# Ppt Analysis

PPT (.pptx/.ppt) 全量解析。覆盖：所有 slide 文本/表格/图表提取、嵌入图片 caption、纯图片 slide 渲染识别、数据标签提取。

- Repository: https://github.com/OpenSenseNova/SenseNova-Skills (6002 stars)
- Category: Documents
- License: MIT
- Last updated: 2026-10-29
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add OpenSenseNova/SenseNova-Skills --skill ppt-analysis -g -a claude-code -y`
Codex: `npx skills add OpenSenseNova/SenseNova-Skills --skill ppt-analysis -g -a codex -y`
Cursor: `npx skills add OpenSenseNova/SenseNova-Skills --skill ppt-analysis -g -a cursor -y`
Gemini CLI: `npx skills add OpenSenseNova/SenseNova-Skills --skill ppt-analysis -g -a gemini-cli -y`

## Description

PPT (.pptx/.ppt) 全量解析。覆盖：所有 slide 文本/表格/图表提取、嵌入图片 caption、纯图片 slide 渲染识别、数据标签提取。

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# PPT Analysis, .pptx / .ppt

## Environment

```python
from pptx import Presentation
from pptx.util import Inches
import os, subprocess, json

# python-pptx is available
# For .ppt (old binary format): convert via libreoffice
def load_pptx(path):
    if path.lower().endswith('.ppt'):
        import subprocess
        out_dir = os.path.dirname(path)
        subprocess.run(
            ['libreoffice', '--headless', '--convert-to', 'pptx', '--outdir', out_dir, path],
            check=True, capture_output=True
        )
        path = path.rsplit('.', 1)[0] + '.pptx'
    return Presentation(path), path
```

---

## Core Method 1: Full Text Extraction (ALL slides)

```python
def extract_all_slides_text(pptx_path):
    """
    Extract text from every slide: text frames, tables, chart titles.
    For slides with no extractable text, flag them for image captioning.
    """
    prs, _ = load_pptx(pptx_path)
    slides_data = []

    for slide_num, slide in enumerate(prs.slides, start=1):
        slide_texts = []
        has_text = False

        for shape in slide.shapes:
            # Text frame (most common)
            if shape.has_text_frame:
                for para in shape.text_frame.paragraphs:
                    text = para.text.strip()
                    if text:
                        slide_texts.append(text)
                        has_text = True

            # Table
            if shape.has_table:
                tbl = shape.table
                for row in tbl.rows:
                    row_text = '\t'.join(cell.text.strip() for cell in row.cells)
                    if row_text.strip():
                        slide_texts.append(row_text)
                        has_text = True

The rest: https://github.com/OpenSenseNova/SenseNova-Skills/blob/HEAD/skills/sn-da-non-spreadsheet-analysis/capability/ppt-analysis/SKILL.md