skills.rest
xpert-ai
xpert-aiOFFICIAL
Explore all skills by this author →
Website𝕏@xpertai_cloudGitHub

mineru

Extract structured text from PDF, Word, PPT, image, and HTML documents.

8|12|Updated Sep 19, 2025
Search Tags:#ocr#markdown#document conversion#text extraction#pdf extraction#document parsing#mineru
One-click install
npx skills add https://github.com/xpert-ai/xpert-plugins --skill mineru-xpert-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mineru
Source: https://github.com/xpert-ai/xpert-plugins/tree/main/xpertai/middlewares/mineru-cli/src/lib/skills
Command: npx skills add https://github.com/xpert-ai/xpert-plugins --skill mineru-xpert-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Users often need to extract structured, editable text from messy, multi-format documents like scanned PDFs, presentations, or web pages, but manual transcription is time-consuming and specialized conversion tools are often expensive or hard to use.

Core Features & Use Cases

  • Multi-format Document Conversion: Supports PDF, Word, PPT, images, HTML and more, converting them to Markdown, Docx, HTML or LaTeX formats.
  • High-Accuracy Parsing: Uses advanced VLM models for complex layouts and mixed content, with built-in OCR for scanned documents to extract text, tables and formulas accurately.
  • Use Case: A researcher can upload a 50-page scanned academic paper and get a fully searchable, editable Markdown file with all structured content preserved automatically.

Quick Start

Use the mineru skill to convert the attached quarterly sales report PDF to clean Markdown with all tables and formulas preserved.

Frequently Asked Questions about mineru

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

FAQPage Schema
How do I convert a scanned PDF to editable Markdown with tables and formulas preserved?▼

To convert scanned PDF to Markdown, the skill applies high-accuracy OCR and VLM models for complex layout parsing, accurately detecting and preserving tables, formulas, and structured content in the output.

What is the best way to extract text from Word, PPT, and HTML files for web archiving?▼

The best way to extract text from Word, PPT, images, and HTML files is using multi-format document conversion, which parses unstructured digital and scanned documents into structured, editable Markdown or Docx formats.

Does this document parsing approach work for long academic papers with complex layouts?▼

Yes, this document parsing approach works for long academic papers. It uses advanced VLM models to handle complex layouts and mixed content, extracting structured text from 50-page scanned documents into fully searchable files.

Can I extract structured content from PDFs when processing resources are limited?▼

Yes, you can extract structured content from PDFs with limited resources. The skill uses integrated cloud APIs for multi-format output generation with an automatic fallback mechanism designed specifically for limited-resource environments.

What output formats can I generate when converting PDF files besides Markdown?▼

When converting PDF files, you can generate Markdown, Docx, HTML, or LaTeX formats. The skill extracts structured, editable text from unstructured multi-format digital and scanned documents for versatile downstream use.

Related Skills

Explore More Content & Communication Skills→
hyperbolic-chyperbolic-c
5

markitdown

Convert PDFs, Word, PPTX, Excel, HTML, EPUB, and images to Markdown.

Community
Advanced
captainflasmrcaptainflasmr
100

emacs-academic-writing

Automate Emacs academic writing workflows for Org-mode and LaTeX documents.

Community
Intermediate
TopduTopdu
1.4k

openocr-skills

Extract text, formulas, and tables from images and scanned PDFs.

Community
Intermediate
trpc-grouptrpc-group
1.6k

ocr

Extract text from images using pytesseract and Pillow.

Official
Advanced