hawkongz

Mineru PDF — Development skill for Claude Code

Development community

High-accuracy PDF content extraction skill for Claude Code — formulas, images, tables, scanned docs.

How to install Mineru PDF

This entry records only its repository, not the path inside it, so there is no exact command to give. Open hawkongz/mineru-pdf and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Mineru PDF does

High-accuracy PDF content extraction skill for Claude Code — formulas, images, tables, scanned docs. Powered by MinerU.

Alternatives in Development

Spreadsheet — Create, edit, analyze, and visualize spreadsheets with formulas 14.6k ★
L Review Extract — Review Code for Extraction Opportunities 3k ★
Octo Docs — Document delivery with export to PPTX, DOCX, PDF formats 2.8k ★

README

MinerU PDF

High-accuracy PDF content extraction for Claude Code — formulas, images, tables

为 Claude Code 补充复杂 PDF 的高精度内容解析能力

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Platform](https://img.shields.io/badge/Platform-Claude%20Code-blue)](https://code.claude.com) [![Stars](https://img.shields.io/github/stars/hawkongz/mineru-pdf)](https://github.com/hawkongz/mineru-pdf)

Language: English | 简体中文

🔍 The Problem

Claude Code's default pdf skill relies on **pypdf + pdfplumber**. Fine for simple documents, but falls short on complex ones:

Scenario	What actually happens
Math formulas	pypdf outputs garbage like `PrðfðXÞ/C0 ...` — completely unusable
Image extraction	pdfplumber / pypdf cannot extract images; pdfimages gives raw binaries with no position info
Output format	Plain text, losing heading hierarchy, reading order, and image-caption associations
Scanned PDFs	Entirely dependent on pytesseract with tedious setup and mediocre results

💡 Solution

**Does not replace the official pdf skill.** `mineru-pdf` is a standalone skill — use it explicitly when you need high-quality extraction.

Simple PDFs (plain text / single column) → default pdf skill (pypdf, sub-second)
Complex PDFs (formulas / multi-column / scanned) → this skill (MinerU, high accuracy)

Editing operations (merge, split, watermark, encrypt) stay with the official pdf skill
Content extraction with formulas, images, or complex layouts → this skill
Installed independen