菜单
This skill should be used when the user asks to "convert a document to markdown", "extract text from PDF", "convert Word/PowerPoint/Excel to markdown", or needs to transform documents into markdown format.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mfmezger/ai_agent_dotfiles --skill convert-to-markdown命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | convert-to-markdown |
| description | This skill should be used when the user asks to "convert a document to markdown", "extract text from PDF", "convert Word/PowerPoint/Excel to markdown", or needs to transform documents into markdown format. |
| version | 0.1.0 |
Convert various document formats to Markdown using markitdown and pandoc.
| Format | Extension | Notes |
|---|---|---|
| Text + OCR hybrid mode available | ||
| Word | .docx | Full support |
| PowerPoint | .pptx | Extracts text from slides |
| Excel | .xlsx | Converts tables |
| HTML | .html, .htm | Full support |
| EPUB | .epub | Via pandoc |
| Images | .jpg, .png, .gif, .webp | OCR extraction |
| Google Docs | URL | Public docs, exports as docx |
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py INPUT
| Flag | Description |
|---|---|
-o, --output PATH | Output path (default: input.md next to original) |
--mode auto|ocr|text | Extraction mode (default: auto) |
--hybrid | PDF only: run both text + OCR, merge results |
# Basic conversion (saves as document.md)
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py document.pdf
# Force OCR mode for scanned document
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py scanned.pdf --mode ocr
# Hybrid extraction for PDFs with mixed content
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py report.pdf --hybrid
# Convert Word document
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py report.docx
# Convert public Google Doc
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py "https://docs.google.com/document/d/DOCUMENT_ID/edit"
# Specify output location
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py slides.pptx -o notes.md
For Google Docs conversion:
https://docs.google.com/document/d/DOC_ID/editfilename.md next to the original file-o to specify a different locationbrew install pandoc # macOS