mcpbeat Sign in

PPTX Manipulation Agent Skill

>

3k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
353
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/claude-office-skills/skills --skill pptx-manipulation

The instruction itself

29 sections, as written by the author

PPTX Manipulation Skill

Overview

This skill enables programmatic creation, editing, and manipulation of Microsoft PowerPoint (.pptx) presentations using the python-pptx library. Create professional slides with text, shapes, images, charts, and tables without manual editing.

How to Use

  • Describe the presentation you want to create or modify
  • Provide content, data, or images to include
  • I'll generate python-pptx code and execute it

Example prompts:

  • "Create a 10-slide pitch deck from this outline"
  • "Add a chart to slide 3 with this data"
  • "Extract all text from this presentation"
  • "Generate slides from this markdown content"

Domain Knowledge

python-pptx Fundamentals

from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.enum.shapes import MSO_SHAPE
from pptx.enum.text import PP_ALIGN

# Create new presentation
prs = Presentation()

# Or open existing
prs = Presentation('existing.pptx')

Presentation Structure

Presentation
├── slide_layouts (predefined layouts)
├── slides (individual slides)
│   ├── shapes (text, images, charts)
│   │   ├── text_frame (paragraphs)
│   │   └── table (rows, cells)
│   └── placeholders (title, content)
└── slide_masters (templates)

Slide Layouts

# Common layout indices (may vary by template)
TITLE_SLIDE = 0
TITLE_CONTENT = 1
SECTION_HEADER = 2
TWO_CONTENT = 3
COMPARISON = 4
TITLE_ONLY = 5
BLANK = 6

# Add slide with layout
slide_layout = prs.slide_layouts[TITLE_CONTENT]
slide = prs.slides.add_slide(slide_layout)

Adding Content

Title Slide
slide_layout = prs.slide_layouts[0]  # Title slide
slide = prs.slides.add_slide(slide_layout)

title = slide.shapes.title
subtitle = slide.placeholders[1]

title.text = "Quarterly Report"
subtitle.text = "Q4 2024 Performance Review"
Text Content
# Using placeholder
body = slide.placeholders[1]
tf = body.text_frame
tf.text = "First bullet point"

# Add more paragraphs
p = tf.add_paragraph()
p.text = "Second bullet point"
p.level = 0

p = tf.add_paragraph()
p.text = "Sub-bullet"
p.level = 1
Text Box
from pptx.util import Inches, Pt

left = Inches(1)
top = Inches(2)
width = Inches(4)
height = Inches(1)

txBox = slide.shapes.add_textbox(left, top, width, height)
tf = txBox.text_frame

p = tf.paragraphs[0]
p.text = "Custom text box"
p.font.bold = True
p.font.size = Pt(18)
Shapes
from pptx.enum.shapes import MSO_SHAPE

# Rectangle
shape = slide.shapes.add_shape(
    MSO_SHAPE.RECTANGLE,
    Inches(1), Inches(2),  # left, top
    Inches(3), Inches(1.5) # width, height
)
shape.text = "Rectangle with text"

# Common shapes:
# MSO_SHAPE.RECTANGLE, ROUNDED_RECTANGLE
# MSO_SHAPE.OVAL, CHEVRON, ARROW_RIGHT
# MSO_SHAPE.CALLOUT_ROUNDED_RECTANGLE
Images
# Add image
slide.shapes.add_picture(
    'image.png',
    Inches(1), Inches(2),  # position
    width=Inches(4)        # auto height
)

# Or specify both dimensions
slide.shapes.add_picture(
    'logo.png',
    Inches(8), Inches(0.5),
    Inches(1.5), Inches(0.75)
)

Tables

# Create table
rows, cols = 4, 3
left = Inches(1)
top = Inches(2)
width = Inches(8)
height = Inches(2)

table = slide.shapes.add_table(rows, cols, left, top, width, height).table

# Set column widths
table.columns[0].width = Inches(2)
table.columns[1].width = Inches(3)
table.columns[2].width = Inches(3)

# Add headers
headers = ['Product', 'Q3 Sales', 'Q4 Sales']
for i, header in enumerate(headers):
    cell = table.cell(0, i)
    cell.text = header
    cell.text_frame.paragraphs[0].font.bold = True

# Add data
data = [
    ['Widget A', '$10,000', '$12,500'],
    ['Widget B', '$8,000', '$9,200'],
    ['Widget C', '$15,000', '$18,000'],
]
for row_idx, row_data in enumerate(data, 1):
    for col_idx, value in enumerate(row_data):
        table.cell(row_idx, col_idx).text = value

Charts

from pptx.chart.data import CategoryChartData
from pptx.enum.chart import XL_CHART_TYPE

# Chart data
chart_data = CategoryChartData()
chart_data.categories = ['Q1', 'Q2', 'Q3', 'Q4']
chart_data.add_series('Sales', (19.2, 21.4, 16.7, 23.8))
chart_data.add_series('Expenses', (12.1, 15.3, 14.2, 18.1))

# Add chart
x, y, cx, cy = Inches(1), Inches(2), Inches(8), Inches(4)
chart = slide.shapes.add_chart(
    XL_CHART_TYPE.COLUMN_CLUSTERED,
    x, y, cx, cy, chart_data
).chart

# Customize
chart.has_legend = True
chart.legend.include_in_layout = False

Formatting

Text Formatting
from pptx.dml.color import RGBColor

run = p.runs[0]
run.font.name = 'Arial'
run.font.size = Pt(24)
run.font.bold = True
run.font.italic = True
run.font.color.rgb = RGBColor(0x00, 0x66, 0xCC)
Shape Fill & Line
from pptx.dml.color import RGBColor

shape.fill.solid()
shape.fill.fore_color.rgb = RGBColor(0x00, 0x80, 0x00)

shape.line.color.rgb = RGBColor(0x00, 0x00, 0x00)
shape.line.width = Pt(2)
Paragraph Alignment
from pptx.enum.text import PP_ALIGN

p.alignment = PP_ALIGN.CENTER  # LEFT, RIGHT, JUSTIFY

Best Practices

  • Use Templates: Start with a .pptx template for consistent branding
  • Layout First: Plan slide structure before coding
  • Reuse Slide Masters: Maintain consistency across presentations
  • Optimize Images: Compress images before adding
  • Test Output: Always verify generated presentations

Common Patterns

Slide Deck Generator

def create_deck(title, slides_content):
    prs = Presentation()
    
    # Title slide
    slide = prs.slides.add_slide(prs.slide_layouts[0])
    slide.shapes.title.text = title
    
    # Content slides
    for slide_data in slides_content:
        slide = prs.slides.add_slide(prs.slide_layouts[1])
        slide.shapes.title.text = slide_data['title']
        
        body = slide.placeholders[1]
        tf = body.text_frame
        for i, point in enumerate(slide_data['points']):
            if i == 0:
                tf.text = point
            else:
                p = tf.add_paragraph()
                p.text = point
    
    return prs

Data-Driven Charts

def add_bar_chart(slide, title, categories, values):
    from pptx.chart.data import CategoryChartData
    from pptx.enum.chart import XL_CHART_TYPE
    
    chart_data = CategoryChartData()
    chart_data.categories = categories
    chart_data.add_series('Values', values)
    
    chart = slide.shapes.add_chart(
        XL_CHART_TYPE.BAR_CLUSTERED,
        Inches(1), Inches(2),
        Inches(8), Inches(4),
        chart_data
    ).chart
    
    chart.chart_title.text_frame.text = title
    return chart

Examples

Example 1: Create a Pitch Deck

from pptx import Presentation
from pptx.util import Inches, Pt

prs = Presentation()

# Slide 1: Title
slide = prs.slides.add_slide(prs.slide_layouts[0])
slide.shapes.title.text = "StartupX"
slide.placeholders[1].text = "Revolutionizing Document Processing"

# Slide 2: Problem
slide = prs.slides.add_slide(prs.slide_layouts[1])
slide.shapes.title.text = "The Problem"
body = slide.placeholders[1].text_frame
body.text = "Manual document processing costs businesses $1T annually"
p = body.add_paragraph()
p.text = "Average worker spends 20% of time on document tasks"
p.level = 1

# Slide 3: Solution
slide = prs.slides.add_slide(prs.slide_layouts[1])
slide.shapes.title.text = "Our Solution"
body = slide.placeholders[1].text_frame
body.text = "AI-powered document automation"
body.add_paragraph().text = "90% faster processing"
body.add_paragraph().text = "99.5% accuracy"
body.add_paragraph().text = "Works with existing tools"

# Slide 4: Market
slide = prs.slides.add_slide(prs.slide_layouts[5])  # Title only
slide.shapes.title.text = "Market Opportunity: $50B by 2028"

# Add chart
from pptx.chart.data import CategoryChartData
from pptx.enum.chart import XL_CHART_TYPE

data = CategoryChartData()
data.categories = ['2024', '2025', '2026', '2027', '2028']
data.add_series('Market Size ($B)', [30, 35, 40, 45, 50])

slide.shapes.add_chart(
    XL_CHART_TYPE.LINE,
    Inches(1), Inches(1.5),
    Inches(8), Inches(5),
    data
)

prs.save('pitch_deck.pptx')

Example 2: Report with Data Table

from pptx import Presentation
from pptx.util import Inches, Pt

prs = Presentation()

# Title slide
slide = prs.slides.add_slide(prs.slide_layouts[0])
slide.shapes.title.text = "Sales Performance Report"
slide.placeholders[1].text = "Q4 2024"

# Data slide
slide = prs.slides.add_slide(prs.slide_layouts[5])
slide.shapes.title.text = "Regional Performance"

# Create table
table = slide.shapes.add_table(5, 4, Inches(0.5), Inches(1.5), Inches(9), Inches(4)).table

# Headers
headers = ['Region', 'Revenue', 'Growth', 'Target']
for i, h in enumerate(headers):
    table.cell(0, i).text = h
    table.cell(0, i).text_frame.paragraphs[0].font.bold = True

# Data
data = [
    ['North America', '$5.2M', '+15%', 'Met'],
    ['Europe', '$3.8M', '+12%', 'Met'],
    ['Asia Pacific', '$2.9M', '+28%', 'Exceeded'],
    ['Latin America', '$1.1M', '+8%', 'Below'],
]
for row_idx, row_data in enumerate(data, 1):
    for col_idx, value in enumerate(row_data):
        table.cell(row_idx, col_idx).text = value

prs.save('sales_report.pptx')

Limitations

  • Cannot render complex animations
  • Limited SmartArt support
  • No video embedding via API
  • Master slide editing is complex
  • Chart types limited to standard Office charts

Installation

pip install python-pptx

Resources

Other skills for the same job

different authors, same section of the catalogue
DOCX
by anthropics
vendor ×16

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

7k tokens
PDF
by anthropics
vendor ×16

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

13k tokens scripts
PPTX
by JayZeeDesign
×15

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

308k tokens scripts
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
PDF
by anthropics
vendor ×10

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

15k tokens scripts
DOCX
by w95
×6

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

5k tokens
PPTX
by w95
×4

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.

2k tokens
Obsidian Markdown
by ZhanlinCui
×3

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

3k tokens

How to use it

Copy the folder

Take claude-office-skills/pptx-manipulation from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference pip. Without those the skill loads but fails at the first command.