add-pdf-reader

Extract text and metadata from PDFs via a Bash CLI.

1|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/breakcafe/picoclaw --skill add-pdf-reader-breakcafe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-pdf-reader
Source: https://github.com/breakcafe/picoclaw/tree/main/.claude/skills/add-pdf-reader
Command: npx skills add https://github.com/breakcafe/picoclaw --skill add-pdf-reader-breakcafe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables container-based Claude agents to read and extract text from PDF documents by wiring in poppler-utils (pdftotext and pdfinfo) and by handling PDFs uploaded via WhatsApp attachments, URLs, or local files.

Core Features & Use Cases

  • PDF text extraction: convert PDFs to readable text for downstream processing.
  • PDF metadata: retrieve file size and metadata via pdfinfo.
  • Workflow integration: works with existing Dockerfile changes and WhatsApp channel updates to automatically download and reference PDFs in group workspaces.

Quick Start

Use the pdf-reader CLI to extract text from a PDF file, fetch PDFs from a URL, or list PDFs in your workspace.

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 attachments in a NanoClaw container agent?

To extract text from PDF attachments in a NanoClaw container agent, this skill wires in poppler-utils (pdftotext) to convert PDF documents into readable text for downstream processing. It integrates directly with your existing Dockerfile and WhatsApp channel workflows.

Can I retrieve PDF metadata and file size using a CLI in a containerized environment?

You can retrieve PDF metadata and file size in a containerized environment by utilizing the pdfinfo CLI tool provided through poppler-utils. This skill automates metadata retrieval for PDFs ingested from local files, URLs, or WhatsApp attachments.

Does this PDF reader skill support processing files from URLs and WhatsApp group workspaces?

This PDF reader skill supports processing files from URLs and WhatsApp group workspaces by automatically downloading and referencing PDFs within the container workflow. It handles ingestion across these channels to enable seamless text extraction.

What is the best way to automate PDF ingestion for Claude agents handling WhatsApp attachments?

The best way to automate PDF ingestion for Claude agents handling WhatsApp attachments is to apply this skill's Bash CLI integration, which handles Dockerfile changes and WhatsApp channel updates to automatically download and process PDF files.

Do I need poppler-utils to enable PDF text extraction for my container agents?

You need poppler-utils installed in your container to enable PDF text extraction, as this skill relies on its pdftotext and pdfinfo components to parse documents and retrieve metadata within the NanoClaw environment.

Why are my PDF documents not parsing correctly in the NanoClaw environment?

PDF documents may not parse correctly in the NanoClaw environment if poppler-utils is not properly wired into your Dockerfile or if the WhatsApp channel updates for automated file downloading are not correctly configured.