Pptx logo

Pptx

Organization
YunjueTech
pptx

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for creating new presentations, modifying content, working with layouts, adding speaker notes, or any presentation tasks.

Overview

PublisherYunjueTech
RepositoryYunjue-Agent
Skill namepptx
Stars
535
Forks
66
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by YunjueTech on GitHub. Read the source before you install it.

Installation

Install the Pptx AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/YunjueTech/Yunjue-Agent/tree/main/example/cli/skills/pptx
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/YunjueTech/Yunjue-Agent.git /tmp/Yunjue-Agent
mkdir -p .claude/skills
cp -r /tmp/Yunjue-Agent/example/cli/skills/pptx .claude/skills/pptx
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pptx in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pptx on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pptx is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PowerPoint Processing

Creating Presentations (Python)

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

prs = Presentation()

# Add title slide
title_slide_layout = prs.slide_layouts[0]
slide = prs.slides.add_slide(title_slide_layout)
title = slide.shapes.title
subtitle = slide.placeholders[1]
title.text = "Hello, World!"
subtitle.text = "python-pptx demo"

# Add content slide
bullet_slide_layout = prs.slide_layouts[1]
slide = prs.slides.add_slide(bullet_slide_layout)
shapes = slide.shapes
title_shape = shapes.title
body_shape = shapes.placeholders[1]
title_shape.text = "Key Points"
tf = body_shape.text_frame
tf.text = "First bullet point"
p = tf.add_paragraph()
p.text = "Second bullet point"
p.level = 1

prs.save('presentation.pptx')

Adding Images

python
from pptx.util import Inches

blank_layout = prs.slide_layouts[6]
slide = prs.slides.add_slide(blank_layout)

left = Inches(1)
top = Inches(1)
width = Inches(5)
slide.shapes.add_picture('image.png', left, top, width=width)

Adding Tables

python
rows, cols = 3, 4
left = Inches(1)
top = Inches(2)
width = Inches(6)
height = Inches(1.5)

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

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

# Add content
table.cell(0, 0).text = "Header 1"
table.cell(1, 0).text = "Data 1"

Adding Charts

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

chart_data = CategoryChartData()
chart_data.categories = ['East', 'West', 'Midwest']
chart_data.add_series('Sales', (19.2, 21.4, 16.7))

x, y, cx, cy = Inches(2), Inches(2), Inches(6), Inches(4.5)
slide.shapes.add_chart(
    XL_CHART_TYPE.COLUMN_CLUSTERED, x, y, cx, cy, chart_data
)

Editing Existing Presentations

python
prs = Presentation('existing.pptx')

# Access slides
for slide in prs.slides:
    for shape in slide.shapes:
        if shape.has_text_frame:
            print(shape.text_frame.text)

# Modify text
slide = prs.slides[0]
slide.shapes.title.text = "New Title"

prs.save('modified.pptx')

Best Practices

  • Use slide layouts for consistency
  • Keep text minimal, use visuals
  • Use Inches() or Pt() for sizing
  • Save frequently during creation

Design & Aesthetics (Practical Rules)

Use these guidelines when generating or editing slides so the deck looks intentional, modern, and consistent.

Layout & Grid

  • Prefer a simple grid (e.g., 12-column feel) and align everything to consistent left edges.
  • Keep a single dominant focal point per slide (one headline + one visual or one chart).
  • Use generous margins/whitespace. As a rule of thumb, keep key content inside ~10% padding from slide edges.
  • Keep consistent spacing between elements (e.g., 8/16/24/32 px style steps). Avoid “almost equal” gaps.

Typography & Hierarchy

  • Use 1 font family (or 2 at most: one for headings, one for body). Avoid mixing many fonts.
  • Establish clear hierarchy:
    • Title: ~36–44 pt
    • Section header: ~28–34 pt
    • Body: ~18–24 pt
    • Caption/footnote: ~12–14 pt
  • Keep line length comfortable; avoid long paragraphs. Prefer bullets with strong nouns/verbs.
  • Use bold for emphasis, avoid underlines; italics only sparingly.

Color System

  • Use a restrained palette:
    • 1 primary accent color
    • 1 neutral dark (text)
    • 1 neutral light (background)
    • Optional 1 secondary accent
  • Maintain contrast: dark text on light background (or vice versa). Avoid low-contrast gray-on-gray.
  • Use color to encode meaning consistently (e.g., success=green, risk=red) and keep it consistent across slides.

Visuals (Icons / Images / Shapes)

  • Prefer high-quality visuals with consistent style (all flat icons, or all line icons—not mixed).
  • Avoid stretching images; preserve aspect ratio and crop intentionally.
  • Use subtle shape styling: thin strokes, soft shadows (if any), consistent corner radius.
  • Avoid decorative clutter: every icon/shape should clarify structure or meaning.

Images / Illustration Direction

  • Prefer one visual style per deck: photo-real, 3D renders, flat illustration, or line illustration. Don’t mix styles.
  • Resolution: use sufficiently large images (avoid blurry screenshots). If an image will be full-width, it should be at least ~1920px wide.
  • Cropping: crop for composition (rule of thirds, clear subject). Avoid awkward cut-offs (hands/heads) unless intentional.
  • Backgrounds: prefer clean backgrounds; remove busy backgrounds when they distract. If needed, place images on a solid/blurred panel.
  • Color & tone: keep color temperature and contrast consistent across slides; apply the same tint/duotone treatment if used.
  • Text on images: ensure readability with overlay scrims/gradient, and keep contrast high. Avoid putting text over noisy areas.
  • Icon usage: keep icon stroke weight and corner style consistent; avoid mixing filled and outline icons in the same row.
  • Captions & sources: if the deck is external-facing, add a small caption/source line for non-original images.
  • Licensing: use properly licensed assets; avoid random web images for public decks unless attribution/license is clear.

Charts & Tables

  • Remove chart junk: minimize gridlines, borders, and unnecessary labels.
  • Use one highlight color to direct attention; keep other series neutral.
  • Prefer direct labels over legends when possible.
  • Keep tables minimal: light row separators, consistent number formats, right-align numbers.

Consistency Checklist (Quick)

  • Same title position across slides
  • Same font sizes for same roles (title/body/caption)
  • Same color usage for same semantics
  • Same alignment rules (left edges, baseline alignment)
  • No overlapping elements; equal spacing; no “almost aligned” objects

Frequently asked questions

What does the Pptx AI skill do?

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for creating new presentations, modifying content, working with layouts, adding speaker notes, or any presentation tasks.

Why use Pptx on TypingMind?

Because you install it once and use it with any model. Pptx is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pptx in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/YunjueTech/Yunjue-Agent/tree/main/example/cli/skills/pptx. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pptx?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pptx?

As many as you like. As long as a model supports skills, you can use Pptx with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pptx AI skill free?

Yes. It is published on GitHub by YunjueTech under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇