Menu
Extract text and tables from PowerPoint (.pptx) files. Use when a user uploads a PPT or PPTX document that needs to be processed.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
当用户请求生成、创建、制作 PPT、演示文稿、课件时使用此技能。这是教育场景中最常用的技能，适合老师备课、课程汇报、学术演讲等需求。
Extract text and tables from Word (.docx) files. Use when a user uploads a Word document that needs to be processed.
Extract text and tables from Markdown (.md) files. Use when a user uploads a Markdown document that needs to be processed.
Extract text and tables from PDF files. Use when a user uploads a PDF document that needs to be processed.
Summarize and structure raw document text (PDF/Word/Markdown/PPT) into a format optimized for PPT generation. Use when the user uploads a document and wants to generate a presentation from it.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
| name | pptx |
| description | Extract text and tables from PowerPoint (.pptx) files. Use when a user uploads a PPT or PPTX document that needs to be processed. |
Extract readable text and structured tables from PPTX files so the content can be summarized and turned into a new PPT.
.pptx file.ppt file that has already been converted or can be converted to .pptxpython-pptx Firstfrom pptx import Presentation
prs = Presentation("presentation.pptx")
text_parts = []
tables = []
for slide in prs.slides:
for shape in slide.shapes:
if shape.has_text_frame:
for paragraph in shape.text_frame.paragraphs:
line = paragraph.text.strip()
if line:
text_parts.append(line)
if shape.has_table:
table_data = []
for row in shape.table.rows:
cells = [cell.text.strip() for cell in row.cells]
table_data.append(cells)
if table_data:
tables.append(table_data)
markitdownpython -m markitdown presentation.pptx
Use this when python-pptx is unavailable or extraction quality is better with markdown output.
.pptIf the original file is .ppt, convert it first:
soffice --headless --convert-to pptx file.ppt
Then process the generated .pptx.
| Problem | Solution |
|---|---|
Legacy .ppt file | Convert to .pptx first |
python-pptx missing | Use markitdown fallback |
| Empty extraction | Try markdown conversion or inspect whether slides are image-heavy |
| Tables not found | Check shape.has_table; some "tables" are actually pasted images |
For the upload-to-PPT workflow:
document-summarizergenerate_ppt(content=...)General follow-up rule for an existing deck:
generate_ppt when the requested final artifact is a PPT and the user explicitly wants a new deck or slide revisions/regeneration.Return (raw_text: str, tables: list[list[list[str]]], slide_count: int):
raw_text: text extracted from all slidestables: tables extracted from slide shapesslide_count: total slide count