extract-pdf

Community

Turn any PDF into structured markdown + images.

AuthorKaihuaTang
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It converts PDFs into Claude-readable content without losing structure, figures, tables, or scanned-page visuals that naive text extraction often mangles.

Core Features & Use Cases

  • Structured Markdown extraction: Preserves headings, lists, and tables so you can summarize and analyze like it’s a readable document.
  • Per-page rendered images: Produces PNGs so Claude can directly interpret charts, equations, and scanned pages in a multimodal way.
  • Complementary plain-text extraction: Uses a second extractor to recover text when the first pass misreads tricky layouts, encoding, or typography.
  • Use Case: When you ask Claude to “look inside this PDF,” this skill prepares a full workspace (manifest + files) for fast, reliable downstream reading and analysis.

Quick Start

Run the extract-pdf skill on your PDF at a given path or URL, writing outputs into an extraction folder, for example by instructing Claude to execute the provided command on your target PDF input.

Dependency Matrix

Required Modules

pymupdf4llmpdfminer.sixpymupdf

Components

scripts

💻 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: extract-pdf
Download link: https://github.com/KaihuaTang/Index.skill/archive/main.zip#extract-pdf

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 471,000+ vetted skills library on demand.