Add gui-new skill — shareable HTML canvases via API#187
Add gui-new skill — shareable HTML canvases via API#187dylanfeltus wants to merge 1 commit intoopenclaw:mainfrom
Conversation
|
Thanks for the pull request! This repository is read-only and is automatically synced from https://clawhub.ai, so we can’t accept changes here. Please make updates on the website instead. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: dbac2675ca
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| ```bash | ||
| curl -X POST https://gui.new/api/canvas \ | ||
| -H "Content-Type: application/json" \ | ||
| -d '{"html": "<h1>Hello</h1>", "title": "My Canvas"}' |
There was a problem hiding this comment.
The documented -d '{"html": "..."}' pattern breaks for typical HTML because unescaped " (from attributes like class="...") or ' (from JS/HTML content) will produce invalid JSON or terminate the shell string, so the create/update API calls fail on common real-world inputs rather than simple <h1> snippets. Since this is the primary workflow of the skill, the docs should show a safe encoding method (for example reading HTML from a file and JSON-encoding it) instead of inline raw HTML.
Useful? React with 👍 / 👎.
1 participant
gui-new
POST HTML, get a shareable link with real-time sync built in.
What it does: Creates shareable HTML canvases via the gui.new API. Visual output layer for AI agents — dashboards, charts, forms, diagrams become live URLs instead of code blocks.
When to use: Generating visual output, sharing/previewing HTML as a live link, creating Mermaid diagrams as shareable links.
Features:
Real-time input sync across all viewers
State persistence
Built-in component library (charts, tables, kanban, timelines, etc.)
npm and pip SDKs
Free tier, no signup needed
Website: https://gui.new
Docs: https://gui.new/docs
npm: https://npmjs.com/package/gui-new
PyPI: https://pypi.org/project/gui-new/