What problem does it solve? Binary documents like PDFs, DOCX files, and scanned images cannot be read directly by text-based tools, blocking AI workflows that need their content. This Skill converts them into Markdown so the text becomes usable for downstream processing. ## Core Features & Use Cases - Broad Format Support: Converts PDF, DOC, DOCX, PPTX, XLS, XLSX, ODS, ODT, RTF, HTML, and images (PNG, JPG, TIFF, BMP, GIF, WEBP) to Markdown. - ZIP Archive Handling: Processes ZIP archives directly, converting every contained file without manual unzipping first. - Structured Output: Returns a JSON path to a result ZIP containing the converted Markdown files next to the source file. - Use Case: You receive a scanned invoice as a PDF and a photo of a signed contract. Run the conversion on both, unzip the results, and immediately work with the extracted text for summarization or data entry. ## Quick Start Ask the assistant to convert your binary document to Markdown by providing its absolute file path, for example to extract the text from a scanned invoice PDF.
