interactive-widgets
Skill0 starsChanged 7 months agoApache-2.0View on GitHub
Interactive widget systems for AI applications including LLM-driven widget generation, dynamic UI components, form builders, and streaming response widgets. Use when asking about 'interactive widgets', 'dynamic UI', 'LLM widgets', 'widget generation', 'streaming widgets', 'form widgets', 'AI response widgets', 'structured responses', or 'widget protocol'.
In this repository37 other files it gives its agents.
- .claude/rules/agents.mdAGENTS.md
- .claude/guides/claude-code/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- core-sdkSkill
- dataflowSkill
- nexusSkill
- kaizenSkill
- kailash-mcpSkill
- cheatsheetsSkill
- development-guidesSkill
- nodes-referenceSkill
- workflow-patternsSkill
- deployment-gitSkill
- frontend-integrationSkill
- testing-strategiesSkill
- architecture-decisionsSkill
- code-templatesSkill
- enterprise-infrastructureSkill
- validation-patternsSkill
- gold-standardsSkill
- security-patternsSkill
- flutter-patternsSkill
- enterprise-ai-uxSkill
- conversation-uxSkill
- uiux-design-principlesSkill
- value-auditSkill
- ai-interaction-patternsSkill
- eatp-referenceSkill
- coc-referenceSkill
- 29-pactSkill
- claude-code-patternsSkill
- error-troubleshootingSkill
- kailash-mlSkill
- kailash-alignSkill
- co-referenceSkill
- managementSkill
- projectSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 123
Use this skill when:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Interactive Widget System
Production-ready patterns for building interactive widget systems that integrate with AI/LLM backends for dynamic, structured user interfaces.
Overview
Interactive widget patterns for:
- LLM-driven widget generation
- Streaming response with structured components
- Dynamic form builders
- Action-response patterns
- Widget protocol design
Reference Documentation
System Overview
- overview - Widget system architecture and navigation
- System components
- Documentation structure
- Quick reference
Technical Specification
- technical-spec - Complete technical specification
- Widget protocol design
- Backend integration
- Frontend rendering
- State management
- Error handling
Implementation Guide
- implementation-guide - Step-by-step implementation
- Backend widget generation
- Frontend widget rendering
- Event handling
- Real-world examples
Quick Patterns
Widget Protocol (JSON)
{
"type": "form",
"id": "user-input-form",
"content": {
"fields": [
{
"type": "text",
"name": "query",
"label": "Enter your question",
"required": true
}
],
"actions": [
{
"type": "submit",
"label": "Send",
"action": "submit_query"
}
]
}
}Backend Widget Generation (Python)
def generate_widget_response(user_query: str) -> dict:
"""Generate structured widget response from LLM."""
response = llm.generate(
prompt=f"Generate a widget response for: {user_query}",
output_schema=WidgetSchema
)
return {
"type": response.widget_type,
"content": response.content,
"actions": response.available_actions
}Frontend Widget Renderer (Dart)
Widget buildWidget(Map<String, dynamic> widgetData) {
switch (widgetData['type']) {
case 'form':
return FormWidget(data: widgetData['content']);
case 'card':
return CardWidget(data: widgetData['content']);
case 'table':
return TableWidget(data: widgetData['content']);
default:
return TextWidget(data: widgetData['content']);
}
}Widget Types
| Type | Purpose | Use Case |
text | Plain text response | Simple answers |
card | Structured information | Entity displays |
form | User input collection | Queries, settings |
table | Tabular data | Lists, comparisons |
chart | Data visualization | Analytics, metrics |
action | Clickable actions | Workflows, confirmations |
progress | Progress indication | Long-running tasks |
CRITICAL Gotchas
| Rule | Why |
| ❌ NEVER trust widget IDs from client | Security - validate server-side |
| ✅ ALWAYS validate widget schemas | Prevent malformed rendering |
| ❌ NEVER block UI on widget generation | Use streaming for responsiveness |
| ✅ ALWAYS handle unknown widget types | Graceful degradation |
When to Use This Skill
Use this skill when:
- Building AI chat interfaces with structured responses
- Creating dynamic form systems
- Implementing streaming UI components
- Designing widget protocols for LLM integration
- Building action-response patterns
Related Skills
- 04-kaizen - AI agent framework
- 19-flutter-patterns - Flutter components
- 22-conversation-ux - Conversation UX
Support
For widget system questions, invoke:
kaizen-specialist- LLM integration patternsflutter-specialist- Widget renderingpattern-expert- Protocol design
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

