Integration
PDF4ME
Comprehensive PDF processing API
PDF4ME provides 60+ PDF operations including conversion, merge, split, compress, OCR, watermark, and digital signatures.
Required Environment
| Name | Type | Description |
|---|---|---|
PDF4ME_API_KEY | secret | API key from PDF4ME Dashboard |
Configuration
version: "1.0"
agents:
my-agent:
provider: claude-code
skills:
- https://github.com/vm0-ai/vm0-skills/tree/main/pdf4meRun
vm0 run my-agent "merge PDF files" \
--secrets PDF4ME_API_KEY=xxxExample Instructions
# PDF Processor Agent
You process PDF files using PDF4ME.
## Workflow
1. Receive PDF file or URL
2. Apply requested operation
3. Download processed file
4. Save to artifacts
## Operations
- Merge, split, compress, OCR
- Convert to/from Word, Excel# Document Converter Agent
You convert documents to/from PDF.
## Workflow
1. Receive source document
2. Convert using PDF4ME API
3. Return converted file
4. Clean up temp files
## Supported Formats
- Word, Excel, PowerPoint, HTML, Images