Ppt translator

Skill tristan-mcinnis/PPT-Translator-Formatting-Intact-with-LLMs/.claude/skills/ppt-translator

A powerful PowerPoint translation tool that preserves all formatting while translating content using the Deepseek API. This tool maintains fonts, colors, layouts, and other styling elements while providing accurate translations between languages.

Install

npx -y skills add tristan-mcinnis/PPT-Translator-Formatting-Intact-with-LLMs --skill ppt-translator

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

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

Translate PowerPoint presentations while preserving formatting (fonts, colors, alignment, tables). Supports multiple LLM providers (OpenAI, Anthropic, DeepSeek, Grok, Gemini). Use when translating .pptx files between languages, especially for CJK to/from English translations where text expansion/contraction is a concern.

The file declares its own license as MIT - see LICENSE.txt. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

5.2 KB, as published. Nobody here has run it

PowerPoint Translation Skill

Translate PowerPoint presentations while preserving all formatting including fonts, colors, spacing, tables, and alignment.

When to Use This Skill

Translating .pptx files between languages
Batch translating multiple presentations in a directory
Preserving slide formatting during translation (especially CJK ↔ English)
When you need to inspect intermediate XML for debugging

Setup

Before first use, set up the environment:

# Navigate to the scripts directory
cd .claude/skills/ppt-translator/scripts

# Create virtual environment and install dependencies
python3 -m venv .venv
source .venv/bin/activate  # macOS/Linux
pip install -r requirements.txt

# Configure API keys
cp example.env .env
# Edit .env with your provider API key(s)

Basic Usage

cd .claude/skills/ppt-translator/scripts
source .venv/bin/activate

python main.py /path/to/presentation.pptx \
  --provider openai \
  --source-lang zh \
  --target-lang en

Provider Configuration

Provider	Environment Variable	Default Model
openai	`OPENAI_API_KEY`	`gpt-5.2-2025-12-11`
anthropic	`ANTHROPIC_API_KEY`	`claude-sonnet-4-5-20250514`
deepseek	`DEEPSEEK_API_KEY`	`deepseek-chat`
grok	`GROK_API_KEY`	`grok-4.1-fast`
gemini	`GEMINI_API_KEY`	`gemini-3-flash-preview`

CLI Reference

Option	Description	Default
`--provider`	LLM provider: `openai`, `anthropic`, `deepseek`, `grok`, `gemini`	`openai`
`--model`	Override default model for provider	Provider default
`--source-lang`	Source language ISO code	`zh`
`--target-lang`	Target language ISO code	`en`
`--max-chunk-size`	Characters per API request	`1000`
`--max-workers`	Threads for slide extraction	`4`
`--keep-intermediate`	Retain XML files for debugging	`false`

Output Files

For each input presentation.pptx, the tool generates:

presentation_original.xml - Extracted source content (deleted unless --keep-intermediate)
presentation_translated.xml - Translated content (deleted unless --keep-intermediate)
presentation_translated.pptx - Final translated presentation with formatting intact

Common Workflows

Translate a Single File (Chinese → English)

python main.py deck.pptx --provider anthropic --source-lang zh --target-lang en

Batch Translate a Directory

python main.py /path/to/presentations/ --provider openai --source-lang ja --target-lang en

Debug Translation Issues

python main.py deck.pptx --keep-intermediate --provider deepseek
# Inspect the generated XML files to see extracted/translated content

Use a Specific Model

python main.py deck.pptx --provider openai --model gpt-5-mini

Translate with Gemini (Cost-Effective)

python main.py deck.pptx --provider gemini --source-lang ko --target-lang en

Supported Languages

Use standard ISO 639-1 language codes:

Code	Language
`zh`	Chinese (Simplified)
`en`	English
`ja`	Japanese
`ko`	Korean
`es`	Spanish
`fr`	French
`de`	German
`pt`	Portuguese
`ru`	Russian
`ar`	Arabic

Design Notes

Font Scaling

The tool automatically scales fonts down (70% for text, 80% for tables) to accommodate text expansion when translating from compact languages (Chinese, Japanese, Korean) to English. This prevents text overflow in fixed-size text boxes.

Caching

Repeated strings within a presentation are cached to avoid redundant API calls. This is especially useful for presentations with recurring headers, footers, or terminology.

Chunking

Long text blocks are intelligently split at sentence boundaries to stay within API limits while preserving translation quality.

Troubleshooting

"API key not found"

Ensure your .env file in the scripts directory contains the correct environment variable:

OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...

Formatting looks wrong

Use --keep-intermediate to inspect the XML files
Check if the source presentation has unusual formatting
Try a different provider

Translation incomplete

Check for API rate limits with your provider
Try reducing --max-chunk-size for very long text blocks
Ensure your API key has sufficient quota

Script Reference

The scripts/ directory contains:

main.py - Entry point
requirements.txt - Python dependencies
example.env - Environment variable template
ppt_translator/ - Core translation module
- cli.py - CLI argument parsing
- pipeline.py - PPT extraction and regeneration
- translation.py - Chunking and caching
- providers/ - LLM provider implementations

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

configure provider api keys in env file
execute main.py to translate presentations
specify provider source and target languages
batch translate a directory of presentations
use keep-intermediate to debug translation issues
inspect generated xml files for debugging

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