According to AlphaMoat, as of 2026-10, Office To Md V2 has 8,261 downloads and 4 stars — ranked by downloads #3,368 among 10,914 AI skills in this ranking, and #358 of 909 in Office.
The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.
| Platform | Downloads | Stars | Comments |
|---|---|---|---|
| ClawHub ↗ | 4.0K | 2 | - |
| SkillHub ↗ | 8.3K | 4 | — |
Platforms count differently and update at different times.
It covers PDF, legacy DOC, DOCX and basic PPTX extraction through Node libraries, with optional Python support for slides. Results can include a local Markdown file, preview and status information. Images are not extracted, complex layouts and tables may be imperfect and protected files are unsupported. Review adjacent output collisions, pre-provision dependencies and use trusted filenames and restricted permissions for PPTX conversion.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-10 | 8.3K | — | 4 |
| 2026-09 | 5.1K | — | 4 |
| 2026-08 | 4.2K | +15.0% | 4 |
| 2026-07 | 3.6K | — | 4 |
| 2026-05 | 2.4K | — | 4 |
| 2026-03 | 1.4K | — | 2 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
# Office to Markdown Converter Skill (v2) ## Description Convert office documents (PDF, DOC, DOCX, PPTX) to Markdown format. This skill uses the word-extractor library for .doc support and provides full OpenClaw integration. ## When to Use - When you need to extract text from office documents - When you want to convert documents to readable Markdown format - When analyzing document content in OpenClaw - Specifically when dealing with legacy .doc format files
## Supported Formats
- **PDF (.pdf)**: Text extraction using pdf-parse
- **Word (.docx)**: Formatting preservation using mammoth + turndown
- **Legacy Word (.doc)**: Text extraction using word-extractor (supports Chinese encoding)
- **PowerPoint (.pptx)**: Basic text extraction using python-pptx
## Dependencies
- Node.js with npm packages: pdf-parse, mammoth, turndown, word-extractor
- Python3 with python-pptx (for PPTX conversion, optional)
- OpenClaw exec tool permission
## Installation
### 1. Copy the skill to your workspace:
```bash
cp -r /root/.openclaw/workspace/office-to-md-v2/office-to-md /path/to/your/workspace/
```
### 2. Install dependencies:
```bash
cd /path/to/your/workspace/office-to-md
npm install
```
### 3. For PPTX support (optional):
```bash
pip3 install python-pptx
```
## Usage in OpenClaw
### Method 1: Direct exec call
```javascript
// Convert any supported document
const result = await exec(
'node /path/to/office-to-md/openclaw-skill.js /path/to/document.doc',
{ workdir: '/path/to/workspace', timeout: 60000 }
);
if (result.exitCode === 0) {
console.log('✅ Document converted successfully');
// Output file: /path/to/document.md
} else {
console.error('❌ Conversion failed:', result.stderr);
}
```
### Method 2: Using the wrapper function
```javascript
// Import the converter
const { convertOfficeToMarkdown } = require('/path/to/office-to-md/openclaw-skill.js');
// Convert document
const conversionResult = await convertOfficeToMarkdown('/path/to/document.pdf');
if (conversionResult.success) {
console.log(`Output: ${conversionResult.outputPath}`);
console.log(`Preview: ${conversionResult.preview}`);
} else {
console.error(`Error: ${conversionResult.error}`);
}
```
### Method 3: Complete OpenClaw integration function
```javascript
async function convertDocumentToMarkdown(filePath) {
// Validate file exists
try {
await read(filePath);
} catch (error) {
return { success: false, error: `File not found: ${filePath}` };
}
// Check file extension
const ext = filePath.toLowerCase().slice(-5);
const supported = ['.pdf', '.doc', '.docx', '.pptx'];
if (!supported.some(s => ext.endsWith(s))) {
return {
success: false,
error: `Unsupported file type. Supported: ${supported.join(', ')}`
};
}
// Convert using the skill
const cmd = `node /path/to/office-to-md/openclaw-skill.js "${filePath}"`;
const result = await exec(cmd, {
workdir: '/path/to/workspace',
timeout: 120000 // 2 minutes for large files
});
if (result.exitCode === 0) {
const outputPath = filePath.replace(/\.[^/.]+$/, '.md');
return {
success: true,
outputPath: outputPath,
message: `Converted to: ${outputPath}`
};
} else {
return {
success: false,
error: result.stderr || 'Conversion failed'
};
}
}
// Usage example
const result = await convertDocumentToMarkdown('/path/to/document.doc');
if (result.success) {
const markdown = await read(result.outputPath);
console.log(markdown.substring(0, 1000));
}
```
## Examples
### Example 1: Convert and analyze a document
```javascript
// Convert a .doc file and analyze its content
const docPath = '/path/to/document.doc';
const convertResult = await exec(
`node /path/to/office-to-md/openclaw-skill.js "${docPath}"`,
{ workdir: '/path/to/workspace' }
);
if (convertResult.exitCode === 0) {
const mdPath = docPath.replace('.doc', '.md');
const content = await read(mdPath);
// Analyze the content
const wordCount = content.split(/\s+/).length;
const lines = content.split('\n').length;
const hasChinese = /[\u4e00-\u9fff]/.test(content);
console.log(`Document analysis:`);
console.log(`- Word count: ${wordCount}`);
console.log(`- Lines: ${lines}`);
console.log(`- Contains Chinese: ${hasChinese}`);
console.log(`- Preview: ${content.substring(0, 200)}...`);
}
```
### Example 2: Batch conversion
```javascript
// Convert multiple documents of different formats
const documents = [
'/path/to/report.pdf',
'/path/to/legacy.doc',
'/path/to/modern.docx',
'/path/to/presentation.pptx'
];
const results = [];
for (const doc of documents) {
console.log(`Converting ${doc}...`);
const result = await exec(
`node /path/to/office-to-md/openclaw-skill.js "${doc}"`,
{ workdir: '/path/to/workspace', timeout: 90000 }
);
const success = result.exitCode === 0;
results.push({
file: doc,
success: success,
error: success ? null : result.stderr
});
console.log(success ? '✅ Success' : '❌ Failed');
}
// Summary
const successful = results.filter(r => r.success).length;
console.log(`\nConversion summary: ${successful}/${results.length} successful`);
```
## API Reference
### convertOfficeToMarkdown(filePath)
Returns a Promise that resolves to:
```javascript
{
success: boolean,
outputPath?: string,
markdown?: string,
preview?: string,
fileType?: string,
message?: string,
stats?: {
lines: number,
characters: number,
words: number
},
error?: string,
stack?: string
}
```
## Configuration
### Timeout Settings
- Small files (<1MB): 30 seconds
- Medium files (1-10MB): 60 seconds
- Large files (>10MB): 120 seconds
### Memory Limits
- Default Node.js memory limit is sufficient for most documents
- For very large files, you may need to increase memory:
```bash
node --max-old-space-size=4096 openclaw-skill.js large-file.doc
```
## Troubleshooting
### Common Issues
1. **"File not found"**
- Check file path and permissions
- Use absolute paths for reliability
2. **"Unsupported file type"**
- Ensure file has correct extension
- Check if file is actually the claimed format
3. **Conversion errors with .doc files**
- The file may be corrupted or in an unusual format
- Try opening in Word and saving as .docx first
4. **Chinese text appears as gibberish**
- word-extractor should handle Chinese encoding automatically
- If issues persist, the file may use unusual encoding
5. **Timeout errors**
- Increase timeout for large files
- Check system resources
### Debug Mode
Enable debug logging by setting environment variable:
```bash
DEBUG=office-to-md node openclaw-skill.js document.doc
```
## Performance
- PDF: Fast, depends on file size
- DOCX: Fast to medium, good formatting preservation
- DOC: Medium, requires binary parsing
- PPTX: Slow, requires Python and external library
## Limitations
- Images in documents are not extracted
- Complex formatting may not be fully preserved
- Tables may convert imperfectly to Markdown
- Very old or corrupted .doc files may fail
- Password-protected files are not supported
## Changelog
### v2.0.0 (2026-02-15)
- Added full .doc support using word-extractor
- Fixed ESM compatibility issues with pptConverter
- Added comprehensive OpenClaw integration
- Improved Chinese text extraction
- Added structured output with statistics
### v1.0.0 (Initial)
- Basic PDF, DOCX, PPTX support
- Simple conversion without .doc support
## License
This skill is provided as-is. The underlying libraries have their own licenses:
- pdf-parse: MIT
- mammoth: BSD-2-Clause
- turndown: MIT
- word-extractor: MIT
- python-pptx: MITA full manual for creating, editing, and managing Tencent Docs through MCP.
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)
A skill that generates PPT decks from a topic and style.
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。
The official skill for working with Kdocs cloud documents through kdocs-cli.
Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.