Claude Skill

pptx

Extract text from Microsoft PowerPoint presentations

LLM Mart · 0 points · 20 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download axoviq-ai-synthadoc-synthadoc_skills_pptx-8dee0ee.zip · 1 KB

axoviq-ai/synthadoc 1226 123 forks AGPL-3.0 Updated 5d ago

Part of axoviq-ai/synthadoc — 10 skills

Install

skills CLI npx skills add https://github.com/axoviq-ai/synthadoc/tree/main/synthadoc/skills/pptx

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install axoviq-ai-synthadoc@llmmart

Git git clone https://github.com/axoviq-ai/synthadoc.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole axoviq-ai/synthadoc collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

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

Files (synthadoc)

scripts

main.py 1.9 KB

# SPDX-License-Identifier: AGPL-3.0-or-later
# Copyright (C) 2026 Paul Chen / axoviq.com
from pptx import Presentation
from synthadoc.skills.base import BaseSkill, ExtractedContent, SkillMeta


class PptxSkill(BaseSkill):
    meta = SkillMeta(name="pptx", description="Extract text from PowerPoint presentations",
                     extensions=[".pptx"])

    async def extract(self, source: str) -> ExtractedContent:
        try:
            prs = Presentation(source)
        except Exception as exc:
            raise ValueError(
                f"Cannot read '{source}' as a PowerPoint file: {exc}. "
                "Ensure the file is a valid .pptx (Office Open XML) document."
            ) from exc
        sections: list[str] = []

        for i, slide in enumerate(prs.slides, start=1):
            lines: list[str] = []
            title = ""
            for shape in slide.shapes:
                if not shape.has_text_frame:
                    continue
                text = shape.text_frame.text.strip()
                if not text:
                    continue
                if shape.shape_type == 13:  # picture — skip
                    continue
                if not title and shape.name.lower().startswith("title"):
                    title = text
                else:
                    lines.append(text)

            notes = ""
            if slide.has_notes_slide:
                notes_text = slide.notes_slide.notes_text_frame.text.strip()
                if notes_text:
                    notes = f"\n_Notes: {notes_text}_"

            heading = f"## Slide {i}" + (f": {title}" if title else "")
            body = "\n".join(lines)
            sections.append(f"{heading}\n{body}{notes}" if body or notes else heading)

        text = "\n\n".join(sections)
        return ExtractedContent(
            text=text,
            source_path=source,
            metadata={"slides": len(prs.slides)},
        )

__init__.py 0 B

requirements.txt 12 B
```
python-pptx
```

SKILL.md 990 B

---
name: pptx
version: "1.0"
description: Extract text from Microsoft PowerPoint presentations
entry:
  script: scripts/main.py
  class: PptxSkill
triggers:
  extensions:
    - ".pptx"
  intents:
    - "powerpoint"
    - "presentation"
    - "pptx"
requires:
  - python-pptx
author: axoviq.com
license: AGPL-3.0-or-later
---

# 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

```bash
pip install python-pptx
```

## Standalone usage

```python
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`