skills.rest
theowenyoung
theowenyoungCOMMUNITY
Explore all skills by this author →
Website𝕏@TheOwenYoungGitHub

add-pdf-reader

Extract text from PDF documents using pdftotext for NanoClaw agents.

Updated Mar 12, 2026
Search Tags:#pdf#cli#whatsapp#container#attachments#pdftotext#poppler-utils
One-click install
npx skills add https://github.com/theowenyoung/nanoclaw --skill add-pdf-reader
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-pdf-reader
Source: https://github.com/theowenyoung/nanoclaw/tree/main/.claude/skills/add-pdf-reader
Command: npx skills add https://github.com/theowenyoung/nanoclaw --skill add-pdf-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many NanoClaw agents cannot natively read or extract text from PDF documents sent via chat, URLs, or stored locally, which prevents automation workflows from understanding and summarizing reports, contracts, and other documents. This skill adds deterministic PDF extraction so agents can process PDF content safely inside their containerized runtime without exposing the host.

Core Features & Use Cases

  • Adds a pdf-reader CLI that wraps poppler-utils (pdftotext/pdfinfo) for extract, fetch, info, and list operations.
  • Integrates PDF handling into the container image by merging poppler-utils and installing a pdf-reader script, and patches the WhatsApp channel to auto-download PDF attachments into the group's attachments/ directory.
  • Use cases: have an agent summarize a report sent via WhatsApp, fetch and index a public PDF URL, or extract specific pages/tables from a saved report.

Quick Start

Ask the assistant to read attachments/report.pdf and summarize the document's main points.

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 sent via WhatsApp?▼

To extract text from WhatsApp PDF attachments, this skill patches the WhatsApp channel to auto-download files into a group attachments directory, then runs pdftotext to make the extracted content available for agent summarization.

Can I fetch and extract text from a PDF URL inside a containerized agent?▼

Yes, you can fetch and extract text from a PDF URL inside a containerized agent. The skill uses a pdf-reader CLI wrapper to fetch remote documents and runs pdftotext extraction safely within the isolated container runtime.

Do I need poppler-utils installed to read PDFs with my agent?▼

Yes, poppler-utils is required. The skill merges poppler-utils into the container image to provide the underlying pdftotext and pdfinfo command-line tools needed for deterministic PDF text and metadata extraction.

What is the best way to summarize a PDF report received in a chat workflow?▼

The best way to summarize a chat PDF report is using a pdf-reader CLI that wraps poppler-utils to extract text locally, allowing the agent to process and summarize the document content without exposing the host system environment.

Does this approach support extracting specific pages or document info from local PDFs?▼

Yes, the pdf-reader CLI supports extract, fetch, info, and list operations. It utilizes poppler-utils like pdfinfo to retrieve document metadata and pdftotext to extract specific pages from saved local PDF reports.

Related Skills

Explore More Software Engineering Skills→
stevengonsalvezstevengonsalvez

add-pdf-reader

Extract text from PDF files via WhatsApp attachments, URLs, or local uploads.

Community
Intermediate
MicrockMicrock
322

PDF Processing

Extract text and tables from PDF files with pdfplumber.

Community
Advanced
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