │       │
└──────┬──────┘       │
       │              │
       └──────┬───────┘
              │
              ▼
    ┌─────────────────┐
    │  Step 3: HTML生成 │
    │  16:9 横屏页面   │
    │  应用风格        │
    └────────┬────────┘
             │
             ▼
    ┌─────────────────┐
    │  Canvas 预览     │  ← 左右翻页、对话修改
    │  用户确认        │
    └────────┬────────┘
             │
             ▼
    ┌─────────────────┐
    │  Step 4: 导出PPTX │
    │  pptxgenjs      │
    │  可编辑文件      │
    └─────────────────┘

Step 1: 风格分析

输入
  • 风格示例图:用户提供的一张或多张 PPT 截图
  • 可选:用户的风格偏好说明
执行

使用 sessions_spawn 调用支持图片识别的 LLM 模型分析风格(使用用户配置的默认模型):

javascript
sessions_spawn({
  model: "default",  // 使用用户配置的默认模型
  task: `分析这张 PPT 截图的视觉风格,提取以下信息:

1. 配色方案:
   - 主色(用于标题/重点)
   - 辅助色(用于副标题/装饰)
   - 背景色
   - 文字色

2. 布局结构:
   - 标题位置和样式
   - 内容区域划分
   - 留白比例

3. 字体风格:
   - 标题字体(粗细/大小层次)
   - 正文字体

4. 装饰元素:
   - 线条/形状
   - 图标/图形
   - 其他装饰

请以 JSON 格式输出风格描述。`,
  // 图片通过会话上下文传入
})
输出格式
json
{
  "colors": {
    "primary": "#1E3A8A",
    "secondary": "#3B82F6",
    "background": "#FFFFFF",
    "text": "#1F2937",
    "accent": "#60A5FA"
  },
  "layout": {
    "titlePosition": "top-left",
    "titleSize": "large",
    "contentArea": "center",
    "whitespaceRatio": 0.3
  },
  "typography": {
    "titleFont": "bold, 36-48px",
    "bodyFont": "regular, 18-24px",
    "hierarchy": "clear distinction between title and body"
  },
  "decorations": {
    "shapes": ["rounded rectangles", "lines"],
    "icons": "minimal, line-style",
    "other": "subtle shadows"
  }
}
用户确认

展示分析结果,询问用户:

我分析了您提供的风格示例,提取出以下风格:
- 主色调:#1E3A8A(深蓝)
- 背景:白色
- ...

是否符合预期?需要调整哪些方面?

用户可以:

  • 确认使用
  • 修改颜色值
  • 调整布局偏好
  • 提供新的风格描述

Step 2: 大纲生成

输入
  • 文稿内容(文本)
  • 可选图片列表(本地路径或 URL)
  • 已确认的风格
执行

分析文稿结构,生成 PPT 大纲:

1. 封面页
   - 标题:{主标题}
   - 副标题:{副标题}
   - 图片:{可选封面图}

2. 目录页
   - 章节:{章节列表}

3. 章节页 x N
   - 标题:{章节标题}
   - 内容:{要点列表,每项 1-2 行}
   - 图片:{配图路径,注明位置意图}
   - 布局建议:{左文右图/上文下图/全图等}

4. 总结页
   - 关键结论
   - 下一步行动

5. 结束页
   - 感谢语
   - 联系方式
图片处理

如果用户提供了图片:

  1. 识别图片意图:根据上下文判断图片应该放在哪页
  2. 规划图片位置:
    • 数据图表 → 右侧或中央
    • 配图/照片 → 背景或侧边
    • 图标 → 标题旁或要点前
  3. 记录图片路径:本地路径或 URL
用户确认

展示大纲,询问:

我根据您的文稿生成了 PPT 大纲:

第1页:封面 - "季度工作汇报"
第2页:目录 - 3个章节
第3页:项目进展 - 左文右图布局
...

共 N 页。确认后我开始生成 HTML 预览。
需要调整页面顺序、合并/拆分页面吗?

Step 2.5: AI 配图生成(可选)

询问用户

大纲确认后,询问用户是否需要 AI 生成配图:

您的 PPT 大纲已生成。是否需要我为您生成 AI 配图?

选择:
1. 全部页面生成配图
2. 仅部分页面生成配图(请告诉我哪些页)
3. 不需要配图,继续下一步
配图策略

根据页面类型生成不同风格的配图:

页面类型配图风格示例提示词
封面页抽象科技/城市/行业背景"抽象科技背景,蓝色渐变,现代化数字城市,简洁几何图形"
概述页概念插图/流程图风格"业务流程概念图,简洁扁平风格,蓝色主色调"
数据页数据可视化风格"数据分析概念插图,图表和仪表盘,科技感"
总结页积极向上的概念图"成功合作概念图,握手或团队,商务风格"
执行流程
1. 分析页面内容,生成提示词
javascript
// 对每个需要配图的页面
const imagePrompt = await generateImagePrompt(slideContent, styleColors);

// 示例输出
{
  "slide": 3,
  "type": "概念插图",
  "prompt": "数字化道路概念图,智慧交通,蓝色科技风格,简洁扁平化设计,现代城市道路俯视图,带有数据流线条,16:9横幅"
}
2. 调用 nanobanana 生成图片
bash
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \
  --prompt "数字化道路概念图,智慧交通,蓝色科技风格,简洁扁平化设计" \
  --size 1344x768 \
  --output "/path/to/output/slide-3-illustration.png"
3. 图片参数设置
javascript
const imageConfig = {
  // 横版配图(适合 PPT)
  size: "1344x768",  // 16:9 横幅
  
  // 方形配图(适合图标、小插图)
  sizeSquare: "1024x1024",
  
  // 默认模型
  model: "gemini-3-pro-image-preview",
  
  // 快速模型(可选)
  modelFast: "gemini-2.5-flash-image",
  
  // 分辨率
  resolution: "1K"
};
配图提示词模板
封面配图
{主题}概念背景图,{风格描述},{主色调}渐变,
现代化{行业}场景,简洁几何图形装饰,
专业商务风格,适合PPT封面,16:9横幅
内容页配图
{页面主题}概念插图,{具体描述},
扁平化设计风格,{主色调}主色调,
简洁专业,适合PPT内容页,16:9横幅
数据/图表配图
数据分析可视化概念图,{具体描述},
科技感设计,{主色调}配色,
简洁现代,适合PPT数据展示页,16:9横幅
配图风格指南

根据提取的风格调整配图:

javascript
function adaptPromptToStyle(basePrompt, extractedStyle) {
  const colorWords = {
    "#003366": "深蓝色",
    "#3366CC": "蓝色",
    "#1E3A8A": "海军蓝",
    "#22C55E": "绿色",
    "#F97316": "橙色"
  };
  
  const primaryColorWord = colorWords[extractedStyle.colors.primary] || "蓝色";
  
  return `${basePrompt},${primaryColorWord}主色调,与PPT风格协调`;
}
生成后的处理
  1. 保存图片到工作目录
  2. 更新大纲中的图片路径
  3. 展示预览给用户确认
  4. 可选调整:用户可以说"重新生成第3页配图"

Step 3: HTML 生成

16:9 页面规格
css
.slide {
  width: 1920px;
  height: 1080px;
  aspect-ratio: 16 / 9;
  /* 或响应式: */
  width: 100%;
  aspect-ratio: 16 / 9;
}
模板参考

使用 assets/html-template/ 中的模板:

html
<!DOCTYPE html>
<html>
<head>
  <link rel="stylesheet" href="base.css">
  <style>
    /* 注入用户风格 */
    :root {
      --primary-color: {{colors.primary}};
      --secondary-color: {{colors.secondary}};
      --background-color: {{colors.background}};
      --text-color: {{colors.text}};
    }
  </style>
</head>
<body>
  <div class="slide" id="slide-1">
    <!-- 内容 -->
  </div>
</body>
</html>
布局类型

参考 references/work-report-layouts.md 中的布局模板:

  • 封面布局
  • 标题+正文布局
  • 左文右图布局
  • 对比布局
  • 数据展示布局
图片嵌入
html
<!-- AI生成的配图 -->
<img src="/path/to/ai-generated-illustration.png" alt="配图描述">

<!-- 用户提供的图片 -->
<img src="/local/path/to/image.png" alt="描述">

<!-- 网络图片 -->
<img src="https://example.com/image.png" alt="描述">

<!-- 样式:自动缩放适配 -->
<style>
.slide img {
  max-width: 100%;
  max-height: 100%;
  object-fit: contain;
}
</style>

Step 4: Canvas 预览

展示方式

使用 canvas 工具或本地服务器展示 HTML:

javascript
// 方式1: canvas(需要 node)
canvas({
  action: "present",
  url: "file:///path/to/slides.html"
})

// 方式2: 本地服务器
// 启动服务器后用浏览器预览
交互功能

用户可以:

  • 翻页:点击左右箭头或按钮
  • 对话修改:说"把标题改成蓝色"、"调整第3页布局"
  • 预览截图:查看渲染效果
迭代修改

接收用户修改指令,更新 HTML,刷新预览。


Step 5: 导出 PPTX

使用 pptxgenjs
javascript
import pptxgen from "pptxgenjs";

let pres = new pptxgen();
pres.layout = "LAYOUT_16x9";

// 应用风格
pres.theme = {
  headFontFace: "Microsoft YaHei",
  bodyFontFace: "Microsoft YaHei"
};

// 添加幻灯片
let slide = pres.addSlide();

// 添加文本
slide.addText("标题", {
  x: 0.5, y: 0.5, w: "90%", h: 1,
  fontSize: 36, color: "1E3A8A", bold: true
});

// 添加 AI 生成的配图
slide.addImage({
  path: "/path/to/ai-generated-illustration.png",
  x: 6, y: 2, w: 4, h: 3
});

// 保存
pres.writeFile({ fileName: "output.pptx" });
风格映射
HTML/CSSpptxgenjs
color: #1E3A8Acolor: "1E3A8A"
font-size: 36pxfontSize: 36
font-weight: boldbold: true
background: #FFFfill: "FFFFFF"
图片处理
javascript
// 本地图片(包括 AI 生成的配图)
slide.addImage({ path: "/path/to/image.png", ... });

// 网络图片(先下载)
const imageData = await fetch(imageUrl);
slide.addImage({ data: imageData, ... });

// 自动缩放
// pptxgenjs 会自动处理,可指定 w/h 或使用 sizing

HTML 转 PPTX 经验教训

⚠️ 常见陷阱
1. 正则匹配嵌套 HTML 标签

问题:使用简单正则 /class="slide"/ 会误匹配 class="slide-content"、class="slide-header" 等。

错误示例:

javascript
// ❌ 错误:会匹配到 slide-content, slide-header 等
const regex = /<div class="slide[^"]*"/g;

正确做法:使用栈匹配嵌套结构

javascript
// ✅ 正确:精确匹配顶层 slide div
function extractSlides(html) {
  const slides = [];
  // 精确匹配 slide 的开始标签,捕获类型
  const regex = /<div class="slide( cover| end)?"[^>]*>/g;
  let match;
  
  while ((match = regex.exec(html)) !== null) {
    const startPos = match.index;
    const slideType = match[1] ? match[1].trim() : 'content';
    
    // 用栈找到匹配的结束 </div>
    let depth = 1;
    let pos = startPos + match[0].length;
    
    while (depth > 0 && pos < html.length) {
      const openIdx = html.indexOf('<div', pos);
      const closeIdx = html.indexOf('</div>', pos);
      
      if (closeIdx === -1) break;
      
      if (openIdx !== -1 && openIdx < closeIdx) {
        depth++;
        pos = openIdx + 4;
      } else {
        depth--;
        pos = closeIdx + 6;
      }
    }
    
    slides.push({
      html: html.substring(startPos, pos),
      type: slideType
    });
  }
  
  return slides;
}
2. 提取嵌套 div 内容

问题:text-section 内部还有嵌套 div,简单正则无法正确提取。

正确做法:

javascript
function extractTextSection(slideHtml) {
  const startMatch = slideHtml.match(/class="text-section"[^>]*>/);
  if (!startMatch) return null;
  
  const startPos = startMatch.index + startMatch[0].length;
  
  // 用栈找结束位置
  let depth = 1;
  let pos = startPos;
  
  while (depth > 0 && pos < slideHtml.length) {
    const openIdx = slideHtml.indexOf('<div', pos);
    const closeIdx = slideHtml.indexOf('</div>', pos);
    
    if (closeIdx === -1) break;
    
    if (openIdx !== -1 && openIdx < closeIdx) {
      depth++;
      pos = openIdx + 4;
    } else {
      depth--;
      pos = closeIdx + 6;
      if (depth === 0) {
        return slideHtml.substring(startPos, closeIdx);
      }
    }
  }
  return null;
}
3. 背景图处理

问题:HTML 中的背景图(如 cover_bg.png)可能被误过滤,或路径处理不正确。

正确做法:

javascript
// 封面页:先添加背景图,再添加半透明遮罩
function createCoverSlide(slide, slideHtml) {
  // 1. 背景图
  const bgPath = `${imgBasePath}/cover_bg.png`;
  if (fs.existsSync(bgPath)) {
    slide.addImage({ path: bgPath, x: 0, y: 0, w: 10, h: 5.625 });
  }
  
  // 2. 半透明遮罩(让文字更清晰)
  slide.addShape('rect', {
    x: 0, y: 0, w: 10, h: 5.625,
    fill: { color: '0d47a1', transparency: 20 }
  });
  
  // 3. 文字内容...
}
4. 图片路径验证

问题:HTML 中的图片路径可能不存在,直接添加会报错。

正确做法:

javascript
// 过滤有效图片
const validImages = images.filter(p => fs.existsSync(p));

if (validImages.length > 0) {
  // 添加图片...
} else {
  // 显示占位符
  slide.addShape('rect', {
    x: imgX, y: imgY, w: imgW, h: imgH,
    fill: { color: 'f5f5f5' },
    line: { color: 'cccccc', width: 1, dashType: 'dash' }
  });
  slide.addText('图片区域', {
    x: imgX, y: imgY + imgH / 2 - 0.2, w: imgW, h: 0.4,
    fontSize: 14, color: '999999', align: 'center'
  });
}
5. 内容提取顺序

问题:HTML 中的内容顺序和预期不一致,导致解析遗漏。

推荐顺序:

javascript
function createContentSlide(slide, slideHtml) {
  // 1. 提取标题栏
  const headerMatch = slideHtml.match(/class="slide-header"[^>]*>([\s\S]*?)<\/div>/);
  
  // 2. 提取 text-section(用栈匹配)
  const textHtml = extractTextSection(slideHtml);
  
  // 3. 提取图片(排除背景图)
  const images = extractImages(slideHtml);
  
  // 4. 处理文本内容
  if (textHtml) {
    // h2 标题
    // h3 之前的段落
    // 网格布局(five-grid, three-grid, four-grid)
    // 流程图(flow-chart)
    // h3 及其内容(需要 split 处理多个 h3)
  }
}
✅ 完整转换脚本模板

参考文件:assets/scripts/html-to-pptx.js

关键要点:

  1. 使用栈匹配嵌套 HTML 结构
  2. 分别处理不同类型的内容(段落、列表、网格、流程图)
  3. 验证图片路径是否存在
  4. 按正确顺序添加 PPT 元素(背景 → 遮罩 → 文字 → 图片)

Resources

references/
  • style-extraction.md - 风格提取详细指南
  • work-report-layouts.md - 工作汇报常用布局模板
  • image-handling.md - 图片处理详细说明
  • ai-illustration-prompts.md - AI 配图提示词模板
assets/
  • html-template/ - HTML/CSS 模板文件
    • base.css - 基础样式
    • slide.html - 页面模板

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references, assets) in skills/report-ppt-generator-pro of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • _meta.json
  • assets/html-template/base.css
  • assets/html-template/slide.html
  • assets/scripts/html-to-pptx.js
  • package.json
  • references/ai-illustration-prompts.md
  • references/image-handling.md
  • references/style-extraction.md
  • references/work-report-layouts.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Report Ppt Generator Pro next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Report Ppt Generator Pro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Report Ppt Generator Pro this skillLeoYeAI/openclaw-master-skills2.2k—~3.3kAutomated safety check: PassMIT
Nano BananaEvoScientist/EvoSkills4782 repos~3.5kAutomated safety check: PassApache-2.0
Document ConverterBlackBeltTechnology/pi-agent-dashboard315—~999Automated safety check: PassMIT
Skywork Pptaiskillstore/marketplace433—~1.9kAutomated safety check: PassNone
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Image To Editable Pptningzimu/image-to-editable-ppt-skill2.9k—~4.3kAutomated safety check: PassMIT

Similar skills

  • Nano Banana

    EvoScientist/EvoSkills

    Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing.

    478 GitHub starsUsed in 2 repos~3.5k tokens
    Documents & OfficeAuto-check passed
  • Document Converter

    BlackBeltTechnology/pi-agent-dashboard

    Convert documents bidirectionally via the pi-doc-engine facade: ingest PDF/DOCX/PPTX/XLSX to provenance-stamped Markdown (with OCR), and produce templated DOCX/PDF from Markdown with diagrams, TOC…

    315 GitHub stars~999 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Skywork Ppt

    aiskillstore/marketplace

    Generate PPTs from topics or templates, edit existing presentations via natural language, or perform local file operations (delete/reorder/merge slides).

    433 GitHub stars~1.9k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes
  • Image To Editable Ppt

    ningzimu/image-to-editable-ppt-skill

    Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied.

    2.9k GitHub stars~4.3k tokensUpdated 24 days ago
    Documents & OfficeAuto-check passed
  • GenOffice Document CLI

    genspark-ai/genoffice

    Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.

    9.2k GitHub stars~19k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Report Ppt Generator Pro

What does Report Ppt Generator Pro do?

Generate professional PowerPoint presentations from text manuscripts and style examples. Report Ppt Generator Pro is an agent skill from LeoYeAI/openclaw-master-skills. Generate professional PowerPoint presentations from text manuscripts and style examples.

When should I use Report Ppt Generator Pro?

Report Ppt Generator Pro fits situations like: users want to create PPT slides from written content; especially for work reports.

How do I install Report Ppt Generator Pro in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill report-ppt-generator-pro -a claude-code`. Or copy the skill folder (skills/report-ppt-generator-pro in LeoYeAI/openclaw-master-skills) into .claude/skills/report-ppt-generator-pro in your project. Claude Code loads it when a task matches its description.

How do I install Report Ppt Generator Pro in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill report-ppt-generator-pro -a codex`. Or copy the skill folder (skills/report-ppt-generator-pro in LeoYeAI/openclaw-master-skills) into .agents/skills/report-ppt-generator-pro in your project. Codex loads it when a task matches its description.

Can I use Report Ppt Generator Pro in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill report-ppt-generator-pro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/report-ppt-generator-pro, .gemini/skills/report-ppt-generator-pro, .github/skills/report-ppt-generator-pro and .opencode/skills/report-ppt-generator-pro in your project.

What does Report Ppt Generator Pro need to run?

Going by SKILL.md and its folder, Report Ppt Generator Pro needs JavaScript for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named GEMINI_API_KEY. Our summary lists: Python 3; Node.js; A credential in GEMINI_API_KEY.

Does Report Ppt Generator Pro access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Report Ppt Generator Pro safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Report Ppt Generator Pro use?

Report Ppt Generator Pro is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Report Ppt Generator Pro use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.6k tokens, read only when the agent opens those files.

What are the alternatives to Report Ppt Generator Pro?

Skills that share tags, products or a category with Report Ppt Generator Pro: Nano Banana (EvoScientist/EvoSkills, 478 stars), Document Converter (BlackBeltTechnology/pi-agent-dashboard, 315 stars), Skywork Ppt (aiskillstore/marketplace, 433 stars) and Markitdown (ImCa0/just-laws, 781 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Report Ppt Generator Pro?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.