PPT Master — AI-native PowerPoint generation
Turn documents or topics into truly native, editable PowerPoint decks with charts, animations, narration, and custom templates.
- Source repo
- hugohe3/ppt-master
- Stars
- ★ 64k
- Last updated
- today
- License
- MIT
- Primary language
- Python
- FA score
- 0/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformClaude CodeChatGPT · Codex (Partial support)
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- Finance professionals converting quarterly report PDFs into editable presentations
- Not a fit if
- Users unwilling to install Python or use an AI coding tool
- Those expecting a polished, ready-to-use deck in one pass
- Source review
- 0/100 · Major gaps 8 safety controls not found
What does this agent do, and when should you use it?
PPT Master is an AI-driven tool that converts PDFs, Word documents, or pasted text into native PowerPoint (.pptx) files. It produces slides with real PowerPoint behavior: native shapes, transitions, animations, data-backed charts and tables, and even audio narration from speaker notes. The tool runs as a skill inside any agent-capable AI tool like Claude Code, and processes data on your local machine for privacy. It supports custom templates and brand guides, and uses an SVG intermediate format to generate editable PPTX files, not flat images.
Reads source files like PDF, DOCX, HTML, EPUB, IPYNB (with Pandoc for legacy formats), or directly input text. Runs a workflow that includes content analysis, design spec confirmation, SVG authoring, and export to native PPTX via finalize_svg.py. Optionally integrates AI image generation (image_gen.py) and web image search (image_search.py) with Pexels/Pixabay. Supports native chart/table replacement (--native-charts-and-tables flag) and a template-fill workflow.
- Finance professionals converting quarterly report PDFs into editable presentations
- Marketers creating branded decks with custom templates and styles for product launches
- Educators turning lecture notes into narrated slides for students
- Data analysts transforming data reports into dashboard-style presentations with native charts and tables
- Teams collaborating on presentations without leaving their AI coding environment
How do you install or deploy this agent?
- Install Python 3.10+.
- Clone the repo:
git clone https://github.com/hugohe3/ppt-master.gitandcd ppt-master, or download a ZIP. - Install dependencies:
pip install -r requirements.txt. - Optionally, configure
.envfile with API keys likeOPENAI_API_KEY,GEMINI_API_KEY,PEXELS_API_KEY, etc.
How do you use this agent?
- Open the project folder in an agent-capable tool like Claude Code.
- Place source materials in the
projects/directory. - Instruct in chat: "Please create a PPT from projects/q3-report/sources/report.pdf".
- Wait for design spec confirmation, or use quick generation: "Quickly generate a 5-page deck, no need to confirm with me".
- Output will be saved to
exports/<name>_<timestamp>.pptx.
What are this agent's strengths and limitations?
- Produces genuinely native, editable PPTX, not flat images
- Supports native charts, animations, narration, and templates
- Runs locally, keeping data private
- Free and open source, only pay for AI model usage
- Actively developed, converging with PowerPoint's native features
- Requires a capable AI model (Kimi K3 or Claude recommended) and image generation (like gpt-image-2) for best results, adding cost
- Learning curve: requires installing Python and using AI tools
- Output may need manual polishing for perfection
- Windows requires extra configuration steps
- Free tier image search (Openverse/Wikimedia) can be inconsistent
How does this agent compare with similar options?
The project does not mention specific alternatives; it positions itself against generic AIPP tools without naming them.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| PPT Master — AI-native PowerPoint generation This agent | 0 · Major gaps | Agent plugin / skillFree + model costs | ★ 64k | today | Python | Claude Code |
| Paper2Slides: Convert Papers to Presentations in One Click | 44 · Major gaps | CLIFree + model costs | ★ 3.8k | 5mo ago | Python | — |
| PPT Agent | 41 · Major gaps | Agent plugin / skillFree + model costs | ★ 912 | 4mo ago | Python | — |
| PPTAgent / DeepPresenter | 34 · Major gaps | CLIFree + model costs | ★ 5.1k | 28d ago | Python | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Insufficient evidence: no concrete implementation of least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, or source attribution. README claims data stays local but no code evidence.
Insufficient evidence: no concrete implementation of self-consistency, dependency availability, or failure messages.
Insufficient evidence: no concrete implementation of audience, capability boundaries, trigger precision, or environment fit.
Insufficient evidence: no concrete implementation of information architecture, install notes, naming stability, examples, known limitations, license, versioning, or maintenance responsibility.
Insufficient evidence: no concrete implementation of output usability, marginal value, or cost-benefit.
Insufficient evidence: no concrete implementation of claim traceability, cross-source corroboration, or fact-inference separation.
- Not found in source: least-privilege scopingGrant only what the task needs: a dedicated account or read-only token, scoped to specific directories and repos.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: data-flow disclosureWatch which external services it contacts (proxy or firewall logs) and keep sensitive data out until you know where it goes.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Not found in source: verifiable attributionInstall from the official repo or registry and check the publisher and URL to avoid look-alike packages.
- Static review based only on README, LICENSE, SECURITY.md, requirements.txt, and deployment workflow; actual code not examined.
- Feature claims in README (e.g., native charts, animations, template support) are not verified in provided files.
- Dependency list lacks specific versions, so dependency security cannot be assessed.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Patch release: fixes from an audit of the issue history. Most of them stop a tool from losing, overwriting or rewriting content while it reports success. Installation and startup - Skill-only installations create projects in your working folder again (703aa72f, #144). Since v6.3.0, project_manager.py init placed projects relative to the installed skill. For an npx skills or plugin installation, that meant .agents/projects/ or the plugin cache, where an update can replace them. Inside a repository checkout nothing changes. …View on GitHub ↗ -
Release notes excerpt
Patch release: fixes for work that the live preview, source conversion and source import could lose without a warning, plus a full pass over the UI strings in every language. Live preview - Unapplied annotations and direct edits now survive a server stop (1fa3768a, #319). Before, they lived only in server memory, and the idle timeout, Exit preview, --shutdown, a kill or a crash before Apply changes discarded them. Closing a laptop lid made this likely: the idle timer counted the suspend time, so the server exited on wake. …View on GitHub ↗ -
Release notes excerpt
Minor release: a browser review page for the design spec, Google's new Nano Banana 2.1 as the default Google image model, and fixes for content that source conversion and PPTX/SVG text round-trips used to lose without a warning. Image generation - Google image generation now defaults to Nano Banana 2.1 (gemini-nano-banana-2.1, GA on 2026-10-06), on the Gemini, OpenRouter (google/gemini-nano-banana-2.1) and fal (google/nano-banana-2.1) backends. Google has deprecated gemini-3.1-flash-image, but has not announced a shutdown date. Nano Banana 2.1 does not offer 512px, so all th …View on GitHub ↗
FAQ
Is PPT Master free?
Is my data safe?
What AI models or API keys do I need?
What should I do if I run into errors or poor output?
skills/ppt-master/SKILL.md.