skills.rest
loongclaw-ai
loongclaw-aiOFFICIAL
Explore all skills by this author →
Website𝕏@loongclawaiGitHub

pdf

Extract text, tables, and images from PDF documents.

641|104|Updated Mar 5, 2026
Search Tags:#automation#pdf#form filling#text extraction#pdfplumber#pypdf#document-processing
One-click install
npx skills add https://github.com/loongclaw-ai/loongclaw --skill pdf-loongclaw-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/loongclaw-ai/loongclaw/tree/main/skills/anthropic-office/pdf
Command: npx skills add https://github.com/loongclaw-ai/loongclaw --skill pdf-loongclaw-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdf2image, pdfplumber, pillow, and includes scripts (resource) components.

What problem does it solve?

This skill eliminates manual PDF handling by consolidating reading, extraction, transformation, annotation, and generation guidance into one actionable playbook.

Core Features & Use Cases

  • Comprehensive PDF manipulation: pypdf, reportlab, and command-line utilities merge, split, rotate, watermark, encrypt, and decrypt documents while pdfplumber and pypdfium2 extract text, tables, and render images.
  • Form intelligence workflow: Scripts detect fillable fields, extract structure, validate coordinates, and either populate forms or draw annotations on non-fillable layouts so every form can be completed reliably.
  • Use Case: Automate vendor invoice processing by extracting line items, populating review forms, and producing secure, annotated PDFs ready for auditors.

Quick Start

Use the pdf skill to extract text from the uploaded invoice.pdf and summarize the totals.

Frequently Asked Questions about pdf

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

FAQPage Schema
How do I extract text and tables from a PDF for document processing?▼

You can automate PDF text extraction by orchestrating pdfplumber and pypdf to parse structured content. The skill serves document-heavy workflows, reading deterministic layouts to produce actionable text and table outputs for agents.

Can I automatically detect and fill form fields in an existing PDF?▼

Yes, you can fill PDF forms using scripts that detect fillable fields, extract structure, and validate coordinates. The workflow populates fillable forms or draws annotations on non-fillable layouts to complete documents reliably.

What is the best way to merge, split, and watermark PDF files in an automated workflow?▼

The best way to merge, split, or watermark PDFs is using pypdf and command-line utilities within this skill. It automates transformations, handling document manipulation tasks deterministically for downstream assistant workflows.

Does this approach work for rendering PDF pages as images using pdf2image and pillow?▼

Yes, rendering PDF pages as images works by orchestrating pdf2image and pillow to parse and render visual content. This allows agents to process scanned layouts and produce annotated image outputs for review.

How do I redact or annotate sensitive information inside a PDF document?▼

Redact and annotate PDF documents by applying deterministic tooling that modifies content directly. The skill supports annotation workflows, allowing agents to draw on non-fillable layouts and secure files for auditors.

Do I need Python dependencies installed to process PDFs for invoice extraction?▼

Yes, you need Python dependencies including pypdf, pdfplumber, pdf2image, and pillow installed. These libraries provide the deterministic tooling required to extract line items and populate review forms for invoice processing.

Related Skills

Explore More Software Engineering Skills→
szweibelszweibel
2

pdf

Automate PDF text and table extraction, merging, splitting, and form filling.

Community
Advanced
rvdbreemenrvdbreemen
199

pdf

Extracts and manipulates text, tables, images, and forms in PDF documents.

Community
Intermediate
Brilly-BohyunBrilly-Bohyun

ocr-and-documents

Extract text from PDFs and scanned documents using OCR and Python libraries.

Community
Advanced
yanochka11yanochka11

pdf

Extract text, tables, metadata, and images from PDF files.

Community
Advanced