Convert PDF, Word, PPT, and image files into structured Markdown via the MinerU API.
npx skills add https://github.com/syzl8512/openclaw-experience --skill mineru
Please help me install this Agent Skill. Skill: mineru Source: https://github.com/syzl8512/openclaw-experience/tree/main/03_%E6%A0%B8%E5%BF%83Skill/mineru Command: npx skills add https://github.com/syzl8512/openclaw-experience --skill mineru
This Skill automates the conversion of various document types (PDF, Word, PPT, images) into structured Markdown, preserving complex elements like formulas and tables, and enabling OCR for images.
Use the mineru skill to parse the PDF document located at https://example.com/document.pdf into Markdown format.
High-intent search queries and answers about installing and using this skill.
To convert a PDF to Markdown while preserving tables and formulas, use a document conversion tool that supports LaTeX extraction and table recognition. This Skill accurately parses complex layouts into structured Markdown format using the MinerU API.
Yes, you can extract text from images and convert them to Markdown. This Skill uses OCR capabilities to recognize text within JPG and PNG files, transforming image-based content into structured Markdown documents.
The best way to convert Word and PPT files into structured Markdown is using an automated document parsing tool. This Skill supports DOCX and PPTX formats, accurately extracting text and structural elements for seamless integration into knowledge bases.
Yes, this document conversion tool supports multi-language documents. It leverages the MinerU API to perform OCR and intelligent parsing, accurately extracting text from various document types and images regardless of language.
To parse a research paper PDF into a clean Markdown document, provide the file URL to this Skill. It automates the conversion process, preserving complex elements like formulas via LaTeX and tables for easier reading.
When converting scanned PDFs to Markdown, this Skill relies on OCR to extract text from images. While it handles complex layouts and multi-language documents effectively, heavily degraded scans may impact OCR accuracy and overall parsing results.
huidgeExtract text from PDFs and scanned documents into Markdown.
sixscripts-aiOptimize retrieval-augmented generation pipelines for LLM-powered tasks.
guihousunRender GitHub-flavored Markdown and Streamlit extensions via st.markdown.
Wike-CHIExtract text, tables, and images from PDFs, DOCX, PPTX, XLSX, and plain text.
