skills.rest
spyqs
spyqsCOMMUNITY
Explore all skills by this author →
GitHub

add-pdf-reader

Extract readable text from PDF attachments in WhatsApp chats, URLs, and local files.

Updated Mar 15, 2026
Search Tags:#pdf#text extraction#whatsapp#document ingestion#url fetching#agent workflows#pdf-reader
One-click install
npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill add-pdf-reader-spyqs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-pdf-reader
Source: https://github.com/spyqs/nanoclaw-email-imap/tree/main/.claude/skills/add-pdf-reader
Command: npx skills add https://github.com/spyqs/nanoclaw-email-imap --skill add-pdf-reader-spyqs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the friction of getting usable text out of PDF files shared in WhatsApp chats, so you can ask questions or extract information without manual downloading and copy-pasting.

Core Features & Use Cases

  • Auto-handles PDF attachments: Detects and downloads PDFs sent as WhatsApp documents into the group workspace.
  • Text extraction via CLI: Converts PDF files into plain text using pdftotext/pdfinfo from poppler-utils for reliable downstream reading.
  • Supports multiple input paths: Works for WhatsApp attachments, direct URLs (via a fetch flow), and local files when available.

Use Case: When a teammate sends a contract or report PDF in WhatsApp, the agent can acknowledge it, extract the text, and answer follow-up questions about what’s inside.

Quick Start

Send a PDF in a WhatsApp chat and ask the agent to read and extract the text from the attached PDF.

Frequently Asked Questions about add-pdf-reader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from PDF documents shared in WhatsApp chats?▼

To extract text from PDF attachments in WhatsApp, this Skill automatically detects and downloads the shared documents, then converts them into plain text using pdftotext. This allows agents to directly read and answer questions about the file contents without manual downloading.

Can I extract text from a PDF using a direct URL instead of a messaging attachment?▼

Yes, URL fetching is supported for PDF text extraction. The Skill uses a dedicated fetch path to download PDFs from direct URLs, alongside its ability to process WhatsApp attachments and local workspace files.

Do I need to install poppler-utils to extract text from PDF files?▼

Yes, poppler-utils is required for PDF text extraction. The container environment must have pdftotext and pdfinfo available, as the Skill relies on these CLI tools to reliably convert PDF documents into readable plain text.

What is the best way to answer questions about a contract PDF sent to my team?▼

The best way to answer questions about a contract PDF is to let the agent ingest it via this Skill. It automatically extracts the text from the shared document, enabling the agent to process the content and provide immediate answers about the file.

Why does PDF text extraction fail in my agent workflow?▼

PDF text extraction fails when the container is missing required CLI dependencies. The Skill explicitly requires pdftotext and pdfinfo from poppler-utils to be installed and available in the environment to successfully process document attachments.

Related Skills

Explore More Content & Communication Skills→
theowenyoungtheowenyoung

add-pdf-reader

Extract text from PDF documents using pdftotext for NanoClaw agents.

Community
Intermediate
claude-office-skillsclaude-office-skills
368

Chat with PDF

Answer questions, summarize, and extract information from PDF documents.

Official
Intermediate
erguotou520erguotou520

add-pdf-reader

Extract text from PDFs in NanoClaw agent workflows.

Community
Intermediate
anilcan-karaanilcan-kara

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf or marker-pdf.

Community
Intermediate