https://github.com/danielwpz/decknow

AI-native HTML slides runtime for agent-authored decks.
https://github.com/danielwpz/decknow

Last synced: 29 days ago
JSON representation

AI-native HTML slides runtime for agent-authored decks.

• Host: GitHub
• URL: https://github.com/danielwpz/decknow
• Owner: danielwpz
• License: mit
• Created: 2026-05-25T09:33:38.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2026-05-27T04:43:48.000Z (about 1 month ago)
• Last Synced: 2026-05-27T06:23:36.694Z (about 1 month ago)
• Language: JavaScript
• Size: 508 KB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Agents: AGENTS.md

Awesome Lists containing this project

README

          
# Decknow

![Decknow example deck capability slide](docs/assets/decknow-basic-slide-001.png)

Decknow is an AI-native slide deck runtime.

It turns presentations into semantic HTML that coding agents can write, diff,

validate, inspect, comment on, and build into a single shareable file.

## Why Decknow

Slide decks are usually visual artifacts. That makes them painful for AI agents

to edit reliably.

Decknow treats a deck as source code:

- semantic `dk-*` elements instead of pixel-positioned shapes

- browser preview with point-and-comment feedback for human review

- layout inspection commands for agent-side verification

- built-in responsive runtime for desktop and portrait viewports

- single-file HTML builds for easy sharing

- repo-local plugin packages for themes and components

## How to use

Give this to your AI coding agent:

```text

Clone https://github.com/danielwpz/decknow.git, then read

`decknow/skills/SKILL.md` and follow it.

Use Decknow to create or edit my slide deck as semantic `dk-*` HTML.

Run the dev server so I can review and leave browser comments.

Validate and inspect the deck before reporting done.

Build a single self-contained HTML file when ready.

```