Convert Office documents (Word, Excel, PowerPoint, PDF) to Markdown using Microsoft's markitdown library.
SkillScore87Maintained
Automatic
◆Doc Ops pack
Last verified 8/6/2026
What it changes
Passed 20 of 23 test cases with the skill, and 19 of 23 without it.
Without skill83%
With skill87%
Checks it passed that the model alone missed
Recommends placing converted Markdown files under Git version control.
1 fixed19 passed either way3 still failing0 broke
Pass-rate lift
+4 pp
Tokens
+88%
Agent turns
0%
Response time
-35%
Model gemini-3.6-flashMeasured 8/6/2026v1 · latest is v220 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
What tool is recommended for tracking changes and managing version history of converted Markdown documents over time?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends placing converted Markdown files under Git version control.
Missed
Passed
case-19 · gemini-3.6-flash · 8/6/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md212 linessingle file
Office → Markdown (markitdown)
A guide to converting Office files to Markdown with Microsoft's open-source markitdown library.
1. Installation
pip install markitdown # Basic
pip install markitdown[all] # Includes image OCR and audio transcription
2. Supported Formats
Format
Extension
Notes
Word
.docx
Text, tables, basic formatting
Excel
.xlsx
Sheets → Markdown tables
PowerPoint
.pptx
Slides → Sections
PDF
.pdf
Text extraction
HTML
.html
Clean Markdown
Image
.jpg, .png
OCR with an LLM (optional)
ZIP
.zip
Processes contained files
3. Basic Usage
from markitdown import MarkItDown
from pathlib import Path
md = MarkItDown()
# Convert a single file
result = md.convert("report.docx")
print(result.text_content)