markdown_converter

Convert a single image to markdown. If the image depicts a flowchart, sequence diagram, class diagram, state machine, ER diagram, Gantt chart, mindmap, pie/quadrant chart, or git graph, emit a ```mermaid``` fenced block. If it's a data table, emit a markdown table. Otherwise, emit a structured markdown description. Use this whenever an image needs to be inlined into a markdown document with its semantic content preserved (not just an OCR dump).

Convert source documents (PDF, Word, PowerPoint, Excel, HTML, EPUB, images, audio, etc.) or URLs to Markdown using Microsoft's markitdown. Auto-installs markitdown + pymupdf + bs4 on first use. Extracts embedded images first and delegates each image to the image-to-markdown agent so flowcharts become mermaid blocks and other images become structured markdown. Reuses previously converted output whenever the same source is requested again and is unchanged — only re-runs the pipeline when the caller's prompt explicitly asks for a refresh. Use this when the user wants to turn one file, a folder of files, or a web URL into clean markdown with semantically-preserved images. Invoke with an absolute source path (file or folder) or an http(s):// URL; output defaults to `<cwd>/tempMarkdown`.

Convert source documents to clean Markdown by delegating to the markitdown-converter agent. Supported sources include PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx), HTML, EPUB, images (.png/.jpg/.jpeg/.webp/.gif/.bmp), audio (.mp3/.wav/.m4a), and data files (.csv/.json/.xml) — single files or whole folders. Trigger this skill WHENEVER the user shares or references such a source and wants to read it, extract it, parse it, dump it, turn it into markdown/text, or make it LLM-friendly — even if they never say the word "markitdown" or "convert". Typical cues include "can you read this PDF", "extract the text from these slides", "parse this spreadsheet", "turn these docs into markdown", "I dragged a folder of reports, summarize them", or simply attaching/mentioning a file of one of the supported types together with any comprehension task. Do NOT attempt the conversion yourself with Read/pdftotext/unzip — always delegate to the `markitdown-converter` agent so caching, image extraction, and semantic image-to-markdown enrichment all work correctly.