Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
MarkItDown is a Python utility that converts various file formats into Markdown format, optimized for use with large language models and text analysis pipelines. It preserves document structure (headings, lists, tables, hyperlinks) while producing clean, token-efficient Markdown output.
Use this skill when users request:
Convert Office documents and PDFs to Markdown while preserving structure.
Supported formats:
Basic usage:
from markitdown import MarkItDown
md = MarkItDown()
result = md.convert("document.pdf")
print(result.text_content)
Command-line:
markitdown document.pdf -o output.md
See references/document_conversion.md for detailed documentation on document-specific features.
Extract text from images using OCR and transcribe audio files to text.
Supported formats:
Image with OCR:
from markitdown import MarkItDown
md = MarkItDown()
result = md.convert("image.jpg")
print(result.text_content) # Includes EXIF metadata and OCR text
Audio transcription:
result = md.convert("audio.wav")
print(result.text_content) # Transcribed speech
See references/media_processing.md for advanced media handling options.
Convert web-based content and e-books to Markdown.
Supported formats:
YouTube transcript:
from markitdown import MarkItDown
md = MarkItDown()
result = md.convert("https://youtube.com/watch?v=VIDEO_ID")
print(result.text_content)
See references/web_content.md for web extraction details.
Convert structured data formats to readable Markdown tables.
Supported formats:
CSV to Markdown table:
from markitdown import MarkItDown
md = MarkItDown()
result = md.convert("data.csv")
print(result.text_content) # Formatted as Markdown table
See references/structured_data.md for format-specific options.
Enhance conversion quality with AI-powered features.
Azure Document Intelligence: For enhanced PDF processing with better table extraction and layout analysis:
from markitdown import MarkItDown
md = MarkItDown(docintel_endpoint="<endpoint>", docintel_key="<key>")
result = md.convert("complex.pdf")
LLM-Powered Image Descriptions: Generate detailed image descriptions using GPT-4o:
from markitdown import MarkItDown
from openai import OpenAI
client = OpenAI()
md = MarkItDown(llm_client=client, llm_model="gpt-4o")
result = md.convert("presentation.pptx") # Images described with LLM
See references/advanced_integrations.md for integration details.
Process multiple files or entire ZIP archives at once.
ZIP file processing:
from markitdown import MarkItDown
md = MarkItDown()
result = md.convert("archive.zip")
print(result.text_content) # All files converted and concatenated
Batch script: Use the provided batch processing script for directory conversion:
python scripts/batch_convert.py /path/to/documents /path/to/output
See scripts/batch_convert.py for implementation details.
Full installation (all features):
uv pip install 'markitdown[all]'
Modular installation (specific features):
uv pip install 'markitdown[pdf]' # PDF support
uv pip install 'markitdown[docx]' # Word support
uv pip install 'markitdown[pptx]' # PowerPoint support
uv pip install 'markitdown[xlsx]' # Excel support
uv pip install 'markitdown[audio]' # Audio transcription
uv pip install 'markitdown[youtube]' # YouTube transcripts
Requirements:
MarkItDown produces clean, token-efficient Markdown optimized for LLM consumption:
Preparing documents for RAG:
from markitdown import MarkItDown
md = MarkItDown()
# Convert knowledge base documents
docs = ["manual.pdf", "guide.docx", "faq.html"]
markdown_content = []
for doc in docs:
result = md.convert(doc)
markdown_content.append(result.text_content)
# Now ready for embedding and indexing
Document analysis pipeline:
# Convert all PDFs in directory
for file in documents/*.pdf; do
markitdown "$file" -o "markdown/$(basename "$file" .pdf).md"
done
MarkItDown supports extensible plugins for custom conversion logic. Plugins are disabled by default for security:
from markitdown import MarkItDown
# Enable plugins if needed
md = MarkItDown(enable_plugins=True)
This skill includes comprehensive reference documentation for each capability:
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Testing patterns for PHPUnit and Playwright E2E tests. Use when writing tests, debugging test failures, setting up test coverage, or implementing test patterns for ActivityPub features.
中文简介正在准备中。当前显示原文说明。
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.
中文简介正在准备中。当前显示原文说明。
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
中文简介正在准备中。当前显示原文说明。
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
中文简介正在准备中。当前显示原文说明。
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
中文简介正在准备中。当前显示原文说明。