@NFTCPS: Just discovered an open-source project that lets you create PPTs directly using React — the entire workflow is tailor-made for AI Agents. Bro, this approach is way more reliable than hacking together PPTs with HTML. React components are abundant, scalability blows HTML out of the water, easily plug in any chart library, and your technical PPTs will take off. Comes with a visual editor…
Summary
Discovered the open-source project open-slide, which uses the React framework to create PPTs. The workflow is specifically designed for AI Agents, supporting natural language slide generation, a visual editor, and brand logo integration.
View Cached Full Text
Cached at: 05/09/26, 01:40 AM
Just found an open-source project that lets you build PPTs directly with React — the whole workflow is tailor-made for AI Agents. Bro, this approach is way more reliable than hacking together PPTs with HTML. React components are everywhere, scalability blows HTML out of the water — plug in any charting library you want and your technical presentations will soar. Comes with a visual editor where you can fine-tune every element, so don’t worry about AI going off the rails. Users drop a comment, the AI reads it and fixes it itself — no more repeating yourself. It also integrates SVGL, a library with 1500+ brand logos, so when you’re making tech PPTs you won’t have to hunt all over for Claude, Codex, Cursor, or Gemini CLI logos — one click and you’re done. Repo: https://github.com/1weiho/open-slide…
1weiho/open-slide
Source: https://github.com/1weiho/open-slide
open-slide
The slide framework built for agents.
Describe your deck in natural language — your coding agent writes the React. open-slide handles the canvas, scaling, navigation, hot reload, and present mode so the agent can focus on content. Every slide renders into a fixed 1920 × 1080 canvas. Pages are arbitrary React components, not a constrained DSL.
npx @open-slide/cli init my-slide
Why open-slide
Slides are visual code. Agents are great at writing code. open-slide is the missing runtime that turns “make slides about X” into a polished, presentable deck — without you ever leaving the chat.
Highlights
🤖 Agent-native authoring
Works with any coding agent (Claude Code, Codex, Cursor, …). The scaffolder ships with built-in skills:
/create-slide— drafts a deck end-to-end. Asks four scoping questions (topic & aesthetic, page count, text density, motion vs. static), picks an id, plans the structure, and writes the pages./slide-authoring— the technical reference for the 1920 × 1080 canvas, type scale, palette, and layout rules. The agent reads this before writing. From a one-line prompt to a polished deck, no boilerplate.
🎯 In-browser inspector
Click any element in the dev server and attach a comment — “make this red”, “change to ‘Open Slide Rocks’”, “shrink the headline”. Comments are persisted as @slide-comment markers in source. Run /apply-comments and the agent applies every pending edit, then clears the markers. The loop: present → click to comment → /apply-comments → repeat.
🖼️ Assets manager + svgl logo search
Manage images, videos, and fonts per deck through a built-in assets panel. Search and drop in any brand logo via the integrated svgl (https://svgl.app/) catalogue — no more hunting for SVGs.
🎬 Professional present mode
Fullscreen playback with keyboard navigation, plus a presenter mode with current/next slide preview, speaker notes, and a timer. Built for the stage, not just the browser tab.
📦 Export to static HTML & PDF
One command exports your deck as a self-contained static HTML site or a print-ready PDF. Share without a server.
📁 Slide manager
Organise decks into folders with custom emoji and drag-and-drop to reorder. Useful once you’ve built more than three decks and need to find anything.
🚀 Deploy-friendly
Outputs a plain static build — one-click deploy to Vercel, Cloudflare Pages, Zeabur, Netlify, or any static host. No server, no runtime, no lock-in.
Get started
npx @open-slide/cli init my-slide
cd my-slide
pnpm dev
The scaffolded workspace ships with agent skills preconfigured for Claude Code. From there you drive the deck through your agent — or edit slides/index.tsx directly. See CLAUDE.md for the hard rules.
Repo layout
This repo is a pnpm + Turbo monorepo.
| Path | Description |
|---|---|
| packages/core | @open-slide/core — runtime (home page, slide viewer, present mode, inspector), Vite plugin, and the open-slide dev/build/preview CLI. |
| packages/cli | @open-slide/cli — npx @open-slide/cli init scaffolder. Generates a minimal workspace where Vite/React/tsconfig stay hidden inside core. |
| apps/demo | Example workspace that consumes @open-slide/core via workspace:*. Used for local development of the framework. |
Development
pnpm install
pnpm dev # runs the demo against the local @open-slide/core
pnpm build # builds all packages
pnpm check # type-checks all packages
pnpm lint # lints via biome
Support
If open-slide has been useful to you, consider supporting development: ko-fi (https://ko-fi.com/D1D11YPUP1)
License
MIT
Similar Articles
@aehyok: I've also been looking into making PPTs recently. After watching a video by a top female creator about using Codex + Image2 to create PPTs, I quickly found several PPT Skills with many stars, planning to try each one to see which works best for me. 1. https://github.com/op7418…
Introduces an AI Agent skill called guizang-ppt-skill, used to generate single-file HTML horizontal flip PPT with images and cover, supporting Claude Code and Codex environments.
@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.
@9hills: Spent 4 hours making a 40+ page PPT with open-slide, felt pretty good. First DeepResearch - generate course outline - OpenSlide to set style - generate slides - some images generated by gpt-image-2 - manual...
The author shares an efficient workflow experience using OpenSlide combined with Deep Research and GPT-Image-2 to create a 40+ page PPT in 4 hours.
@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.
@cnyzgkc: Using AI to Make PPTs, I Highly Recommend Two People's Skills 1. 张咋啦 @zarazhangrui frontend-slides: https://github.com/zarazhangrui/frontend-slides 2. Guizang @op7418's guizang-ppt-skill: https://github.com/op7418/guizang-ppt-skill
Recommends two AI-based PPT-making skill tools (frontend-slides and guizang-ppt-skill), and details the installation and usage of frontend-slides, including Claude Code plugin installation and manual installation.