Convert PDF, Word, image, audio, and video files to Markdown.
npx skills add https://github.com/NNNightglow/replay --skill multiformat-to-md
Please help me install this Agent Skill. Skill: multiformat-to-md Source: https://github.com/NNNightglow/replay/tree/main/skills/multiformat-to-md Command: npx skills add https://github.com/NNNightglow/replay --skill multiformat-to-md
This Skill automates the conversion of various file formats into Markdown, facilitating easy ingestion by language models.
Convert the 'annual_report.pdf' and 'interview.mp4' files to Markdown and save the results to 'output.md'.
High-intent search queries and answers about installing and using this skill.
To convert PDF and Word files to Markdown, the Skill extracts text using pypdf and python-docx, structuring the output for LLM ingestion. It automates data preprocessing for language model training and inference.
Yes, you can extract text from images for LLM training using pytesseract and pillow. The Skill performs OCR on image files to convert embedded text into Markdown, streamlining data preprocessing for language model ingestion.
Transcribe audio and video files to Markdown using openai-whisper and faster-whisper. The Skill handles media transcription by converting spoken audio into structured text, requiring ffmpeg for processing multimedia inputs.
Yes, installing ffmpeg and tesseract-ocr is required for full functionality. Ffmpeg handles audio and video processing for transcription, while tesseract-ocr performs text extraction from images during Markdown conversion.
Automating data preprocessing for mixed file formats is best handled by a multiformat conversion Skill supporting PDFs, Word, images, and audio. It standardizes diverse inputs into Markdown for language model ingestion.
Yes, multiformat-to-md supports converting mixed formats like PDFs and mp4 files in a single batch. It extracts document text and transcribes media simultaneously, outputting structured Markdown for LLM ingestion.
spoonboboConvert PDFs, DOCX, and images to text, markdown, or searchable PDFs.
u9401066Extract text, figures, and citations from PDFs into Markdown.
jkitchinSelect and apply Matplotlib, Seaborn, or Plotly for Python visualizations.
anilcan-karaExtract text from PDFs and scanned documents using pymupdf or marker-pdf.
