add-pdf-reader

To extract text from a PDF in your AI agent, you can use this skill to integrate the `pdftotext` utility. It processes PDF documents from local files, web URLs, or WhatsApp attachments and outputs the extracted text content for your agent to use.

Yes, you can process PDF attachments from WhatsApp using this skill. It handles media downloads directly from WhatsApp attachments and passes the files to `pdftotext` to extract the text content for agent processing.

The best way to read a PDF document from a web URL is to ask your agent to process the provided URL. This skill fetches the online PDF file and leverages `pdftotext` to extract its text content automatically.

Yes, you need `pdftotext` to extract text from local PDF files because this skill leverages it as its core text extraction mechanism. The skill provides the integration layer to pass local files to the utility and return the text output.

This skill performs text extraction using `pdftotext`, which extracts embedded text from standard PDF documents. It does not mention optical character recognition capabilities, so scanned image-only PDFs may not yield extracted text.

Extracting text from PDF invoices sent via WhatsApp allows your AI agent to automatically capture key information from the document. This enables you to parse invoice details and store the extracted text content for later analysis.