skills.rest
erguotou520
erguotou520COMMUNITY
Explore all skills by this author →
WebsiteGitHub

add-pdf-reader

Extract text from PDFs in NanoClaw agent workflows.

Updated Mar 10, 2026
Search Tags:#document processing#pdf#text extraction#whatsapp#container#pdftotext
One-click install
npx skills add https://github.com/erguotou520/myclaw --skill add-pdf-reader-erguotou520
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-pdf-reader
Source: https://github.com/erguotou520/myclaw/tree/main/.claude/skills/add-pdf-reader
Command: npx skills add https://github.com/erguotou520/myclaw --skill add-pdf-reader-erguotou520

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the need for manual PDF handling by giving NanoClaw agents a reliable way to read and extract text from PDF documents.

Core Features & Use Cases

  • PDF Text Extraction: Uses command-line PDF utilities to convert readable PDFs into text for agent consumption.
  • WhatsApp Attachment Support: Automatically downloads PDF attachments from WhatsApp chats into the shared workspace.
  • URL and Local File Reading: Lets agents fetch PDFs from web links or inspect files already present on disk.
  • Use Case: A user sends a contract, invoice, or report as a PDF in chat and the agent can immediately extract the contents and respond with the relevant information.

Quick Start

Merge the pdf-reader skill into NanoClaw, rebuild the container, and restart the service so agents can read PDFs from attachments, URLs, and local files.

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 received in WhatsApp chats?▼

You can extract text from WhatsApp PDF attachments by merging this Skill into NanoClaw, which automatically downloads files into the shared workspace and converts readable PDFs into text using command-line utilities for immediate agent consumption.

Can NanoClaw agents read PDFs from remote URLs and local files?▼

NanoClaw agents can read PDFs from remote URLs and local files. The Skill fetches external PDF documents via web links and inspects existing files within containerized agents to extract their text contents.

Do I need poppler-utils to enable PDF text extraction in containerized agents?▼

Poppler-utils integration is required to enable PDF text extraction. You must merge the Skill into NanoClaw, rebuild the container with poppler-utils, and restart the service so agents can process attachments and files.

What is the best way to automate PDF document processing for chat agents?▼

Automating PDF document processing for chat agents requires a dedicated text extraction workflow. This removes manual handling by letting agents directly process contracts, invoices, and reports received as PDF attachments or URLs.

Why does PDF text extraction fail inside my agent container?▼

PDF text extraction fails inside agent containers when poppler-utils is not integrated during the container build pipeline. You must rebuild the container with the required utilities and validate the setup through the WhatsApp channel.

Related Skills

Explore More Software Engineering Skills→
iceflowericeflower
1

pdf-handling

Convert specified PDF pages to PNG images and extract text content.

Community
Intermediate
ygfuyfffdf-maxygfuyfffdf-max

pdf

Extract text, tables, and metadata from PDFs using Python scripts.

Community
Advanced
spyqsspyqs

add-pdf-reader

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

Community
Intermediate
trpc-grouptrpc-group
1.6k

ocr

Extract text from images using pytesseract and Pillow.

Official
Advanced