This does exactly what you'd expect: pulls all the text out of PowerPoint files so Claude can work with presentation content. It grabs text from each slide and includes speaker notes if they're there, which is actually handy since that's where a lot of context lives. Built on python-pptx, so it's solid. Triggers automatically when you reference a .pptx file or mention PowerPoint in your prompt. Not much complexity here, just a straightforward extraction tool. If you need to analyze, summarize, or repurpose slide decks without manually copying text, this gets the job done.
- GitHub stars
- 452
- last updated
- Jun 11, 2026
Install
$ npx -y skills add axoviq-ai/synthadoc --skill pptx --agent claude-codeInstalls into .claude/skills of the current project.
Files
PPTX Skill
Extracts text from .pptx files using python-pptx. Each slide is rendered
as a titled section; speaker notes are appended when present.
Setup
pip install python-pptx
Standalone usage
import asyncio
from synthadoc.skills.pptx.scripts.main import PptxSkill
skill = PptxSkill()
async def main():
result = await skill.extract("/path/to/slides.pptx")
print(result.text) # slide titles + body text + speaker notes
print(result.metadata) # {"slides": N}
asyncio.run(main())
When this skill is used
- Source path ends with
.pptx - User intent contains:
powerpoint,presentation,pptx
Sponsors
Details
- Repository
- github.com/axoviq-ai/synthadoc
- Category
- Office & Documents
- License
- AGPL-3.0
- First seen
- Jun 11, 2026
