Convert documents and media into structured Markdown text.
npx skills add https://github.com/shushuzn/Rairos --skill markitdown-shushuzn
Please help me install this Agent Skill. Skill: markitdown Source: https://github.com/shushuzn/Rairos/tree/main/skills/markitdown Command: npx skills add https://github.com/shushuzn/Rairos --skill markitdown-shushuzn
This Skill turns complex documents into clean, LLM-friendly Markdown so you can read, search, and reuse their content without manual formatting work.
Ask the AI to convert your file to Markdown by running: markitdown your_document.pdf -o output.md.
High-intent search queries and answers about installing and using this skill.
To convert PDFs and DOCX files to Markdown for literature review ingestion, use a Python-based conversion pipeline that detects file formats and outputs structured text. This process transforms documents into clean, LLM-friendly Markdown for downstream reading and analysis without manual formatting work.
Yes, you can extract text from scanned PDFs and images using built-in OCR support. The conversion pipeline applies OCR to scanned documents and images to produce usable text output, ensuring visual content is captured as structured Markdown.
The best way to transcribe audio files into Markdown text is through a conversion pipeline with transcription support. It processes audio inputs directly, generating structured Markdown text that can be piped to files or processed in batch scripts for data extraction workflows.
Yes, the conversion pipeline supports spreadsheets and PPTX slides. It extracts data from spreadsheets and captures presentation notes from slides, converting them into structured Markdown text for downstream analysis and search.
To generate detailed descriptions for scientific figures and slides, enable optional AI-enhanced image understanding via an LLM provider. This feature improves fidelity for visual content by producing descriptive text within the final Markdown output.
Yes, you can convert YouTube URLs and ZIP archives into Markdown. The pipeline supports URL ingestion and archive extraction, transforming diverse media file formats into clean, LLM-friendly Markdown text for downstream analysis.
Leon102938Transcribe audio to timestamped lyrics in LRC, SRT, or JSON formats.
PancrePal-xiaoyibaoExtract text from local PDF files into structured Markdown format.
Ritabrata-ChakrabortyGenerate and edit images from text descriptions using AI models.
adiytharpansaExtracts text from images, screenshots, and scanned documents using OCR.
