@mnmn94253156337: Let AI make a PPT for you, and it gives you a bunch of divs and a randomly laid out layout. Click to open, and it looks uglier than what you would have done yourself. What's more annoying is Excel—formulas are written incorrectly, formatting is all over the place, and after generation, you have to manually fix everything from start to finish. You might as well do it yourself. MiniMax open-sourced these four doc…
Summary
MiniMax open-sourced four AI document generation skills (PPT, PDF, Excel, Word), usable without an API key, aiming to solve issues like messy formatting and formula errors in AI-generated documents.
View Cached Full Text
Cached at: 06/08/26, 05:19 AM
Let AI create a PPT for you.
What you get is a pile of <div> elements and a completely random layout. Open it up, and it looks even uglier than what you’d make yourself.
Excel is even more annoying — formulas are all over the place, formatting is a total mess, and after it’s generated you still have to manually fix everything from start to finish. Might as well just do it yourself.
MiniMax has open-sourced these four document skills. PPT, PDF, Excel, Word — each one is genuinely usable.
PPT comes with 18 color schemes and 4 styles — no random layouts. Excel runs a formula check after generation to catch basic errors like #REF! and #VALUE!. PDF offers 15 cover styles, with font colors that auto-adapt — ready to print without any tweaks.
No API Key required. Install and let AI write documents for you.
https://github.com/MiniMax-AI/skills…
MiniMax-AI/skills
Source: https://github.com/MiniMax-AI/skills
MiniMax Skills
Beta — This project is under active development. Skills, APIs, and configuration formats may change without notice. We welcome feedback and contributions.
Development skills for AI coding agents. Plug into your favorite AI coding tool and get structured, production-quality guidance for frontend, fullstack, Android, iOS, and shader development.
Skills
| Skill | Description | Source |
|---|---|---|
frontend-dev | Full-stack frontend development combining premium UI design, cinematic animations (Framer Motion, GSAP), AI-generated media assets via MiniMax API (image, video, audio, music, TTS), persuasive copywriting (AIDA framework), and generative art (p5.js, Three.js, Canvas). Tech stack: React / Next.js, Tailwind CSS. | Official |
fullstack-dev | Full-stack backend architecture and frontend-backend integration. REST API design, auth flows (JWT, session, OAuth), real-time features (SSE, WebSocket), database integration (SQL / NoSQL), production hardening, and release checklist. Guided workflow: requirements → architecture → implementation. | Official |
android-native-dev | Android native application development with Material Design 3. Kotlin / Jetpack Compose, adaptive layouts, Gradle configuration, accessibility (WCAG), build troubleshooting, performance optimization, and motion system. | Official |
ios-application-dev | iOS application development guide covering UIKit, SnapKit, and SwiftUI. Touch targets, safe areas, navigation patterns, Dynamic Type, Dark Mode, accessibility, collection views, and Apple HIG compliance. | Official |
flutter-dev | Flutter cross-platform development covering widget patterns, Riverpod/Bloc state management, GoRouter navigation, performance optimization, and testing strategies. | Official |
react-native-dev | React Native and Expo development guide covering components, styling, animations, navigation, state management, forms, networking, performance optimization, testing, native capabilities, and engineering (project structure, deployment, SDK upgrades, CI/CD). | Official |
shader-dev | Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more. ShaderToy-compatible. | Official |
gif-sticker-maker | Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions. Funko Pop / Pop Mart style, powered by MiniMax Image & Video Generation API. | Official |
minimax-pdf | Generate, fill, and reformat PDF documents with a token-based design system. CREATE polished PDFs from scratch (15 cover styles), FILL existing form fields, or REFORMAT documents into a new design. Print-ready output with typography and color derived from document type. | Official |
pptx-generator | Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. | Official |
minimax-xlsx | Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Covers creating new xlsx from scratch via XML templates, reading and analyzing with pandas, editing existing files with zero format loss, formula recalculation, validation, and professional financial formatting. | Official |
minimax-docx | Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: create new documents from scratch, fill/edit content in existing documents, or apply template formatting with XSD validation gate-check. | Official |
vision-analysis | Analyze, describe, and extract information from images using vision AI models. Supports describe, OCR, UI mockup review, chart data extraction, and object detection. Powered by MiniMax VL API with OpenAI GPT-4V fallback. | Community |
minimax-multimodal-toolkit | Generate voice, music, video, and image content via MiniMax APIs — the unified entry for MiniMax multimodal use cases. Covers TTS (text-to-speech, voice cloning, voice design, multi-segment), music (songs, instrumentals), video (text-to-video, image-to-video, start-end frame, subject reference, templates, long-form multi-scene), image (text-to-image, image-to-image with character reference), and media processing (convert, concat, trim, extract) via FFmpeg. | Official |
minimax-music-gen | Generate vocal songs, instrumentals, and covers using MiniMax Music API. Two modes: Basic (one-liner in, song out) and Advanced Control (edit lyrics, refine prompt, plan structure). Supports lyrics generation, style vocabulary, streaming playback, and iterative feedback. | Official |
buddy-sings | Let your Claude Code pet (/buddy) sing a personalized song. Interprets the pet’s name and personality into a unique cached vocal identity, auto-gathers context (conversation, memory, git history) for themed lyrics, and generates music via minimax-music-gen. | Official |
minimax-music-playlist | Generate personalized playlists by analyzing your music taste. Builds a taste profile (genre, mood, language, vocal preferences), plans a themed tracklist, generates songs with album cover art, and refines the profile from feedback. | Official |
Installation
Claude Code
claude plugin marketplace add https://github.com/MiniMax-AI/skills
claude plugin install minimax-skills
Cursor
git clone https://github.com/MiniMax-AI/skills.git ~/.cursor/minimax-skills
Add to your Cursor settings — point the skills path to ~/.cursor/minimax-skills/skills/.
For Windows setup and verification, see .cursor-plugin/INSTALL.md.
Codex
git clone https://github.com/MiniMax-AI/skills.git ~/.codex/minimax-skills
mkdir -p ~/.agents/skills
ln -s ~/.codex/minimax-skills/skills ~/.agents/skills/minimax-skills
Restart Codex to discover the skills. See .codex/INSTALL.md for Windows instructions and details.
OpenCode
git clone https://github.com/MiniMax-AI/skills.git ~/.minimax-skills
mkdir -p ~/.config/opencode/skills
ln -s ~/.minimax-skills/skills/* ~/.config/opencode/skills/
Restart OpenCode to discover the skills. See .opencode/INSTALL.md for details.
VS Code
This repository does not currently ship a standalone VS Code extension.
If you use VS Code, the supported approach is to run one of the supported CLI tools inside the integrated terminal:
- Codex
- Claude Code
- OpenCode
If you want native local-skills configuration from this repo, use Cursor and follow .cursor-plugin/INSTALL.md.
Contributing
We welcome contributions! Before submitting a PR, please read:
- CONTRIBUTING.md — PR format, skill structure requirements, and development guidelines
- PR Review Rules — automated validation checks and quality review criteria
You can run the validation script locally before submitting:
python .claude/skills/pr-review/scripts/validate_skills.py
⭐ Star History
Credits
Some skills in this repository are inspired by or derived from work by the open-source community. See CREDITS.md for full acknowledgments.
License
Similar Articles
@QingQ77: Enable AI Agents to generate beautifully formatted, information-dense Chinese PPTs through non-destructive text editing https://github.com/GordenSun/GordenPPTSkill… A PPT building skill for AI Agents, comes with 17 …
An open-source project that enables AI Agents to generate beautifully formatted Chinese PPTs through non-destructive text editing, providing 17 hand-crafted Chinese PPTX templates and a complete toolchain.
@hank_aibtc: Dreading presentations, roadshows, or defenses? Layouts and animations can eat up half your day. No more worries: Oh My PPT, this pure local AI PPT wizard, eliminates that pain: Input a topic or drop in a document → AI automatically generates the outline, color scheme, and layout → Conversational editing → One-click export to PDF/PPTX…
Oh My PPT is a locally running AI slideshow generation tool that supports automatic presentation creation from documents or topics, with compatibility for offline operation via Ollama.
@vintcessun: Tonight I discovered a project with a novel approach: using GPT to generate luxurious image-format PPTs, then 'decompiling' them back into editable PPTX. Previously, AI-generated PPTs either stacked templates or only exported images. This one directly follows the 'generate image → parse → assemble' path. The core idea is to decompose the PPT image into four layers: background, frame, icons, and text, then reconstruct by coord...
An open-source project named GordenSuperPPTSkills uses GPT to generate luxurious image-format PPTs, then 'decompiles' them into fully editable PPTX files, solving the pain point of AI-generated content being non-editable. The project is split into three independent skills, supporting either just image generation or just image-to-editable conversion, suitable for Codex environment.
@BTCqzy1: Stop using AI to generate PPT images that you can only view but not edit! I've tried various AI tools for PPT before, and they all produced image mosaics—changing a single word meant starting over from scratch. Then I stumbled upon this GitHub hardcore tool ppt-master (23k stars) with the following highlights: · Outputs native .pp...
Introduces an open-source tool called ppt-master that can generate native editable .pptx files from PDF, Word, web links, etc., with support for animations and voice narration, running locally to protect data security.
@yaohui12138: Recently, big shots like guizang, zarazhangrui, and Hua Shu have open-sourced PPT Skills. I spent a day testing 7 PPT skill projects and here's my conclusion: The core reason why AI-generated PPTs look ugly is not that AI lacks ability, but that you haven't given it the right aesthetic constraints...
The author tested 7 open-source PPT Skill projects and points out that the core reason for ugly AI-generated PPTs is the lack of proper aesthetic constraint systems. These projects improve the design quality of AI-generated PPTs by compiling aesthetic rules, and the author introduces each project's features and suitable scenarios.