skills.rest
smorand
smorandCOMMUNITY
Explore all skills by this author →
𝕏@smorand1980GitHub

pdf-extractor

Extracts PDFs to Markdown with embedded images and AI-generated image catalog via Gemini integration.

Updated Aug 23, 2026
Search Tags:#pdf#markdown#ai#extraction
One-click install
npx skills add https://github.com/smorand/claude-config --skill pdf-extractor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-extractor
Source: https://github.com/smorand/claude-config/tree/main/skills/pdf-extractor
Command: npx skills add https://github.com/smorand/claude-config --skill pdf-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf4llm, anthropic, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill extracts PDFs into AI-friendly Markdown, with optional image analysis and an images catalog for quick visual context.

Core Features & Use Cases

  • Two extraction methods: Primary script-based extraction; optional image-based extraction for complex layouts.
  • AI image analysis: Vertex AI Gemini integration for image descriptions and classification.
  • Markdown output: Generated document.md and images.md with embedded images.

Quick Start

Run the PDF extractor on a file path and review the generated document.md and images.md.

Frequently Asked Questions about pdf-extractor

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

FAQPage Schema
How do I extract text and images from a PDF into Markdown format?▼

PDF extraction converts documents into AI-friendly Markdown by parsing content and embedding images. This Skill uses a Go-based binary engine to extract text, images, and layout structure from standard, multi-page, and complex PDFs, generating document.md with embedded images and an images.md catalog for quick visual reference.

Can I extract PDFs with scanned documents or complex layouts?▼

Yes, this Skill handles scanned documents and complex layouts through two extraction methods: primary script-based extraction and optional image-based extraction. The image-based mode uses Vertex AI Gemini integration to analyze and describe visual content when standard text extraction is insufficient.

What's the best way to prepare PDFs for AI processing and batch workflows?▼

PDF extraction into Markdown is the standard preparation for AI processing. This Skill converts PDFs to Claude Code-compatible Markdown with configurable output paths and cleanup options, supporting both single-file and batch processing workflows with absolute file paths.

Do I need to set up a virtual environment to use PDF extraction?▼

Yes, this Skill requires an isolated virtual environment and depends on pymupdf4llm and the Anthropic SDK. The Go-based extraction engine runs within that environment, with optional Vertex AI Gemini integration for image analysis capabilities.

How does AI image analysis work with extracted PDF images?▼

Vertex AI Gemini integration provides automated image descriptions and classification for extracted PDF images. The Skill generates an images.md catalog that organizes analyzed images with their AI-generated summaries for quick visual context lookup.

What file formats and output do I get from PDF extraction?▼

PDF extraction produces Markdown output: document.md contains text with embedded images, and images.md provides a catalog of extracted images with AI-generated descriptions. This format is optimized for Claude Code workflows and downstream analysis.

Related Skills

Explore More Data & Analytics Skills→
rangerrick337rangerrick337
10

pdf-conversion

Convert PDFs to Markdown with preserved formatting and embedded images.

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

Chat with PDF

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

Official
Intermediate
bowoxdailybowoxdaily

claude-api

Create LLM-powered applications using the Claude/Anthropic SDK.

Community
Advanced
debug-zhuweijiandebug-zhuweijian
13

Geek-skills-mineru-pdf-parser

Convert PDFs and common document formats into Markdown text with optional OCR.

Community
Intermediate