Menu
Extract text and tables from PDF files. Use when a user uploads a PDF 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
| name | |
| description | Extract text and tables from PDF files. Use when a user uploads a PDF document that needs to be processed. |
Extract readable text and structured tables from PDF files. This skill is designed to feed extracted content into downstream processing (e.g., document summarization for PPT generation).
.pdf fileimport pdfplumber
text_parts = []
tables = []
with pdfplumber.open("document.pdf") as pdf:
for page in pdf.pages:
# Extract text (preserves layout better than pypdf)
t = page.extract_text()
if t:
text_parts.append(t.strip())
# Extract tables as 2D arrays
page_tables = page.extract_tables()
for pt in page_tables:
if pt and len(pt) >= 2:
tables.append(pt)
Why pdfplumber first:
from pypdf import PdfReader
reader = PdfReader("document.pdf")
text_parts = []
for page in reader.pages:
t = page.extract_text()
if t:
text_parts.append(t.strip())
Use pypdf when:
# Requires: pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path
images = convert_from_path('scanned.pdf')
text = ""
for i, image in enumerate(images):
text += f"Page {i+1}:\n"
text += pytesseract.image_to_string(image)
text += "\n\n"
When to use OCR:
pdftotext or pdfplumber returns empty text# Fast plain text extraction
pdftotext input.pdf output.txt
# Preserve layout
pdftotext -layout input.pdf output.txt
# Specific page range
pdftotext -f 1 -l 5 input.pdf output.txt
| Problem | Solution |
|---|---|
| Empty text (scanned PDF) | Use OCR (Step 3) |
| Garbled text | Check if PDF is encrypted or uses non-standard encoding |
| Tables not extracting | Try page.extract_tables(settings={"vertical_strategy": "lines"}) |
| Memory issues on large PDFs | Process page-by-page in a loop |
| Images instead of text | OCR or skip if images are decorative |
For pptagent pipeline:
"\n\n".join(text_parts)len(pdf.pages)Return (raw_text: str, tables: list[list[list[str]]], page_count: int):
raw_text: all pages joined with double newlinestables: list of tables, each table is list[list[str]] (rows → cells)page_count: total number of pagesExtract text and tables from PowerPoint (.pptx) files. Use when a user uploads a PPT or PPTX document that needs to be processed.
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.
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.