Help us improve
Share bugs, ideas, or general feedback.
From interpretive-orchestration-cowork
This skill should be used when users need to convert PDFs (especially with tables or figures), mentions 'convert', 'PDF', 'document processing', has complex academic papers to import, or asks about document conversion options.
npx claudepluginhub linxule/interpretive-orchestration --plugin interpretive-orchestration-coworkHow this skill is triggered — by the user, by Claude, or both
Slash command
/interpretive-orchestration-cowork:skills/document-conversionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Robust PDF and document conversion with intelligent tool selection. Chooses the best available conversion method based on document complexity and MCP availability.
Parses PDF, Office, and image files into structured Markdown using the MinerU API. Supports OCR, formula/table recognition, batch processing, and multi-format export (DOCX/HTML/LaTeX).
Routes PDF conversions through analysis to select the best extraction strategy and tools based on document type and output format.
Parses PDFs, DOCX, PPTX, HTML, images (20+ formats) to Markdown/HTML/JSON/text with layout/tables/OCR. Chunks for RAG pipelines; batch converts via DocumentConverter.
Share bugs, ideas, or general feedback.
Robust PDF and document conversion with intelligent tool selection. Chooses the best available conversion method based on document complexity and MCP availability.
Use this skill when:
| Feature | MinerU (Optional) | Manual Conversion |
|---|---|---|
| API Key Required | Yes (MINERU_API_KEY) | No |
| PDF Accuracy | 90%+ (VLM mode) | Varies |
| Table Extraction | Excellent | Manual cleanup |
| Figure Handling | Extracts + describes | Manual description |
| Formula Recognition | Yes | Limited |
| Multi-column | Excellent | Manual formatting |
| Cost | Pay per page | Free |
Is the document a PDF with tables/figures?
├── Yes, complex tables
│ └── MinerU available?
│ ├── Yes → Use MinerU (vlm mode)
│ └── No → Manual conversion + review
├── Yes, simple formatting
│ └── Manual conversion or external tool
└── No, other format
└── Is it audio?
├── Yes → External transcription service
└── No → Manual conversion
Use mineru_parse to convert this academic paper:
- URL: https://example.com/paper.pdf
- Model: vlm (for 90% accuracy)
- Enable: formula, table recognition
For simple PDFs without MinerU:
1. Use Adobe Acrobat to export to Word/text
2. Or open in Google Docs for auto-OCR
3. Review and clean up formatting
For multiple PDFs:
1. Check which have complex tables (use MinerU if available)
2. Process simple ones with manual conversion
3. Queue complex ones for MinerU batch if API key available
Parse only specific pages:
mineru_parse({
url: "https://...",
pages: "1-10,15,20-25"
})
Process multiple documents:
mineru_batch({
urls: ["url1", "url2", "url3"],
model: "vlm"
})
After conversion, verify:
If MinerU unavailable:
For audio files, use external services: