skills.rest
qfwc258
qfwc258COMMUNITY
Explore all skills by this author →
GitHub

markdown-converter

Convert documents, media, and archives to Markdown using markitdown.

1|Updated Mar 25, 2026
Search Tags:#pdf#markdown#document conversion#llm#docx#convert#markitdown
One-click install
npx skills add https://github.com/qfwc258/trae-skills --skill markdown-converter-qfwc258
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: markdown-converter
Source: https://github.com/qfwc258/trae-skills/tree/main/markdown-converter
Command: npx skills add https://github.com/qfwc258/trae-skills --skill markdown-converter-qfwc258

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown.

What problem does it solve? LLMs and text analysis pipelines work best with Markdown, but source content often lives in PDFs, Word documents, spreadsheets, presentations, HTML, or media files. This Skill converts those formats into clean Markdown without requiring any local installation. ## Core Features & Use Cases - Broad Format Support: Convert PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, EPub, ZIP archives, and YouTube URLs to Markdown. - Media Extraction: Pull EXIF metadata and OCR text from images, plus transcription from audio files. - Zero-Install Execution: Runs via uvx markitdown, so dependencies are fetched and cached automatically on first use. - Use Case: You receive a quarterly report as a .docx and a data appendix as .xlsx. Convert both to Markdown in seconds and feed them directly into an LLM for summarization or analysis. ## Quick Start Convert the attached report.pdf to Markdown and save the result as report.md.

Frequently Asked Questions about markdown-converter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a PDF to Markdown from the command line?▼

Run uvx markitdown input.pdf -o output.md to convert a PDF directly to a Markdown file. The uvx runner fetches markitdown automatically, so no prior installation is needed.

What file formats can markitdown convert to Markdown?▼

markitdown supports PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, EPub, ZIP archives, YouTube URLs, images with EXIF and OCR, and audio with transcription.

Can I convert a file from stdin without knowing its type?▼

Yes, pipe the file into uvx markitdown and pass a type hint with -x for extension, -m for MIME type, or -c for charset. For example, cat document | uvx markitdown -x .pdf > output.md.

Why does PDF text extraction produce poor results sometimes?▼

Complex or scanned PDFs may lack a structured text layer, causing incomplete extraction. Use the -d flag with an Azure Document Intelligence endpoint via -e to get higher-quality extraction for those documents.

Does markitdown require installation before use?▼

No installation is required because uvx runs markitdown in an ephemeral environment. The first run caches dependencies, making subsequent conversions faster.

Related Skills

Explore More Content & Communication Skills→
googleworkspacegoogleworkspace
30.3k

recipe-save-email-attachments

Transfer attachments from email to specified Google Drive folders.

Official
Intermediate
kreuzberg-devkreuzberg-dev
9.2k

chunking

Split extracted text into sized chunks for LLM context windows and RAG ingestion.

Official
Intermediate
agilebydesignagilebydesign
1

chunk-content

Break long-form Markdown into chunked files for embedding and memory indexing.

Official
Intermediate
woodfishhhhwoodfishhhh
32

pdf

Extract text and tables from PDFs with fallback extraction strategies.

Community
Intermediate