训练与评测机器学习与科研 AIK-Dense-AI/claude-scientific-skills训练与评测
MA

MarkItDown

维护者 K-Dense Inc. · 最近更新 2026年4月1日

MarkItDown是一个Python tool developed by Microsoft ,用于 converting various file formats to Markdown。 It's particularly useful ,用于 converting documents into LLM-friendly text format,as Markdown is token-efficient 、 well-understood by modern language models。

Claude CodeOpenClawNanoClaw训练编排评测比较markitdowndocument-processingworkflowdocument processing & conversion

原始来源

K-Dense-AI/claude-scientific-skills

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/markitdown

维护者
K-Dense Inc.
许可
MIT license
最近更新
2026年4月1日

技能摘要

来自 SKILL.md 的关键信息

2 min

核心说明

  • Convert documents to clean,structured Markdown。
  • Token-efficient format ,用于 LLM processing。
  • 支持 15+ file formats。
  • Optional AI-enhanced image descriptions。
  • OCR ,用于 images 、 scanned documents。

原始文档

SKILL.md 摘录

Visual Enhancement with Scientific Schematics

When creating documents with this skill, always consider adding scientific diagrams and schematics to enhance visual communication.

If your document does not already contain schematics or diagrams:

  • Use the scientific-schematics skill to generate AI-powered publication-quality diagrams
  • Simply describe your desired diagram in natural language
  • Nano Banana Pro will automatically generate, review, and refine the schematic

For new documents: Scientific schematics should be generated by default to visually represent key concepts, workflows, architectures, or relationships described in the text.

How to generate schematics:

The AI will automatically:

  • Create publication-quality images with proper formatting
  • Review and refine through multiple iterations
  • Ensure accessibility (colorblind-friendly, high contrast)
  • Save outputs in the figures/ directory

When to add schematics:

  • Document conversion workflow diagrams
  • File format architecture illustrations
  • OCR processing pipeline diagrams
  • Integration workflow visualizations
  • System architecture diagrams
  • Data flow diagrams
  • Any complex concept that benefits from visualization

For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.


Supported Formats

FormatDescriptionNotes
PDFPortable Document FormatFull text extraction
DOCXMicrosoft WordTables, formatting preserved
PPTXPowerPointSlides with notes
XLSXExcel spreadsheetsTables and data
ImagesJPEG, PNG, GIF, WebPEXIF metadata + OCR
AudioWAV, MP3Metadata + transcription
HTMLWeb pagesClean conversion
CSVComma-separated valuesTable format
JSONJSON dataStructured representation
XMLXML documentsStructured format
ZIPArchive filesIterates contents
EPUBE-booksFull text extraction
YouTubeVideo URLsFetch transcriptions

Or from source

git clone https://github.com/microsoft/markitdown.git cd markitdown pip install -e 'packages/markitdown[all]'

适用场景

  • Use MarkItDown in 科研工作流 aligned ,支持 this subject area。
  • Follow upstream documentation ,用于 full working procedure。
  • Use markitdown in 科研工作流 aligned ,支持 this subject area。

不适用场景

  • Do not rely on this catalog entry alone ,用于 installation 或 maintenance details。

相关技能

相关技能

返回目录
BI
训练与评测机器学习与科研 AI

bio-immunoinformatics-tcr-epitope-binding

bio-immunoinformatics-tcr-epitope-binding:预测 TCR-epitope specificity ,使用 ERGO-II 、 深度学习 models ,用于 T-cell receptor antig…

OpenClawNanoClaw训练编排
FreedomIntelligence/OpenClaw-Medical-Skills查看
GE
训练与评测机器学习与科研 AI

Get Available Resources

Get Available Resources:检测 available computational resources 、 generate strategic recommendations ,用于 scientific computi…

Claude Code训练编排
K-Dense-AI/claude-scientific-skills查看
HY
训练与评测机器学习与科研 AI

Hypothesis Generation

Hypothesis Generation:Hypothesis generation是一个systematic process ,用于 developing testable explanations。 Formulate evidenc…

Claude CodeOpenClaw训练编排
K-Dense-AI/claude-scientific-skills查看
PY
训练与评测机器学习与科研 AI

PyMOO

PyMOO:Pymoo是一个comprehensive Python 框架 ,用于 optimi。

Claude CodeOpenClaw训练编排
K-Dense-AI/claude-scientific-skills查看