11st of 20 in Agent frameworks and SDKs
ppt-master
Agent skill that turns documents into natively editable PowerPoint decks
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 62.1k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
2,855 on 25 Mar 202662,074 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
PPT Master is a workflow ("skill") that runs inside an agent-capable AI tool such as Claude Code, Cursor or Codex CLI. It reads source material like PDFs, DOCX and web pages, plans the argument, and exports a .pptx with native shapes, data-backed charts and tables, and slide masters via the template route. It can also fill existing decks, extract templates, and add transitions, animations and narration.
Who it is for: People who want editable PowerPoint decks generated from documents by an agent
Strengths
- Exports native PowerPoint objects (shapes, charts, tables), not flattened images
- Runs on your machine; only model API calls leave it
- Works with any agent-capable tool and model: Claude, GPT, Gemini, Kimi
- Also fills existing .pptx files and distills reusable templates
Weaknesses
- Output quality depends on the driving model; README recommends Kimi K3 or Claude with ~1M context
- Image-heavy decks need a separate AI image generation API such as gpt-image-2
- Needs an agent tool installed plus Python 3.10+; no standalone UI
- SmartArt is deliberately unsupported; one-shot decks still need manual polish
What it needs
- no GPU
- Needs Python 3.10+, An agent-capable AI tool (Claude Code, Cursor, Codex CLI, etc.), pandoc (only for legacy formats like .doc, .odt, .rtf)
- Models: Kimi K3, Claude, GPT, Gemini, gpt-image-2
Head to head
Also in Agent frameworks and SDKs
See all 20| Rank | Project | Score |
|---|---|---|
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 86 out of 100 |
| #5 | crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows | 80 out of 100 |
| #6 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 78 out of 100 |