pdf-vision

Community

Intelligent PDF to Markdown conversion.

Authorcdeistopened
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill tackles the challenge of converting complex PDF documents, especially scanned ones, into clean, usable Markdown, overcoming the limitations of traditional text-based extraction methods.

Core Features & Use Cases

  • Vision-Powered Conversion: Utilizes AI vision models to understand document layout, tables, and text, even in scanned or degraded documents.
  • Robust Extraction: Handles multi-column layouts, tables, footnotes, and flowcharts that often break standard PDF parsers.
  • Use Case: Convert a scanned, multi-page government form with complex tables and handwritten annotations into a structured Markdown document for easier analysis and data entry.

Quick Start

Use the pdf-vision skill to convert the attached document 'annual-report.pdf' into markdown format.

Dependency Matrix

Required Modules

pymupdfgoogle-genai

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: pdf-vision
Download link: https://github.com/cdeistopened/skill-stack/archive/main.zip#pdf-vision

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.