MarkItDown File to Markdown Converter
Paste the following prompt into your AI chat to install this skill:
Install @user_a7465146/markitdown-uvx according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem Solved
Office documents, web pages, and media files are often stored as binary or proprietary formats. Feeding them directly to an LLM can lose structure, create encoding issues, and make batch processing harder. markitdown normalizes these inputs into Markdown while preserving headings, lists, tables, and links, making context easier to parse.
How It Works
It accepts files or stdin via CLI and chooses a conversion path based on extension, MIME type, and encoding hints. Use -o for output, -x pdf for stdin, and --keep-data-uris to retain base64 images. Common formats such as PDF, DOCX, PPTX, XLSX, HTML, EPUB, and CSV are handled directly; ZIP archives are traversed and converted file by file; audio and YouTube need transcription support.
Boundaries
Text extraction is the priority. It does not guarantee faithful reconstruction of PDF images, complex layouts, or scanned content. Audio conversion depends on ffmpeg and transcription components. For richer visual content, combine OCR with a second LLM pass. For batch jobs, verify the required extras are installed to avoid silent format failures.
Use Cases
- Convert a PDF manual to Markdown, extracting headings, lists, and tables for LLM QA.
- Batch convert Excel and HTML files inside a ZIP archive for unified field retrieval.
- Extract structured content from DOCX/PPTX files to build model-readable prompt material.
- Read image EXIF metadata and keep base64 data for downstream visual analysis.
Best For
- RAG system engineers: convert PDF, DOCX, and PPTX into Markdown for model context.
- Data engineers: batch parse Excel and CSV files in ZIP archives to extract table fields.
- Content engineers: convert EPUB and HTML documents into structured text for summaries.
- Evaluation engineers: extract PPTX and Word body text into Markdown for output comparison.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Generates structured and consistently styled academic presentation PPTX files from paper PDFs for graduate seminars.