Pptx generator

Skill epiphany-dynamics/claude-skills-portfolio/pptx-generator

Production Claude Code skills/plugins built for real business workflows. Demonstrates mastery of Anthropic's Agent Skills framework.

Install

npx -y skills add epiphany-dynamics/claude-skills-portfolio --skill pptx-generator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate brand-compliant PowerPoint presentations from raw text or markdown input. Enforces corporate fonts, colors, and layouts defined in a JSON brand config. Uses python-pptx to produce .pptx files. Supports custom templates. Use when asked to create a presentation, slide deck, or .pptx file from text content.

SKILL.md

3.3 KB, as published. Nobody here has run it

PPTX Generator — Branded Presentation Skill

Generate .pptx presentations that enforce corporate brand standards from raw text input.

How it works

Brand config (assets/sample_brand_config.json) defines fonts, colors, and layout mappings
Markdown input uses # for title slides and ## for content slides, with - for bullets
The script (scripts/generate_pptx.py) parses the input, applies brand rules, and outputs a .pptx

Quick start

python scripts/generate_pptx.py \
  --config assets/sample_brand_config.json \
  --input assets/sample_content.md \
  --output presentation.pptx

To use a client's existing .pptx template as the base (preserves their master slides):

python scripts/generate_pptx.py \
  --config brand_config.json \
  --input content.md \
  --output presentation.pptx \
  --template client_template.pptx

Workflow for new clients

Step 1: Analyze the template

When a client provides their .pptx template, extract the brand system:

from pptx import Presentation
from pptx.util import Pt

prs = Presentation("client_template.pptx")

# Extract master slide layouts
for i, layout in enumerate(prs.slide_layouts):
    print(f"Layout {i}: {layout.name}")
    for ph in layout.placeholders:
        print(f"  Placeholder {ph.placeholder_format.idx}: {ph.name} ({ph.width}, {ph.height})")

# Extract theme colors and fonts from the first slide
slide = prs.slides[0] if prs.slides else None
if slide:
    for shape in slide.shapes:
        if shape.has_text_frame:
            for para in shape.text_frame.paragraphs:
                for run in para.runs:
                    print(f"Font: {run.font.name}, Size: {run.font.size}, Bold: {run.font.bold}")

Step 2: Build the brand config

Create a JSON config that maps the extracted values:

{
  "company": "Client Name",
  "fonts": {
    "heading": { "name": "Their Font", "size": 36, "bold": true, "color": "#HEX" },
    "body": { "name": "Their Font", "size": 18, "bold": false, "color": "#HEX" }
  },
  "colors": {
    "primary_bg": "#HEX",
    "accent": "#HEX"
  }
}

Step 3: Generate presentations

Once the config exists, any text input produces brand-compliant slides via the slash command.

Input format

# Presentation Title
Optional subtitle text

## Slide title
- Bullet point one
- Bullet point two

## Another slide
Body paragraph text instead of bullets.

# creates a title slide (layout 0)
## creates a content slide (layout 1)
- or * creates bullet points
Plain text after ## becomes body content
First line after # becomes the subtitle

Brand config reference

See references/brand-config-spec.md for the full configuration schema.

Extending

The script is designed to be extended per client:

Add new layout types (two-column, image+text, data table)
Add chart generation via python-pptx chart API
Add image insertion with auto-sizing
Add speaker notes from content annotations

Gives 0 of the 12 instructions most pdf office docs skills give

Counted across 635 of the 690 authors here whose files we hold, read 2026-08-06

extract text using pdfplumberin 92 of 635, across 25 files
create PDFs using reportlabin 83 of 635, across 16 files
read FORMS.md to fill out PDF formsin 80 of 635, across 13 files
OCR scanned PDFs using pytesseractin 77 of 635, across 10 files
merge or split PDFs using qpdfin 70 of 635, across 3 files
use Excel formulas instead of hardcoded calculated valuesin 68 of 635, across 12 files
unpack edit xml and repack existing documentsin 63 of 635, across 8 files
document sources for hardcoded valuesin 61 of 635, across 9 files
write minimal python code without unnecessary commentsin 59 of 635, across 7 files
run the recalculation script after adding or modifying formulasin 58 of 635, across 6 files
fix all identified formula errors and recalculatein 58 of 635, across 6 files
format years as text stringsin 57 of 635, across 5 files

Said here and by no other author read

Enforce corporate brand standards
Parse markdown input into slides
Apply fonts from brand config
Apply colors from brand config
Use a provided template if supplied
Extract brand system from templates

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.