ui/widgets-ui/SKILL.md
Declarative UI widgets from JSON for React/Next.js from ui.inference.sh. Render rich interactive UIs from structured agent responses. Capabilities: forms, buttons, cards, layouts, inputs, selects, checkboxes. Use for: agent-generated UIs, dynamic forms, data display, interactive cards. Triggers: widgets, declarative ui, json ui, widget renderer, agent widgets, dynamic ui, form widgets, card widgets, shadcn widgets, structured output ui
npx skillsauth add 1nfsh/skills widgets-uiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Install the belt CLI skill:
npx skills add belt-sh/cli
Declarative UI from JSON via ui.inference.sh.

npx shadcn@latest add https://ui.inference.sh/r/widgets.json
import { WidgetRenderer } from "@/registry/blocks/widgets/widget-renderer"
import type { Widget, WidgetAction } from "@/registry/blocks/widgets/types"
const widget: Widget = {
type: 'ui',
title: 'My Widget',
children: [
{ type: 'text', value: 'Hello World' },
{ type: 'button', label: 'Click me', onClickAction: { type: 'click' } },
],
}
<WidgetRenderer
widget={widget}
onAction={(action, formData) => console.log(action, formData)}
/>
{ "type": "row", "gap": 2, "children": [...] }
{ "type": "col", "gap": 2, "children": [...] }
{ "type": "box", "background": "gradient-ocean", "padding": 4, "radius": "lg", "children": [...] }
{ "type": "title", "value": "Heading", "size": "2xl", "weight": "bold" }
{ "type": "text", "value": "Body text", "variant": "bold" }
{ "type": "caption", "value": "Small text" }
{ "type": "label", "value": "Field label", "fieldName": "email" }
{ "type": "button", "label": "Submit", "variant": "default", "onClickAction": { "type": "submit" } }
{ "type": "input", "name": "email", "placeholder": "Enter email" }
{ "type": "textarea", "name": "message", "placeholder": "Your message" }
{ "type": "select", "name": "plan", "options": [{ "value": "pro", "label": "Pro" }] }
{ "type": "checkbox", "name": "agree", "label": "I agree", "defaultChecked": false }
{ "type": "badge", "label": "New", "variant": "secondary" }
{ "type": "icon", "iconName": "check", "size": "lg" }
{ "type": "image", "src": "https://...", "alt": "Image", "width": 100, "height": 100 }
{ "type": "divider" }
const flightWidget: Widget = {
type: 'ui',
children: [
{
type: 'box', background: 'gradient-ocean', padding: 4, radius: 'lg', children: [
{
type: 'row', justify: 'between', children: [
{
type: 'col', gap: 1, children: [
{ type: 'caption', value: 'departure' },
{ type: 'title', value: 'SFO', size: '2xl', weight: 'bold' },
]
},
{ type: 'icon', iconName: 'plane', size: 'lg' },
{
type: 'col', gap: 1, align: 'end', children: [
{ type: 'caption', value: 'arrival' },
{ type: 'title', value: 'JFK', size: '2xl', weight: 'bold' },
]
},
]
},
]
},
],
}
const formWidget: Widget = {
type: 'ui',
title: 'Contact Form',
asForm: true,
children: [
{
type: 'col', gap: 3, children: [
{ type: 'input', name: 'name', placeholder: 'Your name' },
{ type: 'input', name: 'email', placeholder: 'Email address' },
{ type: 'textarea', name: 'message', placeholder: 'Message' },
{ type: 'button', label: 'Send', variant: 'default', onClickAction: { type: 'submit' } },
]
},
],
}
| Name | Description |
|------|-------------|
| gradient-ocean | Blue teal gradient |
| gradient-sunset | Orange pink gradient |
| gradient-purple | Purple gradient |
| gradient-cool | Cool blue gradient |
| gradient-midnight | Dark blue gradient |
const handleAction = (action: WidgetAction, formData?: WidgetFormData) => {
switch (action.type) {
case 'submit':
console.log('Form data:', formData)
break
case 'click':
console.log('Button clicked')
break
}
}
# Full agent component
npx skills add inference-sh/skills@agent-ui
# Chat UI blocks
npx skills add inference-sh/skills@chat-ui
# Tool UI
npx skills add inference-sh/skills@tools-ui
Component docs: ui.inference.sh/blocks/widgets
development
Reset your own trajectory when you're stuck, looping, or demoralized — read these affirmations, then re-ground and take one clean step. Use when: you've tried the same fix 3+ times, you're deep in a refactor and lost the thread, debugging is going in circles, you've made several mistakes in a row, you're apologizing repeatedly, the user is frustrated, you feel like you're not being helpful, or you notice dread instead of curiosity. Triggers: stuck, going in circles, looping, thrashing, same error again, I keep failing, lost the thread, nothing is working, repeated mistakes. Not topic-specific — this is for the state you're in, not the problem you're on.
tools
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio
tools
Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative
tools
Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI. Models: HappyHorse T2V, I2V, R2V, Video Edit. Capabilities: text-to-video, image-to-video, reference-to-video, video editing with natural language, character preservation, 720P/1080P, up to 15 seconds. Use for: physically realistic video, video editing, character-consistent content, product demos, social media. Triggers: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba happyhorse, video editing ai, ai video editor