Extract text from PDFs via WhatsApp, URLs, or local files using pdftotext.
npx skills add https://github.com/sliamh11/Deus --skill add-pdf-reader-sliamh11
Please help me install this Agent Skill. Skill: add-pdf-reader Source: https://github.com/sliamh11/Deus/tree/main/.claude/skills/add-pdf-reader Command: npx skills add https://github.com/sliamh11/Deus --skill add-pdf-reader-sliamh11
PDFs often contain critical information trapped in images or scattered across chat attachments. This skill solves the challenge of converting PDF content into searchable, readable text that Deus agents can process within their workflows.
Instruct the agent to read a PDF attachment or URL and extract its text for downstream tasks.
High-intent search queries and answers about installing and using this skill.
Extracting text from PDF attachments in WhatsApp is handled by downloading the files to your workspace and running the pdftotext CLI to convert them into searchable plain text for agent processing.
Reading PDFs from a URL or local file path is fully supported, as the tool channels these sources into the pdftotext CLI to extract plain text for downstream agent analysis.
Poppler-utils must be installed in the container, because the text extraction relies on its pdftotext CLI to parse PDF content into readable text for the agents.
Processing invoices and documents trapped in PDF files is best handled by using pdftotext-based extraction, which converts the content into plain text for in-context review and summarization.
Extracting text from image-based PDFs using pdftotext may yield poor results, as this approach parses embedded text layers rather than performing OCR on images to retrieve content.
Arno37Extract text from PDFs via the pdftotext CLI for NanoClaw agents.
sunchenddExtract text and tables from PDFs using Python libraries.
erguotou520Extract text from PDFs in NanoClaw agent workflows.
samlaggzExtract text and data from PDFs and scanned documents.
