Office extraction
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill office-extractionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Extracts text from DOCX and PPTX documents for content analysis.
SKILL.md
1.0 KB, as published. Nobody here has run it
Office Extraction Skill
This skill provides methods for extracting text from Microsoft Office documents (.docx, .pptx).
Methods
1. Using docx2txt or pandoc
If installed, these tools can convert Office docs to text.
# For DOCX
pandoc -t plain "document.docx" -o "output.txt"
2. Using Gemini CLI docx and pptx Skills
These specialized skills provide direct tools for document manipulation.
// For DOCX
await docx.read_file({ file_path: "paper.docx" });
// For PPTX
await pptx.read_presentation({ file_path: "slides.pptx" });
3. Manual Extraction (unzip)
DOCX and PPTX are ZIP archives. You can unzip them and read the XML.
unzip -p "document.docx" word/document.xml | sed -e 's/<[^>]*>//g'
Usage Pattern
Extract the main body text or titles to identify the document's subject matter.