skills.rest
dfpalhano
dfpalhanoCOMMUNITY
Explore all skills by this author →
GitHub

mineru-pdf

Parse PDF documents to extract text, tables, and formulas.

Updated Feb 26, 2026
Search Tags:#ocr#pdf#text extraction#mlx#parser#table extraction#formula extraction
One-click install
npx skills add https://github.com/dfpalhano/openclaw-workspace --skill mineru-pdf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mineru-pdf
Source: https://github.com/dfpalhano/openclaw-workspace/tree/main/skills/mineru-pdf
Command: npx skills add https://github.com/dfpalhano/openclaw-workspace --skill mineru-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of structured content from PDF documents, saving significant time and effort compared to manual data entry or processing.

Core Features & Use Cases

  • Comprehensive Extraction: Extracts text, tables, and mathematical formulas from PDFs.
  • Multiple Backends: Supports various processing backends, including MLX-accelerated inference on Apple Silicon for optimal performance.
  • Use Case: Quickly process a batch of research papers to extract all tables and formulas for a literature review, or extract key information from scanned invoices.

Quick Start

Use the mineru-pdf skill to parse the PDF document located at /path/to/document.pdf and save the output to /path/to/output.

Frequently Asked Questions about mineru-pdf

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

FAQPage Schema
How do I extract text, tables, and formulas from PDF documents?▼

You can extract text, tables, and formulas from PDFs by using a parser that supports multiple backends and OCR to process both digital and scanned documents into structured content.

Can I use MLX-accelerated inference on Apple Silicon for PDF text extraction?▼

Yes, you can use MLX-accelerated inference on Apple Silicon for PDF text extraction, offering optimal performance when parsing documents and extracting structured tables and formulas.

Does OCR work for extracting tables from scanned PDF files?▼

Yes, built-in OCR handles scanned PDF files and various image formats, successfully extracting text, tables, and formulas from documents that are not digitally native.

What is the best way to process a batch of research papers to extract tables and formulas?▼

The best way to extract tables and formulas from research papers is using an automated PDF parser, which processes multiple documents to pull structured data for literature reviews.

How do I save extracted PDF content to a specific output path?▼

You can save extracted PDF content by using a direct tool designed for persistent file saving, specifying the input document path and the desired output directory.

What is the difference between persistent file saving and temporary processing for PDF parsing?▼

Persistent file saving stores extracted PDF content on disk, while temporary processing handles data transiently within Claude Code using an MCP method without saving output files.

Related Skills

Explore More Software Engineering Skills→
joonlabjoonlab
8

deepseek-ocr

Extract text from images and PDFs using the DeepSeek-OCR-8bit model.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
musical-basicsmusical-basics

mcporter

Manage MCP servers and invoke tools from the terminal.

Community
Intermediate
psd401psd401
2

local-tts

Generate speech audio with MLX acceleration and the Kokoro-82M model on Apple Silicon.

Official
Intermediate